AI Research News Feeds for November 20th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data : Abstract: Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simp...
• MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features : Abstract: Eye tracking data quantifies the attentional bias towards negative stimuli that is frequently observed in depressed groups. Audio and video data capture the affective flattening and psychomo...
• Hyperspectral Image Classification using Spectral-Spatial Mixer Network : Abstract: This paper introduces SS-MixNet, a lightweight and effective deep learning model for hyperspectral image (HSI) classification. The architecture integrates 3D convolutional layers for local s...
• First Frame Is the Place to Go for Video Content Customization : Abstract: What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this ...
• GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization : Abstract: Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools, leaving a gap toward more general-purpose agentic models...
• RoMa v2: Harder Better Faster Denser Feature Matching : Abstract: Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold-standard due to its high accuracy and robustness. H...
• Application of Graph Based Vision Transformers Architectures for Accurate Temperature Prediction in Fiber Specklegram Sensors : Abstract: Fiber Specklegram Sensors (FSS) are highly effective for environmental monitoring, particularly for detecting temperature variations. However, the nonlinear nature of specklegram data presen...
• Image Denoising Using Transformed L1 (TL1) Regularization via ADMM : Abstract: Total variation (TV) regularization is a classical tool for image denoising, but its convex $\ell_1$ formulation often leads to staircase artifacts and loss of contrast. To address these iss...
• BBox DocVQA: A Large Scale Bounding Box Grounded Dataset for Enhancing Reasoning in Document Visual Question Answer : Abstract: Document Visual Question Answering (DocVQA) is a fundamental task for multimodal document understanding and a key testbed for vision language reasoning. However, most existing DocVQA dataset...
• Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception : Abstract: In embodied AI perception systems, visual perception should be active: the goal is not to passively process static images, but to actively acquire more informative data within pixel and spat...
• Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration : Abstract: Existing multimodal reasoning models and frameworks suffer from fundamental architectural limitations: most lack the human-like ability to autonomously explore diverse reasoning pathways-whe...
• IPR-1: Interactive Physical Reasoner : Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarly acquire human-like reasoning from intera...
• A Novel CustNetGC Boosted Model with Spectral Features for Parkinson's Disease Prediction : Abstract: Parkinson's disease is a neurodegenerative disorder that can be very tricky to diagnose and treat. Such early symptoms can include tremors, wheezy breathing, and changes in voice quality as ...
• MHR: Momentum Human Rig : Abstract: We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum lib...
• Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation : Abstract: Source-free domain adaptation (SFDA) alleviates the domain discrepancy among data obtained from domains without accessing the data for the awareness of data privacy. However, existing conven...
• UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization : Abstract: Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-specialize on...
• MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition : Abstract: In recent years, multimodal Graph Convolutional Networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. The reliance on high-energy-consuming continuous fl...
• Unobtrusive Monitoring of Simulated Physical Weakness Using Fine-Grained Behavioral Features and Personalized Modeling : Abstract: Aging and chronic conditions affect older adults' daily lives, making early detection of developing health issues crucial. Weakness, common in many conditions, alters physical movements and ...
• Self Pre-training with Topology- and Spatiality-aware Masked Autoencoders for 3D Medical Image Segmentation : Abstract: Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel i...
• MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation : Abstract: Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions. While pre...
• Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models : Abstract: Multimodal Large Language Models (MLLMs) have garnered significant attention recently and demonstrate outstanding capabilities in various tasks such as OCR, VQA, captioning, $\textit{etc}$. ...
• Integration of nested cross-validation, automated hyperparameter optimization, high-performance computing to reduce and quantify the variance of test performance estimation of deep learning models : Abstract: Background and Objectives: The variability and biases in the real-world performance benchmarking of deep learning models for medical imaging compromise their trustworthiness for real-world d...
• Beyond Diagnosis: Evaluating Multimodal LLMs for Pathology Localization in Chest Radiographs : Abstract: Recent work has shown promising performance of frontier large language models (LLMs) and their multimodal counterparts in medical quizzes and diagnostic tasks, highlighting their potential f...
• DeepContrast: Deep Tissue Contrast Enhancement using Synthetic Data Degradations and OOD Model Predictions : Abstract: Microscopy images are crucial for life science research, allowing detailed inspection and characterization of cellular and tissue-level structures and functions. However, microscopy data are...
• RN-SDEs: Limited-Angle CT Reconstruction with Residual Null-Space Diffusion Stochastic Differential Equations : Abstract: Computed tomography is a widely used imaging modality with applications ranging from medical imaging to material analysis. One major challenge arises from the lack of scanning information at...
• Human-AI Collaboration and Explainability for 2D/3D Registration Quality Assurance : Abstract: Purpose: As surgery increasingly integrates advanced imaging, algorithms, and robotics to automate complex tasks, human judgment of system correctness remains a vital safeguard for patient s...
• Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting : Abstract: The recent introduction of 3D Gaussian Splatting (3DGS) has significantly advanced novel view synthesis. Several studies have further improved the rendering quality of 3DGS, yet they still e...
• An Event-triggered System for Social Persuasion and Danger Alert in Elder Home Monitoring : Abstract: In the study, the physical state and mental state of elders are both considered, and an event-triggered system has developed to detect events: watch dog, danger notice and photo link. By ado...
• Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation : Abstract: Few-shot segmentation has garnered significant attention. Many recent approaches attempt to introduce the Segment Anything Model (SAM) to handle this task. With the strong generalization abi...
• SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection : Abstract: Accurate, up-to-date High-Definition (HD) maps are critical for urban planning, infrastructure monitoring, and autonomous navigation. However, these maps quickly become outdated as environme...
• Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance : Abstract: Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual...
• Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation : Abstract: Self-supervised depth estimation has gained significant attention in autonomous driving and robotics. However, existing methods exhibit substantial performance degradation under adverse weat...
• MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction : Abstract: This paper proposes a novel metric for Human Motion Prediction (HMP). Since a single past sequence can lead to multiple possible futures, a probabilistic HMP method predicts such multiple mo...
• Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset : Abstract: The applicability of current lesion segmentation models for chest X-rays (CXRs) has been limited both by a small number of target labels and the reliance on long, detailed expert-level text ...
• Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition : Abstract: Reference-based object composition methods fail when inserting real-world objects into stylized domains. This under-explored problem is currently split between practical "blenders" that lack...
• Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval : Abstract: This paper addresses the challenges of learning representations for recipes and food images in the cross-modal retrieval problem. As the relationship between a recipe and its cooked dish is ...
• Physics-Based Benchmarking Metrics for Multimodal Synthetic Images : Abstract: Current state of the art measures like BLEU, CIDEr, VQA score, SigLIP-2 and CLIPScore are often unable to capture semantic or structural accuracy, especially for domain-specific or context-d...
• SkinGPT-R1: Adapter-Only Dual Distillation for Efficient Dermatology Reasoning : Abstract: We present SkinGPT-R1, a dermatology focused vision language model that makes diagnostic chain of thought reasoning explicit, step by step, and verifiable. To support skin specific reasoning...
• SplitFlux: Learning to Decouple Content and Style from a Single Image : Abstract: Disentangling image content and style is essential for customized image generation. Existing SDXL-based methods struggle to achieve high-quality results, while the recently proposed Flux mod...
• Edge-Centric Relational Reasoning for 3D Scene Graph Prediction : Abstract: 3D scene graph prediction aims to abstract complex 3D environments into structured graphs consisting of objects and their pairwise relationships. Existing approaches typically adopt object-c...
• Taming Generative Synthetic Data for X-ray Prohibited Item Detection : Abstract: Training prohibited item detection models requires a large amount of X-ray security images, but collecting and annotating these images is time-consuming and laborious. To address data insuff...
• Text2Loc++: Generalizing 3D Point Cloud Localization from Natural Language : Abstract: We tackle the problem of localizing 3D point cloud submaps using complex and diverse natural language descriptions, and present Text2Loc++, a novel neural network designed for effective cros...
• Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models : Abstract: 3D Vision-Language Foundation Models (VLFMs) have shown strong generalization and zero-shot recognition capabilities in open-world point cloud processing tasks. However, these models often u...
• A Multimodal Transformer Approach for UAV Detection and Aerial Object Recognition Using Radar, Audio, and Video Data : Abstract: Unmanned aerial vehicle (UAV) detection and aerial object recognition are critical for modern surveillance and security, prompting a need for robust systems that overcome limitations of sing...
• What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs : Abstract: Split DNNs enable edge devices by offloading intensive computation to a cloud server, but this paradigm exposes privacy vulnerabilities, as the intermediate features can be exploited to reco...
• Adaptive thresholding pattern for fingerprint forgery detection : Abstract: Fingerprint liveness detection systems have been affected by spoofing, which is a severe threat for fingerprint-based biometric systems. Therefore, it is crucial to develop some techniques t...
• IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers : Abstract: Previous Quantization-Aware Training (QAT) methods for vision transformers rely on expensive retraining to recover accuracy loss in non-linear layer quantization, limiting their use in resou...
• Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training : Abstract: Understanding complex human activities demands the ability to decompose motion into fine-grained, semantic-aligned sub-actions. This motion grounding process is crucial for behavior analysis...
• Breaking Expert Knowledge Limits: Self-Pruning for Large Language Models : Abstract: Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size. Existing pruning methods (e.g., Wanda) ...
• ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation : Abstract: Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and sever...
• EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects : Abstract: Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi...
• Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detection : Abstract: Multimodal object detection has attracted significant attention in both academia and industry for its enhanced robustness. Although numerous studies have focused on improving modality fusion...
• HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented Generation : Abstract: Advanced multimodal Retrieval-Augmented Generation (MRAG) techniques have been widely applied to enhance the capabilities of Large Multimodal Models (LMMs), but they also bring along novel s...
• A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturing : Abstract: Remanufacturing describes a process where worn products are restored to like-new condition and it offers vast ecological and economic potentials. A key step is the quality inspection of disa...
• Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras : Abstract: Object detection in autonomous driving suffers from motion blur and saturation under fast motion and extreme lighting. Spike cameras, offer microsecond latency and ultra high dynamic range f...
• Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners : Abstract: Purse seiners play a crucial role in tuna fishing, as approximately 69% of the world's tropical tuna is caught using this gear. All tuna Regional Fisheries Management Organizations have esta...
• FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI : Abstract: Densely annotated medical image datasets that capture not only diagnostic labels but also the underlying reasoning behind these diagnoses are scarce. Such reasoning-related annotations are e...
• Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels : Abstract: Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement m...
• Learning to Expand Images for Efficient Visual Autoregressive Modeling : Abstract: Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from ...
• Multi-Text Guided Few-Shot Semantic Segmentation : Abstract: Recent CLIP-based few-shot semantic segmentation methods introduce class-level textual priors to assist segmentation by typically using a single prompt (e.g., a photo of class). However, the...
• A Hybrid CNN-ViT-GNN Framework with GAN-Based Augmentation for Intelligent Weed Detection in Precision Agriculture : Abstract: The task of weed detection is an essential element of precision agriculture since accurate species identification allows a farmer to selectively apply herbicides and fits into sustainable ag...
• Scriboora: Rethinking Human Pose Forecasting : Abstract: Human pose forecasting predicts future poses based on past observations, and has many significant applications in areas such as action recognition, autonomous driving or human-robot interact...
• Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector : Abstract: Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition. In view of antiforensics, it is significant to develop advanced adversarial attacks for evaluati...
• From Low-Rank Features to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers : Abstract: Feature-map knowledge distillation (KD) is highly effective for convolutional networks but often fails for Vision Transformers (ViTs). To understand this failure and guide method design, we ...
• AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning : Abstract: With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large visio...
• CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking : Abstract: 3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point...
• Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition : Abstract: LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments ...
• MaskMed: Decoupled Mask and Class Prediction for Medical Image Segmentation : Abstract: Medical image segmentation typically adopts a point-wise convolutional segmentation head to predict dense labels, where each output channel is heuristically tied to a specific class. This ri...
• FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation : Abstract: Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in...
• The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification : Abstract: Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identifi...
• Multi-Stage Residual-Aware Unsupervised Deep Learning Framework for Consistent Ultrasound Strain Elastography : Abstract: Ultrasound Strain Elastography (USE) is a powerful non-invasive imaging technique for assessing tissue mechanical properties, offering crucial diagnostic value across diverse clinical applic...
• MambaIO: Global-Coordinate Inertial Odometry for Pedestrians via Multi-Scale Frequency-Decoupled Modeling : Abstract: Inertial Odometry (IO) enables real-time localization using only acceleration and angular velocity measurements from an Inertial Measurement Unit (IMU), making it a promising solution for lo...
