AI Research News Feeds for September 3rd, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Combining Evidence Across Filtrations
• Leveraging Offline Data in Linear Latent Contextual Bandits
• Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guarantees
• Learning in complex action spaces without policy gradients
• WeSpeR: Computing non-linear shrinkage formulas for the weighted sample covariance
• FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening
• Beyond the Kolmogorov Barrier: A Learnable Weighted Hybrid Autoencoder for Model Order Reduction
• Memory Capacity of Nonlinear Recurrent Networks: Is it Informative?
• The Complexity of Learning Sparse Superposed Features with Feedback
• A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
• Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
• Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
• A Log-Linear Analytics Approach to Cost Model Regularization for Inpatient Stays through Diagnostic Code Merging
• Solving dynamic portfolio selection problems via score-based diffusion models
• Data-driven Discovery of Digital Twins in Biomedical Research
• Variational Uncertainty Decomposition for In-Context Learning
• Distribution estimation via Flow Matching with Lipschitz guarantees
• Wild Refitting for Model-Free Excess Risk Evaluation of Opaque ML/AI Models under Bregman Loss
• Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models
• Feature Augmentations for High-Dimensional Learning
• FBMS: An R Package for Flexible Bayesian Model Selection and Model Averaging
• Regime-Switching Langevin Monte Carlo Algorithms
• Generalized promotion time cure model: A new modeling framework to identify cell-type-specific genes and improve survival prognosis
• Asynchronous and Stochastic Distributed Resource Allocation
• Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
• Wrong Model, Right Uncertainty: Spatial Associations for Discrete Data with Misspecification
• Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
• Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
• Extending Model-x Framework to Missing Data
• A Flexible Framework for Incorporating Patient Preferences Into Q-Learning
• ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription
• Two-Sided Nearest Neighbors: An adaptive and minimax optimal procedure for matrix completion
• Gradient-free stochastic optimization for additive models
• A Generalization Theory for Zero-Shot Prediction
• Stochastic optimization on matrices and a graphon McKean-Vlasov limit
• Distance and Kernel-Based Measures for Global and Local Two-Sample Conditional Distribution Testing
• Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithm
• Statistical Performance Guarantee for Subgroup Identification with Generic Machine Learning
• RS-OOD: A Vision-Language Augmented Framework for Out-of-Distribution Detection in Remote Sensing
• SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images
• Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image Generation
• Hues and Cues: Human vs. CLIP
• OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
• Ordinal Adaptive Correction: A Data-Centric Approach to Ordinal Image Classification with Noisy Labels
• Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion
• Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
• MedDINOv3: How to adapt vision foundation models for medical image segmentation?
• Simulation-based inference of yeast centromeres
• Assessing One-Dimensional Cluster Stability by Extreme-Point Trimming
• Probit Monotone BART
• The Nondecreasing Rank
• Partial Functional Dynamic Backdoor Diffusion-based Causal Model
• Identifying Causal Direction via Dense Functional Classes
• Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
• Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection
• Lipschitz-Guided Design of Interpolation Schedules in Generative Models
• Preconditioned Regularized Wasserstein Proximal Sampling
• The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
• Design of Experiment for Discovering Directed Mixed Graph
• Non-Linear Model-Based Sequential Decision-Making in Agriculture
• Inference in Spreading Processes with Neural-Network Priors
• Amputation-imputation based generation of synthetic tabular data for ratemaking
• DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
• Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework
• A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation
• Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models
• 2D Gaussian Splatting with Semantic Alignment for Image Inpainting
• Ensemble-Based Event Camera Place Recognition Under Varying Illumination
• MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
• Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
• Draw-In-Mind: Learning Precise Image Editing via Chain-of-Thought Imagination
• Explaining What Machines See: XAI Strategies in Deep Object Detection Models
• Palette Aligned Image Diffusion
• Vision-Based Embedded System for Noncontact Monitoring of Preterm Infant Behavior in Low-Resource Care Settings
• Unsupervised Training of Vision Transformers with Synthetic Negatives
• See No Evil: Adversarial Attacks Against Linguistic-Visual Association in Referring Multi-Object Tracking Systems
• Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives
• ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning
• A Data-Centric Approach to Pedestrian Attribute Recognition: Synthetic Augmentation via Prompt-driven Diffusion Models