• INQUIRE-Search: A Framework for Interactive Discovery in Large-Scale Biodiversity Databases : Abstract: Large community science platforms such as iNaturalist contain hundreds of millions of biodiversity images that often capture ecological context on behaviors, interactions, phenology, and hab...
• GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI : Abstract: Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framework spanning...
• Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization : Abstract: Embeddings have become a cornerstone in the functionality of large language models (LLMs) due to their ability to transform text data into rich, dense numerical representations that capture ...
• Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video : Abstract: We present Gaussian See, Gaussian Do, a novel approach for semantic 3D motion transfer from multiview video. Our method enables rig-free, cross-category motion transfer between objects with ...
• When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation : Abstract: Accurate identification and segmentation of dental caries in panoramic radiographs are critical for early diagnosis and effective treatment planning. Automated segmentation remains challengi...
• B-Rep Distance Functions (BR-DF): How to Represent a B-Rep Model by Volumetric Distance Functions? : Abstract: This paper presents a novel geometric representation for CAD Boundary Representation (B-Rep) based on volumetric distance functions, dubbed B-Rep Distance Functions (BR-DF). BR-DF encodes th...
• GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis : Abstract: Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for...
• InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization : Abstract: We address the task of multi-view image editing from sparse input views, where the inputs can be seen as a mix of images capturing the scene from different viewpoints. The goal is to modify ...
• FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding : Abstract: As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specif...
• nnMIL: A generalizable multiple instance learning framework for computational pathology : Abstract: Computational pathology holds substantial promise for improving diagnosis and guiding treatment decisions. Recent pathology foundation models enable the extraction of rich patch-level repres...
• X-WIN: Building Chest Radiograph World Model via Predictive Sensing : Abstract: Chest X-ray radiography (CXR) is an essential medical imaging technique for disease diagnosis. However, as 2D projectional images, CXRs are limited by structural superposition and hence fail...
• CPSL: Representing Volumetric Video via Content-Promoted Scene Layers : Abstract: Volumetric video enables immersive and interactive visual experiences by supporting free viewpoint exploration and realistic motion parallax. However, existing volumetric representations fro...
• Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities : Abstract: Periodic human activities with implicit workflows are common in manufacturing, sports, and daily life. While short-term periodic activities -- characterized by simple structures and high-con...
• RocSync: Millisecond-Accurate Temporal Synchronization for Heterogeneous Camera Systems : Abstract: Accurate spatiotemporal alignment of multi-view video streams is essential for a wide range of dynamic-scene applications such as multi-view 3D reconstruction, pose estimation, and scene und...
• FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR Evaluation : Abstract: We introduce FinCriticalED (Financial Critical Error Detection), a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level. Financial document...
• WarNav: An Autonomous Driving Benchmark for Segmentation of Navigable Zones in War Scenes : Abstract: We introduce WarNav, a novel real-world dataset constructed from images of the open-source DATTALION repository, specifically tailored to enable the development and benchmarking of semantic ...
• CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification : Abstract: Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matchi...
• Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans : Abstract: Mathematical thinking is a fundamental aspect of human cognition. Cognitive scientists have investigated the mechanisms that underlie our ability to thinking geometrically and numerically, t...
• UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space : Abstract: In the field of human-object interaction (HOI), detection and generation are two dual tasks that have traditionally been addressed separately, hindering the development of comprehensive inte...
• Hyperspectral Super-Resolution with Inter-Image Variability via Degradation-based Low-Rank and Residual Fusion Method : Abstract: The fusion of hyperspectral image (HSI) with multispectral image (MSI) provides an effective way to enhance the spatial resolution of HSI. However, due to different acquisition conditions, t...
• CellGenNet: A Knowledge-Distilled Framework for Robust Cell Segmentation in Cancer Tissues : Abstract: Accurate nuclei segmentation in microscopy whole slide images (WSIs) remains challenging due to variability in staining, imaging conditions, and tissue morphology. We propose CellGenNet, a k...
• ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling : Abstract: Existing approaches for the problem of ultrasound image segmentation, whether supervised or semi-supervised, are typically specialized for specific anatomical structures or tasks, limiting t...
• Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks : Abstract: Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in la...
• BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching : Abstract: Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perfor...
• MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation : Abstract: Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer f...
• TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition : Abstract: Multimodal Emotion Recognition (MER) aims to accurately identify human emotional states by integrating heterogeneous modalities such as visual, auditory, and textual data. Existing approache...
• Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis : Abstract: Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned diffusion ...
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models : Abstract: Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirec...
• Computer-Use Agents as Judges for Generative User Interface : Abstract: Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed primarily fo...
• SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models : Abstract: Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance...
• When to Think and When to Look: Uncertainty-Guided Lookback : Abstract: Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision la...
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping : Abstract: Mixture-of-Experts (MoE) Multimodal large language models (MLLMs) excel at vision-language tasks, but they suffer from high computational inefficiency. To reduce inference overhead, expert s...
• Think Visually, Reason Textually: Vision-Language Synergy in ARC : Abstract: Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation r...
• MessIRve: A Large-Scale Spanish Information Retrieval Dataset : Abstract: Information retrieval (IR) is the task of finding relevant documents in response to a user query. Although Spanish is the second most spoken native language, there are few Spanish IR dataset...
• Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts? : Abstract: Human understanding of text depends on general semantic concepts of words rather than their superficial forms. To what extent does our human intuition transfer to language models? In this wo...
• Decentralized Gaussian Process Classification and an Application in Subsea Robotics : Abstract: Teams of cooperating autonomous underwater vehicles (AUVs) rely on acoustic communication for coordination, yet this communication medium is constrained by limited range, multi-path effects,...
• Convergence and Sketching-Based Efficient Computation of Neural Tangent Kernel Weights in Physics-Based Loss : Abstract: In multi-objective optimization, multiple loss terms are weighted and added together to form a single objective. These weights are chosen to properly balance the competing losses according t...
• A Physics Informed Machine Learning Framework for Optimal Sensor Placement and Parameter Estimation : Abstract: Parameter estimation remains a challenging task across many areas of engineering. Because data acquisition can often be costly, limited, or prone to inaccuracies (noise, uncertainty) it is c...
• US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery : Abstract: Ultrasound offers a radiation-free, cost-effective solution for real-time visualization of spinal landmarks, paraspinal soft tissues and neurovascular structures, making it valuable for intr...
• Near-optimal delta-convex estimation of Lipschitz functions : Abstract: This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on its convergence rate. The approach extends ma...
• CODE-II: A large-scale dataset for artificial intelligence in ECG analysis : Abstract: Data-driven methods for electrocardiogram (ECG) interpretation are rapidly progressing. Large datasets have enabled advances in artificial intelligence (AI) based ECG analysis, yet limitatio...
• Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning : Abstract: Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable features via m...
• R\'enyi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincar\'e Inequalities : Abstract: Characterizing the differential privacy (DP) of learning algorithms has become a major challenge in recent years. In parallel, many studies suggested investigating the behavior of stochastic...
• VisPlay: Self-Evolving Vision-Language Models from Images : Abstract: Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annota...
• Front-door Reducibility: Reducing ADMGs to the Standard Front-door Setting via a Graphical Criterion : Abstract: Front-door adjustment provides a simple closed-form identification formula under the classical front-door criterion, but its applicability is often viewed as narrow and strict. Although ID a...
• RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food Rescue : Abstract: Food rescue organizations simultaneously tackle food insecurity and waste by working with volunteers to redistribute food from donors who have excess to recipients who need it. Volunteer fee...
• Tokenisation over Bounded Alphabets is Hard : Abstract: Recent works have shown that tokenisation is NP-complete. However, these works assume tokenisation is applied to inputs with unboundedly large alphabets -- an unrealistic assumption, given t...
• Resource-Constrained Decentralized Federated Learning via Personalized Event-Triggering : Abstract: Federated learning (FL) is a popular technique for distributing machine learning (ML) across a set of edge devices. In this paper, we study fully decentralized FL, where in addition to devic...
• Explaining Time Series Classification Predictions via Causal Attributions : Abstract: Despite the excelling performance of machine learning models, understanding their decisions remains a long-standing goal. Although commonly used attribution methods from explainable AI attem...
• ExDAG: an MIQP Algorithm for Learning DAGs : Abstract: There has been a growing interest in causal learning in recent years. Commonly used representations of causal structures, including Bayesian networks and structural equation models (SEM), ta...
• Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Tensorflow Pretrained Models : Abstract: The application of TensorFlow pre-trained models in deep learning is explored, with an emphasis on practical guidance for tasks such as image classification and object detection. The study c...
• Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration : Abstract: Gradient clipping has long been considered essential for ensuring the convergence of Stochastic Gradient Descent (SGD) in the presence of heavy-tailed gradient noise. In this paper, we revis...
• xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories : Abstract: Time series data is prevalent across numerous fields, necessitating the development of robust and accurate forecasting models. Capturing patterns both within and between temporal and multiva...
• Coresets from Trajectories: Selecting Data via Correlation of Loss Differences : Abstract: Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Correlati...
• Optimizing In-Context Learning for Efficient Full Conformal Prediction : Abstract: Reliable uncertainty quantification is critical for trustworthy AI. Conformal Prediction (CP) provides prediction sets with distribution-free coverage guarantees, but its two main variants f...
• Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequality : Abstract: We present a new framework for analysing the Expectation Maximization (EM) algorithm. Drawing on recent advances in the theory of gradient flows over Euclidean-Wasserstein spaces, we extend ...
• Towards Data Valuation via Asymmetric Data Shapley : Abstract: As data emerges as a vital driver of technological and economic advancements, a key challenge is accurately quantifying its value in algorithmic decision-making. The Shapley value, a well-es...
• Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning : Abstract: This study investigates the feasibility of using electrocardiogram (ECG) data combined with basic patient metadata to estimate and monitor prompt laboratory abnormalities. We use the MIMIC-I...
• Beacon2Science: Enhancing STEREO/HI beacon data with machine learning for efficient CME tracking : Abstract: Observing and forecasting coronal mass ejections (CME) in real-time is crucial due to the strong geomagnetic storms they can generate that can have a potentially damaging effect, for example...
• Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective : Abstract: With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time ...
• Temporal Predictors of Outcome in Reasoning Language Models : Abstract: The chain-of-thought (CoT) paradigm uses the elicitation of step-by-step rationales as a proxy for reasoning, gradually refining the model's latent representation of a solution. However, it ...
• LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs : Abstract: Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior exposure dur...
• COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation : Abstract: Large language models (LLMs) often generate fluent but factually incorrect statements despite having access to relevant evidence, a failure mode rooted in how they allocate attention between...
• The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech : Abstract: Spontaneous speech presents several challenges for speech synthesis, particularly in capturing the natural flow of conversation, including turn-taking, pauses, and disfluencies. Although spe...
• Human or LLM as Standardized Patients? A Comparative Study for Medical Education : Abstract: Standardized Patients (SP) are indispensable for clinical skills training but remain expensive, inflexible, and difficult to scale. Existing large-language-model (LLM)-based SP simulators pr...
• Opinion Mining and Analysis Using Hybrid Deep Neural Networks : Abstract: Understanding customer attitudes has become a critical component of decision-making due to the growing influence of social media and e-commerce. Text-based opinions are the most structured, ...
• Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation : Abstract: Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, w...
• OEMA: Ontology-Enhanced Multi-Agent Collaboration Framework for Zero-Shot Clinical Named Entity Recognition : Abstract: Clinical named entity recognition (NER) is crucial for extracting information from electronic health records (EHRs), but supervised models like CRF and BioClinicalBERT require costly annotat...
• Context Cascade Compression: Exploring the Upper Limits of Text Compression : Abstract: Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the fea...
• IndicGEC: Powerful Models, or a Measurement Mirage? : Abstract: In this paper, we report the results of the TeamNRC's participation in the BHASHA-Task 1 Grammatical Error Correction shared task https://github.com/BHASHA-Workshop/IndicGEC2025/ for 5 India...
• MAPROC at AHaSIS Shared Task: Few-Shot and Sentence Transformer for Sentiment Analysis of Arabic Hotel Reviews : Abstract: Sentiment analysis of Arabic dialects presents significant challenges due to linguistic diversity and the scarcity of annotated data. This paper describes our approach to the AHaSIS shared t...
• Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models : Abstract: We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for large language models (LLMs). Across 25 frontier proprietary and open-weight models, ...