• SALAD -- Semantics-Aware Logical Anomaly Detection
• NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking
• SegFormer Fine-Tuning with Dropout: Advancing Hair Artifact Removal in Skin Lesion Analysis
• Enhancing Zero-Shot Pedestrian Attribute Recognition with Synthetic Data Generation: A Comparative Study with Image-To-Image Diffusion Models
• Omnidirectional Spatial Modeling from Correlated Panoramas
• ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
• Palmistry-Informed Feature Extraction and Analysis using Machine Learning
• A Multimodal Cross-View Model for Predicting Postoperative Neck Pain in Cervical Spondylosis Patients
• DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
• PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Clouds
• A Continuous-Time Consistency Model for 3D Point Cloud Generation
• MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentation
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
• Unified Supervision For Vision-Language Modeling in 3D Computed Tomography
• Acoustic Interference Suppression in Ultrasound images for Real-Time HIFU Monitoring Using an Image-Based Latent Diffusion Model
• Kwai Keye-VL 1.5 Technical Report
• ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association
• O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
• TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization
• Improving Large Vision and Language Models by Learning from a Panel of Peers
• Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
• OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
• GaussianGAN: Real-Time Photorealistic controllable Human Avatars
• Examination of PCA Utilisation for Multilabel Classifier of Multispectral Images
• Deep Learning-Based Rock Particulate Classification Using Attention-Enhanced ConvNeXt
• Clinical Metadata Guided Limited-Angle CT Image Reconstruction
• TransMatch: A Transfer-Learning Framework for Defect Detection in Laser Powder Bed Fusion Additive Manufacturing
• Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition
• PractiLight: Practical Light Control Using Foundational Diffusion Models
• Latent Gene Diffusion for Spatial Transcriptomics Completion
• Enabling Federated Object Detection for Connected Autonomous Vehicles: A Deployment-Oriented Evaluation
• Doctoral Thesis: Geometric Deep Learning For Camera Pose Prediction, Registration, Depth Estimation, and 3D Reconstruction
• HydroVision: Predicting Optically Active Parameters in Surface Water Using Computer Vision
• Automated Wildfire Damage Assessment from Multi view Ground level Imagery Via Vision Language Models
• RT-DETRv2 Explained in 8 Illustrations
• Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation
• Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
• ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization
• Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
• SAR-NAS: Lightweight SAR Object Detection with Neural Architecture Search
• Multi-Representation Adapter with Neural Architecture Search for Efficient Range-Doppler Radar Object Detection
• Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervals
• Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive scene Segmentation
• Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation
• Image Quality Enhancement and Detection of Small and Dense Objects in Industrial Recycling Processes
• Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation
• AgroSense: An Integrated Deep Learning System for Crop Recommendation via Soil Image Analysis and Nutrient Profiling
• M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision
• Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
• Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices
• Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework
• Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning
• RibPull: Implicit Occupancy Fields and Medial Axis Extraction for CT Ribcage Scans
• Neural Scene Designer: Self-Styled Semantic Image Manipulation
• MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization
• Bangladeshi Street Food Calorie Estimation Using Improved YOLOv8 and Regression Model
• InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Information
• Mamba-CNN: A Hybrid Architecture for Efficient and Accurate Facial Beauty Prediction
• SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization
• Traces of Image Memorability in Vision Encoders: Activations, Attention Distributions and Autoencoder Losses
• Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars
• Pose as Clinical Prior: Learning Dual Representations for Scoliosis Screening
• Spotlighter: Revisiting Prompt Tuning from a Representative Mining View
• DarkVRAI: Capture-Condition Conditioning and Burst-Order Selective Scan for Low-light RAW Video Denoising
• Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
• Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
• Weather-Dependent Variations in Driver Gaze Behavior: A Case Study in Rainy Conditions
• AI-driven Dispensing of Coral Reseeding Devices for Broad-scale Restoration of the Great Barrier Reef
• CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation
• Seeing through Unclear Glass: Occlusion Removal with One Shot
• A Unified Low-level Foundation Model for Enhancing Pathology Image Quality
• SpectMamba: Integrating Frequency and State Space Models for Enhanced Medical Image Detection
• Bidirectional Sparse Attention for Faster Video Diffusion Training
• PVINet: Point-Voxel Interlaced Network for Point Cloud Compression
• FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation
• GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
• MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentation
• MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
• DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion
• FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
• SegAssess: Panoramic quality mapping for robust and transferable unsupervised segmentation assessment
• PrediTree: A Multi-Temporal Sub-meter Dataset of Multi-Spectral Imagery Aligned With Canopy Height Maps
• DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency
• Generalizable Self-supervised Monocular Depth Estimation with Mixture of Low-Rank Experts for Diverse Endoscopic Scenes
• Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation
• PRINTER:Deformation-Aware Adversarial Learning for Virtual IHC Staining with In Situ Fidelity
• POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
• FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework
• InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos
• Secure and Scalable Face Retrieval via Cancelable Product Quantization
• Aligned Anchor Groups Guided Line Segment Detector
• Diffusion-Based Image-to-Brain Signal Generation with Cross-Attention Mechanisms for Visual Prostheses
• OmniReason: A Temporal-Guided Vision-Language-Action Framework for Autonomous Driving
• Multimodal Iterative RAG for Knowledge Visual Question Answering
• SWAGSplatting: Semantic-guided Water-scene Augmented Gaussian Splatting
• Adaptive Contrast Adjustment Module: A Clinically-Inspired Plug-and-Play Approach for Enhanced Fetal Plane Classification
• Sequential Difference Maximization: Generating Adversarial Examples via Multi-Stage Optimization
• Surface Defect Detection with Gabor Filter Using Reconstruction-Based Blurring U-Net-ViT
• UPGS: Unified Pose-aware Gaussian Splatting for Dynamic Scene Deblurring
• SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3
• Satellite Image Utilization for Dehazing with Swin Transformer-Hybrid U-Net and Watershed loss
• Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
• Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective
• Automatic Identification and Description of Jewelry Through Computer Vision and Neural Networks for Translators and Interpreters
• ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation
• LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model
• CSFMamba: Cross State Fusion Mamba Operator for Multimodal Remote Sensing Image Classification
• CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition
• Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision
• EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions
• Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification
• MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure
• No More Sibling Rivalry: Debiasing Human-Object Interaction Detection
• Towards Adaptive Visual Token Pruning for Large Multimodal Models
• CryptoFace: End-to-End Encrypted Face Recognition
• LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables
• Iterative Low-rank Network for Hyperspectral Image Denoising
• A Multimodal Head and Neck Cancer Dataset for AI-Driven Precision Oncology
• Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis
• NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
• Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentation
• Visually Grounded Narratives: Reducing Cognitive Burden in Researcher-Participant Interaction
• HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization
• Double-Constraint Diffusion Model with Nuclear Regularization for Ultra-low-dose PET Reconstruction
• DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
• LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
• Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation
• SemaMIL: Semantic Reordering with Retrieval-Guided State Space Modeling for Whole Slide Image Classification
• Stage-wise Adaptive Label Distribution for Facial Age Estimation
• Encoder-Only Image Registration
• Exploring Decision-Making Capabilities of LLM Agents: An Experimental Study on Jump-Jump Game
• TRUST: Token-dRiven Ultrasound Style Transfer for Cross-Device Adaptation
• Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation
• Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
• A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging
• C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection
• DGL-RSIS: Decoupling Global Spatial Context and Local Class Semantics for Training-Free Remote Sensing Image Segmentation
• MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
• Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
• Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding
• FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training
• DynaGuard: A Dynamic Guardrail Model With User-Defined Policies
• Similarity between Units of Natural Language: The Transition from Coarse to Fine Estimation
• Rule-Guided Joint Embedding Learning over Knowledge Graphs
• Semantic Parsing for Question Answering over Knowledge Graphs
• Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports
• Whose LLM is it Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard
• Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations
• Why Not Transform Chat Large Language Models to Non-English?