• HEAD-QA v2: Expanding a Healthcare Benchmark for Reasoning : Abstract: We introduce HEAD-QA v2, an expanded and updated version of a Spanish/English healthcare multiple-choice reasoning dataset originally released by Vilares and Gómez-Rodríguez (2019). The upda...
• The Empowerment of Science of Science by Large Language Models: New Tools and Methods : Abstract: Large language models (LLMs) have exhibited exceptional capabilities in natural language understanding and generation, image recognition, and multimodal tasks, charting a course towards AGI ...
• A Compliance-Preserving Retrieval System for Aircraft MRO Task Search : Abstract: Aircraft Maintenance Technicians (AMTs) spend up to 30% of work time searching manuals, a documented efficiency bottleneck in MRO operations where every procedure must be traceable to certif...
• DEPO: Dual-Efficiency Preference Optimization for LLM Agents : Abstract: Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cos...
• NAMeGEn: Creative Name Generation via A Novel Agent-based Multiple Personalized Goal Enhancement Framework : Abstract: Trained on diverse human-authored texts, Large Language Models (LLMs) unlocked the potential for Creative Natural Language Generation (CNLG), benefiting various applications like advertising...
• Building Robust and Scalable Multilingual ASR for Indian Languages : Abstract: This paper describes the systems developed by SPRING Lab, Indian Institute of Technology Madras, for the ASRU MADASR 2.0 challenge. The systems developed focuses on adapting ASR systems to i...
• LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering : Abstract: Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their di...
• Standardising the NLP Workflow: A Framework for Reproducible Linguistic Analysis : Abstract: The introduction of large language models and other influential developments in AI-based language processing have led to an evolution in the methods available to quantitatively analyse langu...
• Multimodal Evaluation of Russian-language Architectures : Abstract: Multimodal large language models (MLLMs) are currently at the center of research attention, showing rapid progress in scale and capabilities, yet their intelligence, limitations, and risks r...
• HSKBenchmark: Modeling and Benchmarking Chinese Second Language Acquisition in Large Language Models through Curriculum Tuning : Abstract: Language acquisition is vital to revealing the nature of human language intelligence and has recently emerged as a promising perspective for improving the interpretability of large language ...
• Optimizing Agricultural Research: A RAG-Based Approach to Mycorrhizal Fungi Information : Abstract: Retrieval-Augmented Generation (RAG) represents a transformative approach within natural language processing (NLP), combining neural information retrieval with generative language modeling t...
• Skin-R1: Toward Trustworthy Clinical Reasoning for Dermatological Diagnosis : Abstract: The emergence of vision-language models (VLMs) has opened new possibilities for clinical reasoning and has shown promising performance in dermatological diagnosis. However, their trustworthi...
• Evaluating Multimodal Large Language Models on Vertically Written Japanese Text : Abstract: Multimodal Large Language Models (MLLMs) have seen rapid advances in recent years and are now being applied to visual document understanding tasks. They are expected to process a wide range ...
• ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based Progression : Abstract: In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RA...
• Knowledge-Informed Automatic Feature Extraction via Collaborative Large Language Model Agents : Abstract: The performance of machine learning models on tabular data is critically dependent on high-quality feature engineering. While Large Language Models (LLMs) have shown promise in automating fe...
• CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries : Abstract: We introduce CASTELLA, a human-annotated audio benchmark for the task of audio moment retrieval (AMR). Although AMR has various useful potential applications, there is still no established b...
• M, Toolchain and Language for Reusable Model Compilation : Abstract: Complex software-driven systems often interleave distributed, concurrent computation processes with physical interactions with the environment. Developing these systems more efficiently and ...
• ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing : Abstract: Chart editing reduces manual effort in visualization design. Typical benchmarks limited in data diversity and assume access to complete chart code, which is seldom in real-world scenarios. T...
• SkyEgg: Joint Implementation Selection and Scheduling for Hardware Synthesis using E-graphs : Abstract: Hardware synthesis from high-level descriptions remains fundamentally limited by the sequential optimization of interdependent design decisions. Current methodologies, including state-of-the...
• CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search : Abstract: Dense retrieval has become a foundational paradigm in modern search systems, especially on short-video platforms. However, most industrial systems adopt a self-reinforcing training pipeline ...
• From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs : Abstract: The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify thei...
• Cross-Modal Consistency-Guided Active Learning for Affective BCI Systems : Abstract: Deep learning models perform best with abundant, high-quality labels, yet such conditions are rarely achievable in EEG-based emotion recognition. Electroencephalogram (EEG) signals are easil...
• Complex variational autoencoders admit K\"ahler structure : Abstract: It has been discovered that latent-Euclidean variational autoencoders (VAEs) admit, in various capacities, Riemannian structure. We adapt these arguments but for complex VAEs with a complex ...
• FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model : Abstract: In industrial equipment monitoring, fault diagnosis is critical for ensuring system reliability and enabling predictive maintenance. However, the scarcity of fault data, due to the rarity of...
• Vehicle Routing Problems via Quantum Graph Attention Network Deep Reinforcement Learning : Abstract: The vehicle routing problem (VRP) is a fundamental NP-hard task in intelligent transportation systems with broad applications in logistics and distribution. Deep reinforcement learning (DRL)...
• Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning : Abstract: Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR su...
• Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones : Abstract: Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for d...
• D2D Power Allocation via Quantum Graph Neural Network : Abstract: Increasing wireless network complexity demands scalable resource management. Classical GNNs excel at graph learning but incur high computational costs in large-scale settings. We present a f...
• EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control : Abstract: Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in this context...
• Optimized scheduling of electricity-heat cooperative system considering wind energy consumption and peak shaving and valley filling : Abstract: With the global energy transition and rapid development of renewable energy, the scheduling optimization challenge for combined power-heat systems under new energy integration and multiple u...
• PLATONT: Learning a Platonic Representation for Unified Network Tomography : Abstract: Network tomography aims to infer hidden network states, such as link performance, traffic load, and topology, from external observations. Most existing methods solve these problems separatel...
• GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning : Abstract: The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as ...
• SNAP: Low-Latency Test-Time Adaptation with Sparse Updates : Abstract: Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, ...
• Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs : Abstract: Specialized edge accelerators rely on low-bit quantization, but vendor compilers differ in scaling, clipping, and kernel support, often as black boxes. The same floating-point (FP) checkpoin...