• Intrinsic Test of Unlearning Using Parametric Knowledge Traces
• MEGen: Generative Backdoor into Large Language Models via Model Editing
• On the Diagram of Thought
• AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
• Performance is not All You Need: Sustainability Considerations for Algorithms
• MESTI-MEGANet: Micro-expression Spatio-Temporal Image and Micro-expression Gradient Attention Networks for Micro-expression Recognition
• Dual-Stage Global and Local Feature Framework for Image Dehazing
• Self-supervised large-scale kidney abnormality detection in drug safety assessment studies
• Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders
• Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety
• GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery
• A High-Accuracy Fast Hough Transform with Linear-Log-Cubed Computational Complexity for Arbitrary-Shaped Images
• Language-Aware Information Maximization for Transductive Few-Shot CLIP
• MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
• SpecEval: Evaluating Model Adherence to Behavior Specifications
• GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning
• MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
• L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages
• The Forgotten Code: Validating a Century-Old Translation System with AI
• Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
• Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition
• Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
• Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
• Jointly Reinforcing Diversity and Quality in Language Model Generations
• PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture
• ChipChat: Low-Latency Cascaded Conversational Agent in MLX
• KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation
• ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
• Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering
• Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
• Do Video Language Models Really Know Where to Look? Diagnosing Attention Failures in Video Language Models
• LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
• MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model
• ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition
• CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-commerce Markets
• Reinforced Visual Perception with Tools
• ShortageSim: Simulating Drug Shortages under Information Asymmetry
• RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
• Content and Engagement Trends in COVID-19 YouTube Videos: Evidence from the Late Pandemic
• From Attack Descriptions to Vulnerabilities: A Sentence Transformer-Based Approach
• E-THER: A PCT-Grounded Dataset for Benchmarking Empathic AI
• Understanding Space Is Rocket Science - Only Top Reasoning Models Can Solve Spatial Understanding Tasks
• Parallel Needleman-Wunsch on CUDA to measure word similarity based on phonetic transcriptions
• Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
• chDzDT: Word-level morphology-aware language model for Algerian social media text
• Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
• Mic Drop or Data Flop? Evaluating the Fitness for Purpose of AI Voice Interviewers for Data Collection within Quantitative & Qualitative Research Contexts
• Extracting OPQRST in Electronic Health Records using Large Language Models with Reasoning
• Weakly Supervised Medical Entity Extraction and Linking for Chief Complaints
• DRAssist: Dispute Resolution Assistance using Large Language Models
• StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching
• DeepSeek performs better than other Large Language Models in Dental Cases
• NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task
• Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation
• How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis
• Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization
• JudgeAgent: Dynamically Evaluate LLMs with Agent-as-Interviewer
• CMRAG: Co-modality-based document retrieval and visual question answering
• AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
• Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
• Avoidance Decoding for Diverse Multi-Branch Story Generation
• FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
• Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
• LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue
• DCPO: Dynamic Clipping Policy Optimization
• Implicit Reasoning in Large Language Models: A Comprehensive Survey
• Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models
• An Ensemble Classification Approach in A Multi-Layered Large Language Model Framework for Disease Prediction
• EmoPerso: Enhancing Personality Detection with Self-Supervised Emotion-Aware Modelling
• Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions
• SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
• Mitigating Catastrophic Forgetting in Continual Learning through Model Growth
• DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Taks Based on Data and Model Compression
• Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
• Annotation and modeling of emotions in a textual corpus: an evaluative approach
• Culture is Everywhere: A Call for Intentionally Cultural Evaluation
• TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering
• Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization
• LongCat-Flash Technical Report
• KoBLEX: Open Legal Question Answering with Multi-hop Reasoning
• Can Large Language Models Master Complex Card Games?
• Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
• WATCHED: A Web AI Agent Tool for Combating Hate Speech by Expanding Data
• ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links
• Analysing the Language of Neural Audio Codecs
• LLMs cannot spot math errors, even when allowed to peek into the solution
• Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
• On the Alignment of Large Language Models with Global Human Opinion
• Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal
• Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
• Do Retrieval Augmented Language Models Know When They Don't Know?
• MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models
• Service, Solidarity, and Self-Help: A Comparative Topic Modeling Analysis of Community Unionism in the Boot and Shoe Union and Unite Community
• CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
• In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents
• Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief
• Testing the assumptions about the geometry of sentence embedding spaces: the cosine measure need not apply
• Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry
• TransGAT: Transformer-Based Graph Neural Networks for Multi-Dimensional Automated Essay Scoring
• Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations
• Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings
• Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
• Exploring and Mitigating Fawning Hallucinations in Large Language Models
• EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes
• SeLeRoSa: Sentence-Level Romanian Satire Detection Dataset
• Supervised In-Context Fine-Tuning for Generative Sequence Labeling
• MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework
• Structure and Destructure: Dual Forces in the Making of Knowledge Engines
• RPRO:Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning
• Performance Analysis of Supervised Machine Learning Algorithms for Text Classification
• Ranking of Bangla Word Graph using Graph-based Ranking Algorithms
• We Politely Insist: Your LLM Must Learn the Persian Art of Taarof
• A Dynamic Fusion Model for Consistent Crisis Response
• Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
• Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation
• A Paradigm Gap in Urdu
• Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation
• REFRAG: Rethinking RAG based Decoding
• Natural Context Drift Undermines the Natural Language Understanding of Large Language Models
• Dream-Coder 7B: An Open Diffusion Language Model for Code
• Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective
• Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA
• Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning
• Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation
• Statutory Construction and Interpretation for Artificial Intelligence
• Efficient Large Language Models with Zero-Shot Adjustable Acceleration
• MultiStream-LLM: Bridging Modalities for Robust Sign Language Translation
• The Rarity Blind Spot: A Framework for Evaluating Statistical Reasoning in LLMs
• The Temporal Game: A New Perspective on Temporal Relation Extraction
• Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval
• Wage Sentiment Indices Derived from Survey Comments via Large Language Models
• Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models
• GIER: Gap-Driven Self-Refinement for Large Language Models
• GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction
• The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang
• GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
• CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning
• Entropy-based Coarse and Compressed Semantic Speech Representation Learning
• Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization
• Thinking Hard, Going Misaligned: Emergent Misalignment in LLMs
• StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks
• Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling
• Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?
• Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
• Do small language models generate realistic variable-quality fake news headlines?
• Text Reinforcement for Multimodal Time Series Forecasting
• CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders
• Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs
• Designing LMS and Instructional Strategies for Integrating Generative-Conversational AI
• LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA
• Decomposing and Revising What Language Models Generate
• LegalChainReasoner: A Legal Chain-guided Framework for Criminal Judicial Opinion Generation
• CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA
• TMT: A Simple Way to Translate Topic Models Using Dictionaries
• Genetic Programming with Model Driven Dimension Repair for Learning Interpretable Appointment Scheduling Rules
• Fantastic Pretraining Optimizers and Where to Find Them
• Abex-rat: Synergizing Abstractive Augmentation and Adversarial Training for Classification of Occupational Accident Reports
• Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time
• Conditional-$t^3$VAE: Equitable Latent Space Allocation for Fair Generation
• DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing
• Baichuan-M2: Scaling Medical Capability with Large Verifier System
• Balanced Multimodal Learning: An Unidirectional Dynamic Interaction Perspective
• Extrapolated Markov Chain Oversampling Method for Imbalanced Text Classification
• RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting
• Fisher information flow in artificial neural networks
• Cache Management for Mixture-of-Experts LLMs -- extended version
• Generative Sequential Notification Optimization via Multi-Objective Decision Transformers
• SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
• Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size
• Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior
• Learning Longitudinal Stress Dynamics from Irregular Self-Reports via Time Embeddings
• Entropy-Driven Curriculum for Multi-Task Training in Human Mobility Prediction
• REVELIO -- Universal Multimodal Task Load Estimation for Cross-Domain Generalization
• Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling
• Efficient Transformer-Inspired Variants of Physics-Informed Deep Operator Networks
• Reinforcement Learning for Machine Learning Engineering Agents
• Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
• Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks
• A Multi-target Bayesian Transformer Framework for Predicting Cardiovascular Disease Biomarkers during Pandemics
• When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
• Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation
• GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
• Deep Reinforcement Learning for Real-Time Drone Routing in Post-Disaster Road Assessment Without Domain Knowledge
• Predicting NCAP Safety Ratings: An Analysis of Vehicle Characteristics and ADAS Features Using Machine Learning
• MATL-DC: A Multi-domain Aggregation Transfer Learning Framework for EEG Emotion Recognition with Domain-Class Prototype under Unseen Targets
• Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers
• A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture
• Geometric origin of adversarial vulnerability in deep learning
• Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
• Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
• Building surrogate models using trajectories of agents trained by Reinforcement Learning
• Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervals
• Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward
• Multitask Battery Management with Flexible Pretraining
• Causal Sensitivity Identification using Generative Learning
• DPF-CM: A Data Processing Framework with Privacy-Preserving Vector Databases for Chinese Medical LLMs Training and Deployment
• CbLDM: A Diffusion Model for recovering nanostructure from pair distribution function
• The Geometry of Nonlinear Reinforcement Learning
• Benchmarking Optimizers for Large Language Model Pretraining
• MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper
• Any-Order Flexible Length Masked Diffusion
• Reinforcement Learning Driven Generalizable Feature Representation for Cross-User Activity Recognition
• IMU-Enhanced EEG Motion Artifact Removal with Fine-Tuned Large Brain Models
• REFINESTAT: Efficient Exploration for Probabilistic Program Synthesis
• RoFt-Mol: Benchmarking Robust Fine-Tuning with Molecular Graph Foundation Models
• Disentangling Slow and Fast Temporal Dynamics in Degradation Inference with Hierarchical Differential Models
• AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models
• Fairness in Federated Learning: Trends, Challenges, and Opportunities
• XAI-Driven Machine Learning System for Driving Style Recognition and Personalized Recommendations
• Predicting Multi-Type Talented Students in Secondary School Using Semi-Supervised Machine Learning
• Tabular Diffusion Counterfactual Explanations
• An Explainable Gaussian Process Auto-encoder for Tabular Data
• DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
• Superposition in Graph Neural Networks
• SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers
• ART: Adaptive Resampling-based Training for Imbalanced Classification
• Diagnosing Psychiatric Patients: Can Large Language and Machine Learning Models Perform Effectively in Emergency Cases?