• On the Internal Semantics of Time-Series Foundation Models : Abstract: Time-series Foundation Models (TSFMs) have recently emerged as a universal paradigm for learning across diverse temporal domains. However, despite their empirical success, the internal mecha...
• KrawtchoukNet: A Unified GNN Solution for Heterophily and Over-smoothing with Adaptive Bounded Polynomials : Abstract: Spectral Graph Neural Networks (GNNs) based on polynomial filters, such as ChebyNet, suffer from two critical limitations: 1) performance collapse on "heterophilic" graphs and 2) performance...
• LaguerreNet: Advancing a Unified Solution for Heterophily and Over-smoothing with Adaptive Continuous Polynomials : Abstract: Spectral Graph Neural Networks (GNNs) suffer from two critical limitations: poor performance on "heterophilic" graphs and performance collapse at high polynomial degrees (K), known as over-s...
• STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Detection : Abstract: Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging. Standard reconstruction-based methods, includin...
• Multi-layer Stack Ensembles for Time Series Forecasting : Abstract: Ensembling is a powerful technique for improving the accuracy of machine learning models, with methods like stacking achieving strong results in tabular tasks. In time series forecasting, ho...
• Cost-Aware Prediction (CAP): An LLM-Enhanced Machine Learning Pipeline and Decision Support System for Heart Failure Mortality Prediction : Abstract: Objective: Machine learning (ML) predictive models are often developed without considering downstream value trade-offs and clinical interpretability. This paper introduces a cost-aware predi...
• CID: Measuring Feature Importance Through Counterfactual Distributions : Abstract: Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous methods exist, the lack of a definitive grou...
• Parameter Importance-Driven Continual Learning for Foundation Models : Abstract: Domain-specific post-training often causes catastrophic forgetting, making foundation models lose their general reasoning ability and limiting their adaptability to dynamic real-world enviro...
• EVA-Net: Interpretable Brain Age Prediction via Continuous Aging Prototypes from EEG : Abstract: The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medica...
• Proximal Approximate Inference in State-Space Models : Abstract: We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangian formulation that casts Bayesian inferen...
• Towards Understanding Layer Contributions in Tabular In-Context Learning Models : Abstract: Despite the architectural similarities between tabular in-context learning (ICL) models and large language models (LLMs), little is known about how individual layers contribute to tabular pr...
• TSFM in-context learning for time-series classification of bearing-health status : Abstract: This paper introduces a classification method using in-context learning in time-series foundation models (TSFM). We show how data, which was not part of the TSFM training data corpus, can be...
• FairEnergy: Contribution-Based Fairness meets Energy Efficiency in Federated Learning : Abstract: Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy. However, balancing energy efficiency and fair participation while ensur...
• NTK-Guided Implicit Neural Teaching : Abstract: Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3...
• Sample-Adaptivity Tradeoff in On-Demand Sampling : Abstract: We study the tradeoff between sample complexity and round complexity in on-demand sampling, where the learning algorithm adaptively samples from $k$ distributions over a limited number of ro...
• PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles : Abstract: Runtime geofencing for ground vehicles is rapidly emerging as a critical technology for enforcing Operational Design Domains (ODDs). However, existing solutions struggle to reconcile high-fi...
• CODE: A global approach to ODE dynamics learning : Abstract: Ordinary differential equations (ODEs) are a conventional way to describe the observed dynamics of physical systems. Scientists typically hypothesize about dynamical behavior, propose a math...
• Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open Challenges : Abstract: Continual learning (CL) is a branch of machine learning that aims to enable agents to adapt and generalise previously learned abilities so that these can be reapplied to new tasks or environ...
• DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models : Abstract: Enabling Vision-Language-Action (VLA) models to "think before acting" via Chain-of-Thought (CoT) is a promising path to overcoming the data-hungry nature of end-to-end robot policies. Howeve...
• Walrus: A Cross-Domain Foundation Model for Continuum Dynamics : Abstract: Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-...
• The Impact of Quantization on Large Reasoning Model Reinforcement Learning : Abstract: Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aw...
• Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications : Abstract: Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer...
• Reservoir Computing via Multi-Scale Random Fourier Features for Forecasting Fast-Slow Dynamical Systems : Abstract: Forecasting nonlinear time series with multi-scale temporal structures remains a central challenge in complex systems modeling. We present a novel reservoir computing framework that combines...
• Convex Clustering Redefined: Robust Learning with the Median of Means Estimator : Abstract: Clustering approaches that utilize convex loss functions have recently attracted growing interest in the formation of compact data clusters. Although classical methods like k-means and its w...
• MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging : Abstract: Modeling genomic sequences faces two unsolved challenges: the information density varies widely across different regions, while there is no clearly defined minimum vocabulary unit. Relying o...
• Fully Differentiable dMRI Streamline Propagation in PyTorch : Abstract: Diffusion MRI (dMRI) provides a distinctive means to probe the microstructural architecture of living tissue, facilitating applications such as brain connectivity analysis, modeling across m...
• Implicit Bias of the JKO Scheme : Abstract: Wasserstein gradient flow provides a general framework for minimizing an energy functional $J$ over the space of probability measures on a Riemannian manifold $(M,g)$. Its canonical time-dis...
• How to pick the best anomaly detector? : Abstract: Anomaly detection has the potential to discover new physics in unexplored regions of the data. However, choosing the best anomaly detector for a given data set in a model-agnostic way is an ...
• Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings : Abstract: Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality....
• Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard : Abstract: To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom modules. Although numerous prior works have show...
• Exact Learning of Weighted Graphs Using Composite Queries : Abstract: In this paper, we study the exact learning problem for weighted graphs, where we are given the vertex set, $V$, of a weighted graph, $G=(V,E,w)$, but we are not given $E$. The problem, which...
• HULFSynth : An INR based Super-Resolution and Ultra Low-Field MRI Synthesis via Contrast factor estimation : Abstract: We present an unsupervised single image bidirectional Magnetic Resonance Image (MRI) synthesizer that synthesizes an Ultra-Low Field (ULF) like image from a High-Field (HF) magnitude image a...
• On-Premise SLMs vs. Commercial LLMs: Prompt Engineering and Incident Classification in SOCs and CSIRTs : Abstract: In this study, we evaluate open-source models for security incident classification, comparing them with proprietary models. We utilize a dataset of anonymized real incidents, categorized acc...
• Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report : Abstract: This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three PANN archit...