• Industrial Steel Slag Flow Data Loading Method for Deep Learning Applications
• A-FloPS: Accelerating Diffusion Sampling with Adaptive Flow Path Sampler
• Adaptive Physics-Informed Neural Networks with Multi-Category Feature Engineering for Hydrogen Sorption Prediction in Clays, Shales, and Coals
• T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation
• AnomalyExplainer Explainable AI for LLM-based anomaly detection using BERTViz and Captum
• Mitigating Clinician Information Overload: Generative AI for Integrated EHR and RPM Data Analysis
• Experimental Assessment of a Multi-Class AI/ML Architecture for Real-Time Characterization of Cyber Events in a Live Research Reactor
• Learning from Peers: Collaborative Ensemble Adversarial Training
• Financial Decision Making using Reinforcement Learning with Dirichlet Priors and Quantum-Inspired Genetic Optimization
• Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
• Progressive Element-wise Gradient Estimation for Neural Network Quantization
• LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptions
• FNODE: Flow-Matching for data-driven simulation of constrained multibody systems
• Democratizing Agentic AI with Fast Test-Time Scaling on the Edge
• From TLinFormer to TConstFormer: The Leap to Constant-Time Transformer Attention: Achieving O(1) Computation and O(1) KV Cache during Autoregressive Inference
• Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference
• Speech Foundation Models Generalize to Time Series Tasks from Wearable Sensor Data
• Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data
• Are We Really Learning the Score Function? Reinterpreting Diffusion Models Through Wasserstein Gradient Flow Matching
• Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
• Metis: Training Large Language Models with Advanced Low-Bit Quantization
• Memory Limitations of Prompt Tuning in Transformers
• Universal Properties of Activation Sparsity in Modern Large Language Models
• Cross-Domain Malware Detection via Probability-Level Fusion of Lightweight Gradient Boosting Models
• A Novel Method to Determine Total Oxidant Concentration Produced by Non-Thermal Plasma Based on Image Processing and Machine Learning
• Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
• VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding
• Can AI be Auditable?
• KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache
• TimeCopilot
• A Multi-Strategy Approach for AI-Generated Text Detection
• Forecasting the Ionosphere from Sparse GNSS Data with Temporal-Fusion Transformers
• NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization
• RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring
• LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
• Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language Model
• Confident, Calibrated, or Complicit: Probing the Trade-offs between Safety Alignment and Ideological Bias in Language Models in Detecting Hate Speech
• Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
• It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip Ensembles
• Exam Readiness Index (ERI): A Theoretical Framework for a Composite, Explainable Index
• Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning
• Low Power Approximate Multiplier Architecture for Deep Neural Networks
• Multimodal Deep Learning for Phyllodes Tumor Classification from Ultrasound and Clinical Data
• Embodied AI in Social Spaces: Responsible and Adaptive Robots in Complex Setting - UKAIRS 2025 (Copy)
• Evaluating the Effectiveness of Transformer Layers in Wav2Vec 2.0, XLS-R, and Whisper for Speaker Identification Tasks
• Criteria for Credible AI-assisted Carbon Footprinting Systems: The Cases of Mapping and Lifecycle Modeling
• Generative AI for Industrial Contour Detection: A Language-Guided Vision System
• OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews
• Access Paths for Efficient Ordering with Large Language Models
• Continuously Tempered Diffusion Samplers
• Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach
• Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots
• LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning
• Target-Oriented Single Domain Generalization
• AQFusionNet: Multimodal Deep Learning for Air Quality Index Prediction with Imagery and Sensor Data
• SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding
• Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
• Unifying Adversarial Perturbation for Graph Neural Networks
• Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation
• The Resurgence of GCG Adversarial Attacks on Large Language Models
• DAOVI: Distortion-Aware Omnidirectional Video Inpainting
• A Study on the Framework for Evaluating the Ethics and Trustworthiness of Generative AI
• TECP: Token-Entropy Conformal Prediction for LLMs
• Applying Deep Learning to Anomaly Detection of Russian Satellite Activity for Indications Prior to Military Activity
• Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?
• Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thought
• From Data to Decision: A Multi-Stage Framework for Class Imbalance Mitigation in Optical Network Failure Analysis
• Scaffold Diffusion: Sparse Multi-Category Voxel Structure Generation with Discrete Diffusion
• MolErr2Fix:Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and Revision
• The Collaborations among Healthcare Systems, Research Institutions, and Industry on Artificial Intelligence Research and Development
• Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
• Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
• Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
• Private, Verifiable, and Auditable AI Systems
• AEGIS : Automated Co-Evolutionary Framework for Guarding Prompt Injections Schema
• Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning
• Exploiting a Mixture-of-Layers in an Electrocardiography Foundation Model
• Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers
• The Application of Virtual Environments and Artificial Intelligence in Higher Education: Experimental Findings in Philosophy Teaching
• Meta-learning ecological priors from large language models explains human learning and decision making
• Embodied AI: Emerging Risks and Opportunities for Policy Action
• A Whole New World: Creating a Parallel-Poisoned Web Only AI-Agents Can See
• CoComposer: LLM Multi-agent Collaborative Music Composition
• LLM-based Triplet Extraction for Automated Ontology Generation in Software Engineering Standards
• Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval
• Pilot Study on Generative AI and Critical Thinking in Higher Education Classrooms
• Principled Approximation Methods for Efficient and Scalable Deep Learning
• Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments
• Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
• Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment
• Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025
• An LLM-enabled semantic-centric framework to consume privacy policies
• Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
• How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction
• EigenBench: A Comparative Behavioral Measure of Value Alignment
• mFARM: Towards Multi-Faceted Fairness Assessment based on HARMs in Clinical Decision Support
• Generative KI f\"ur TA
• AGI as Second Being: The Structural-Generative Ontology of Intelligence
• LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents
• Rewarding Explainability in Drug Repurposing with Knowledge Graphs
• Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem
• Exploring Diffusion Models for Generative Forecasting of Financial Charts
• Explainability-Driven Dimensionality Reduction for Hyperspectral Imaging
• When Agents go Astray: Course-Correcting SWE Agents with PRMs
• Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning
• AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
• GridMind: LLMs-Powered Agents for Power System Analysis and Operations
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
• Per-sender neural network classifiers for email authorship validation
• Optimized Renewable Energy Planning MDP for Socially-Equitable Electricity Coverage in the US
• DeepEmoNet: Building Machine Learning Models for Automatic Emotion Recognition in Human Speeches
• From Sound to Sight: Towards AI-authored Music Videos
• ZeroQAT: Your Quantization-aware Training but Efficient
• Deep Learning-Driven Multimodal Detection and Movement Analysis of Objects in Culinary
• Transfer Learning for Minimum Operating Voltage Prediction in Advanced Technology Nodes: Leveraging Legacy Data and Silicon Odometer Sensing
• Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis
• Exploring and Reshaping the Weight Distribution in LLM
• Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
• ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
• SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
• UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins
• A Hybrid Ai Framework For Strategic Patent Portfolio Pruning: Integrating Learning To-Rank And Market Need Analysis For Technology Transfer Optimization
• Ultra Strong Machine Learning: Teaching Humans Active Learning Strategies via Automated AI Explanations
• CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs
• Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
• Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
• Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
• Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
• FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
• Heads or Tails: A Simple Example of Causal Abstractive Simulation
• Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
• Communicative Agents for Slideshow Storytelling Video Generation based on LLMs
• GradeSQL: Outcome Reward Models for Ranking SQL Queries from Large Language Models
• Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
• DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
• The Need for Verification in AI-Driven Scientific Discovery
• LLM-empowered Agents Simulation Framework for Scenario Generation in Service Ecosystem Governance
• Counterfactual Sensitivity for Faithful Reasoning in Language Models
• Structured AI Decision-Making in Disaster Management
• Throttling Web Agents Using Reasoning Gates
• Unraveling LLM Jailbreaks Through Safety Knowledge Neurons
• A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models
• Beyond Memorization: Reasoning-Driven Synthesis as a Mitigation Strategy Against Benchmark Contamination
• Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation
• Ensemble Debates with Local Large Language Models for AI Alignment
• MODE: Mixture of Document Experts for RAG
• Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
• Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
• Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget
• Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
• SHERPA: A Model-Driven Framework for Large Language Model Execution
• SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces
• NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks
• Artificial Intelligence-Based Analysis of Ice Cream Melting Behavior Under Various Ingredients
• LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
• Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
• BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
• Efficient Graph Understanding with LLMs via Structured Context Injection
• Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Sampling