• Artificial intelligence approaches for energy-efficient laser cutting machines : Abstract: This research addresses the significant challenges of energy consumption and environmental impact in laser cutting by proposing novel deep learning (DL) methodologies to achieve energy reduc...
• Compiling to recurrent neurons : Abstract: Discrete structures are currently second-class in differentiable programming. Since functions over discrete structures lack overt derivatives, differentiable programs do not differentiate th...
• Reconstruction of three-dimensional shapes of normal and disease-related erythrocytes from partial observations using multi-fidelity neural networks : Abstract: Reconstruction of 3D erythrocyte or red blood cell (RBC) morphology from partial observations, such as microscope images, is essential for understanding the physiology of RBC aging and the p...
• MermaidSeqBench: An Evaluation Benchmark for LLM-to-Mermaid Sequence Diagram Generation : Abstract: Large language models (LLMs) have demonstrated excellent capabilities in generating structured diagrams from natural language descriptions. In particular, they have shown great promise in ge...
• Quality-Controlled Multimodal Emotion Recognition in Conversations with Identity-Based Transfer Learning and MAMBA Fusion : Abstract: This paper addresses data quality issues in multimodal emotion recognition in conversation (MERC) through systematic quality control and multi-stage transfer learning. We implement a quality...
• Selective Forgetting in Option Calibration: An Operator-Theoretic Gauss-Newton Framework : Abstract: Calibration of option pricing models is routinely repeated as markets evolve, yet modern systems lack an operator for removing data from a calibrated model without full retraining. When quot...
• Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation : Abstract: Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functi...
• Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation : Abstract: This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of mo...
• Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning : Abstract: Next-generation networks utilize the Open Radio Access Network (O-RAN) architecture to enable dynamic resource management, facilitated by the RAN Intelligent Controller (RIC). While deep rei...
• Resource-Based Time and Cost Prediction in Project Networks: From Statistical Modeling to Graph Neural Networks : Abstract: Accurate prediction of project duration and cost remains one of the most challenging aspects of project management, particularly in resource-constrained and interdependent task networks. Tra...
• Latent space analysis and generalization to out-of-distribution data : Abstract: Understanding the relationships between data points in the latent decision space derived by the deep learning system is critical to evaluating and interpreting the performance of the system ...
• Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference : Abstract: Mixture-of-Experts (MoE) models scale LLM capacity efficiently, but deployment on consumer GPUs is limited by the large memory footprint of inactive experts. Static post-training quantizatio...
• Complex-Valued 2D Gaussian Representation for Computer-Generated Holography : Abstract: We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up ...
• Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization : Abstract: Human-like agents have long been one of the goals in pursuing artificial intelligence. Although reinforcement learning (RL) has achieved superhuman performance in many domains, relatively li...
• Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering : Abstract: Genomic question answering often requires complex reasoning and integration across diverse biomedical sources. GeneGPT addressed this challenge by combining domain-specific APIs with OpenAI'...
• GPU-Initiated Networking for NCCL : Abstract: Modern AI workloads, especially Mixture-of-Experts (MoE) architectures, increasingly demand low-latency, fine-grained GPU-to-GPU communication with device-side control. Traditional GPU commu...
• Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit : Abstract: In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussia...
• WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images : Abstract: Active learning reduces annotation costs in medical imaging by strategically selecting the most informative samples for labeling. However, individual acquisition strategies often exhibit inc...
• CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery : Abstract: Spatial Transcriptomics enables mapping of gene expression within its native tissue context, but current platforms measure only a limited set of genes due to experimental constraints and exc...
• Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distribution to Multivariate Settings : Abstract: Conformal prediction (CP) constructs uncertainty sets for model outputs with finite-sample coverage guarantees. A candidate output is included in the prediction set if its non-conformity sco...
• DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging : Abstract: High-dimensional neuroimaging analyses for clinical diagnosis are often constrained by compromises in spatiotemporal fidelity and by the limited adaptability of large-scale, general-purpose ...
• Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation : Abstract: High-quality intraoperative feedback from a surgical trainer is pivotal for improving trainee performance and long-term skill acquisition. Automating natural, trainer-style feedback promises...
• Multimodal Wireless Foundation Models : Abstract: Wireless foundation models (WFMs) have recently demonstrated promising capabilities, jointly performing multiple wireless functions and adapting effectively to new environments. However, whi...
• Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs : Abstract: Large Language Models (LLMs) are increasingly integrated into intelligent tutoring systems to provide human-like and adaptive instruction. However, most existing approaches fail to capture h...
• Data-driven Prediction of Species-Specific Plant Responses to Spectral-Shifting Films from Leaf Phenotypic and Photosynthetic Traits : Abstract: The application of spectral-shifting films in greenhouses to shift green light to red light has shown variable growth responses across crop species. However, the yield enhancement of crops u...
• HinTel-AlignBench: A Framework and Benchmark for Hindi-Telugu with English-Aligned Samples : Abstract: With nearly 1.5 billion people and more than 120 major languages, India represents one of the most diverse regions in the world. As multilingual Vision-Language Models (VLMs) gain prominence...
• BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI : Abstract: Accurate brain age estimation from structural MRI is a valuable biomarker for studying aging and neurodegeneration. Traditional regression and CNN-based methods face limitations such as manu...
• Particle Monte Carlo methods for Lattice Field Theory : Abstract: High-dimensional multimodal sampling problems from lattice field theory (LFT) have become important benchmarks for machine learning assisted sampling methods. We show that GPU-accelerated pa...
• Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking : Abstract: Evolutionary multitasking (EMT) algorithms typically require tailored designs for knowledge transfer, in order to assure convergence and optimality in multitask optimization. In this paper, ...
• Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story : Abstract: Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants remain und...
• Why Physics Still Matters: Improving Machine Learning Prediction of Material Properties with Phonon-Informed Datasets : Abstract: Machine learning (ML) methods have become powerful tools for predicting material properties with near first-principles accuracy and vastly reduced computational cost. However, the performanc...
• Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution : Abstract: We investigate the use of Reinforcement Learning for the optimal execution of meta-orders, where the objective is to execute incrementally large orders while minimizing implementation shortf...
• Graph Query Networks for Object Detection with Automotive Radar : Abstract: Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional grid and se...
• Robust Bayesian Optimisation with Unbounded Corruptions : Abstract: Bayesian Optimization is critically vulnerable to extreme outliers. Existing provably robust methods typically assume a bounded cumulative corruption budget, which makes them defenseless aga...
• Exponential Lasso: robust sparse penalization under heavy-tailed noise and outliers with exponential-type loss : Abstract: In high-dimensional statistics, the Lasso is a cornerstone method for simultaneous variable selection and parameter estimation. However, its reliance on the squared loss function renders it ...
• Fast Post-Hoc Confidence Fusion for 3-Class Open-Set Aerial Object Detection : Abstract: Developing reliable UAV navigation systems requires robust air-to-air object detectors capable of distinguishing between objects seen during training and previously unseen objects. While man...
• Controlling False Positives in Image Segmentation via Conformal Prediction : Abstract: Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc frame...
• D4C: Data-free Quantization for Contrastive Language-Image Pre-training Models : Abstract: Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenarios. While ...
• Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation : Abstract: Accurately simulating wave propagation is crucial in fields such as acoustics, electromagnetism, and seismic analysis. Traditional numerical methods, like finite difference and finite elemen...
• Gini Score under Ties and Case Weights : Abstract: The Gini score is a popular tool in statistical modeling and machine learning for model validation and model selection. It is a purely rank based score that allows one to assess risk ranking...
• SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome : Abstract: Recent advances in computational pathology have leveraged vision-language models to learn joint representations of Hematoxylin and Eosin (HE) images with spatial transcriptomic (ST) profiles...
• RS-CA-HSICT: A Residual and Spatial Channel Augmented CNN Transformer Framework for Monkeypox Detection : Abstract: This work proposes a hybrid deep learning approach, namely Residual and Spatial Learning based Channel Augmented Integrated CNN-Transformer architecture, that leverages the strengths of CNN ...
• A Tensor Compiler for Processing-In-Memory Architectures : Abstract: Processing-In-Memory (PIM) devices integrated with high-performance Host processors (e.g., GPUs) can accelerate memory-intensive kernels in Machine Learning (ML) models, including Large Lang...
• Transformer Injectivity & Geometric Robustness - Analytic Margins and Bi-Lipschitz Uniformity of Sequence-Level Hidden States : Abstract: Under real-analytic assumptions on decoder-only Transformers, recent work shows that the map from discrete prompts to last-token hidden states is generically injective on finite prompt sets....
• DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models : Abstract: Assessing the reasoning ability of Large Language Models (LLMs) over data remains an open and pressing research question. Compared with LLMs, human reasoning can derive corresponding modific...
• Dynamic Nested Hierarchies: Pioneering Self-Evolution in Machine Learning Architectures for Lifelong Intelligence : Abstract: Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures th...
• Empowering Multi-Turn Tool-Integrated Reasoning with Group Turn Policy Optimization : Abstract: Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for ...
• FinTRec: Transformer Based Unified Contextual Ads Targeting and Personalization for Financial Applications : Abstract: Transformer-based architectures are widely adopted in sequential recommendation systems, yet their application in Financial Services (FS) presents distinct practical and modeling challenges ...
• Transformer-Guided Deep Reinforcement Learning for Optimal Takeoff Trajectory Design of an eVTOL Drone : Abstract: The rapid advancement of electric vertical take-off and landing (eVTOL) aircraft offers a promising opportunity to alleviate urban traffic congestion. Thus, developing optimal takeoff trajec...
• Bringing Federated Learning to Space : Abstract: As Low Earth Orbit (LEO) satellite constellations rapidly expand to hundreds and thousands of spacecraft, the need for distributed on-board machine learning becomes critical to address downl...
• It's LIT! Reliability-Optimized LLMs with Inspectable Tools : Abstract: Large language models (LLMs) have exhibited remarkable capabilities across various domains. The ability to call external tools further expands their capability to handle real-world tasks. Ho...
• Structured Contrastive Learning for Interpretable Latent Representations : Abstract: Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, whil...
• Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis : Abstract: Deep graph learning has advanced Alzheimer's (AD) disease classification from MRI, but most models remain correlational, confounding demographic and genetic factors with disease specific fea...
• How to Train Private Clinical Language Models: A Comparative Study of Privacy-Preserving Pipelines for ICD-9 Coding : Abstract: Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for de...
• Knowledge Graphs as Structured Memory for Embedding Spaces: From Training Clusters to Explainable Inference : Abstract: We introduce Graph Memory (GM), a structured non-parametric framework that augments embedding-based inference with a compact, relational memory over region-level prototypes. Rather than trea...
• IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics : Abstract: The ionosphere is a critical component of near-Earth space, shaping GNSS accuracy, high-frequency communications, and aviation operations. For these reasons, accurate forecasting and modelin...
• Simulated Human Learning in a Dynamic, Partially-Observed, Time-Series Environment : Abstract: While intelligent tutoring systems (ITSs) can use information from past students to personalize instruction, each new student is unique. Moreover, the education problem is inherently difficu...
• Oversampling techniques for predicting COVID-19 patient length of stay : Abstract: COVID-19 is a respiratory disease that caused a global pandemic in 2019. It is highly infectious and has the following symptoms: fever or chills, cough, shortness of breath, fatigue, muscle ...
• Interpretable temporal fusion network of multi- and multi-class arrhythmia classification : Abstract: Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms. However,...
• Deep Pathomic Learning Defines Prognostic Subtypes and Molecular Drivers in Colorectal Cancer : Abstract: Precise prognostic stratification of colorectal cancer (CRC) remains a major clinical challenge due to its high heterogeneity. The conventional TNM staging system is inadequate for personali...
• Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection : Abstract: Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recently, Mamba-based state-space models have sh...
• Semiconductor Industry Trend Prediction with Event Intervention Based on LSTM Model in Sentiment-Enhanced Time Series Data : Abstract: The innovation of the study is that the deep learning method and sentiment analysis are integrated in traditional business model analysis and forecasting, and the research subject is TSMC fo...
• Efficient RF Passive Components Modeling with Bayesian Online Learning and Uncertainty Aware Sampling : Abstract: Conventional radio frequency (RF) passive components modeling based on machine learning requires extensive electromagnetic (EM) simulations to cover geometric and frequency design spaces, cr...
• Novel sparse matrix algorithm expands the feasible size of a self-organizing map of the knowledge indexed by a database of peer-reviewed medical literature : Abstract: Past efforts to map the Medline database have been limited to small subsets of the available data because of the exponentially increasing memory and processing demands of existing algorithms...