AI Research News Feeds for August 14th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• A deep learning model with machine vision system for recognizing type of the food during the food consumption
• A dataset of high-resolution plantar pressures for gait analysis across varying footwear and walking speeds
• Distributional Sensitivity Analysis: Enabling Differentiability in Sample-Based Inference
• Learning topological states from randomized measurements using variational tensor network tomography
• Variance-Reduced Fast Operator Splitting Methods for Generalized Equations
• HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction
• MedPatch: Confidence-Guided Multi-Stage Fusion for Multimodal Clinical Data
• Dynamic Survival Prediction using Longitudinal Images based on Transformer
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
• Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations
• Robustness analysis of Deep Sky Objects detection models on HPC
• Toward Human-Robot Teaming: Learning Handover Behaviors from 3D Scenes
• Prompt-aligned Gradient for Prompt Tuning
• Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
• Ear-Keeper: A Cross-Platform AI System for Rapid and Accurate Ear Disease Diagnosis
• STAC: Leveraging Spatio-Temporal Data Associations For Efficient Cross-Camera Streaming and Analytics
• Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos
• Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation
• From Few to More: Scribble-based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labels
• ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
• Joint multi-dimensional dynamic attention and transformer for general image restoration
• ViewDelta: Scaling Scene Change Detection through Text-Conditioning
• UltraRay: Introducing Full-Path Ray Tracing in Physics-Based Ultrasound Simulation
• HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
• Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
• Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation
• GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT
• Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
• NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
• Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization
• Scaling Vision Mamba Across Resolutions via Fractal Traversal
• CAS-IQA: Teaching Vision-Language Models for Synthetic Angiography Quality Assessment
• MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism
• Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning
• SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
• 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
• Calibrated Self-supervised Vision Transformers Improve Intracranial Arterial Calcification Segmentation from Clinical CT Head Scans
• Modulate and Reconstruct: Learning Hyperspectral Imaging from Misaligned Smartphone Views
• Learning Adaptive Node Selection with External Attention for Human Interaction Recognition
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection
• Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
• HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation
• FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisition
• Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesis
• RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation
• Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding
• DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes
• Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation
• MPT: Motion Prompt Tuning for Micro-Expression Recognition
• RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration
• Animate-X++: Universal Character Image Animation with Dynamic Backgrounds
• Event-driven Robust Fitting on Neuromorphic Hardware
• CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios
• Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
• From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts
• CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
• GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs
• SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images
• SARE: Semantic-Aware Reconstruction Error for Generalizable Diffusion-Generated Image Detection
• SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking
• Learning Spatial Decay for Vision Transformers
• Physics-guided Deep Unfolding Network for Enhanced Kronecker Compressive sensing
• Iterative Volume Fusion for Asymmetric Stereo Matching
• Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
• Topological Invariant-Based Iris Identification via Digital Homology and Machine Learning
• WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization
• WEC-DG: Multi-Exposure Wavelet Correction Method Guided by Degradation Description
• A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation
• Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion
• SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs
• Offline Auto Labeling: BAAS
• SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing
• Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
• BridgeTA: Bridging the Representation Gap in Knowledge Distillation via Teacher Assistant for Bird's Eye View Map Segmentation
• Plane Detection and Ranking via Model Information Optimization
• Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation
• Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors
• Multi-Contrast Fusion Module: An attention mechanism integrating multi-contrast features for fetal torso plane classification
• Multi-Sequence Parotid Gland Lesion Segmentation via Expert Text-Guided Segment Anything Model
• The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge
• TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos
• Noise-adapted Neural Operator for Robust Non-Line-of-Sight Imaging
• NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generation
• GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
• PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training
• Slot Attention-based Feature Filtering for Few-Shot Learning
• MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers
• Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing System
• Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
• MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
• DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
• MeMoSORT: Memory-Assisted Filtering and Motion-Adaptive Association Metric for Multi-Person Tracking
• MUJICA: Reforming SISR Models for PBR Material Super-Resolution via Cross-Map Attention
• Poaching Hotspot Identification Using Satellite Imagery
• Evolution of Low-Level and Texture Human-CLIP Alignment
• ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining
• KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging
• Reverse Convolution and Its Applications to Image Restoration
• Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment
• Enhancing Diffusion Face Generation with Contrastive Embeddings and SegFormer Guidance
• ARI3D: A Software for Interactive Quantification of Regions in X-Ray CT 3D Images
• Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
• OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
• HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics
• E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
• SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
• Towards Comprehensive Cellular Characterisation of H&E slides
• Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?
• AST-n: A Fast Sampling Approach for Low-Dose CT Reconstruction using Diffusion Models
• LIA-X: Interpretable Latent Portrait Animator
• MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification
• PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
• A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
• LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
• From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
• LongIns: A Challenging Long-context Instruction-based Exam for LLMs
• Memorization Over Reasoning? Exposing and Mitigating Verbatim Memorization in Large Language Models' Character Understanding Evaluation
• Efficient Inference for Large Reasoning Models: A Survey
• Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
• Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
• IP-CRR: Information Pursuit for Interpretable Classification of Chest Radiology Reports
• LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning
• MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
• DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments
• Applying Text Embedding Models for Efficient Analysis in Labeled Property Graphs
• Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
• FineState-Bench: A Comprehensive Benchmark for Fine-Grained State Control in GUI Agents
• Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
• Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic Model
• UltraLight Med-Vision Mamba for Classification of Neoplastic Progression in Tubular Adenomas
• Blink-to-code: real-time Morse code communication via eye blink detection and classification
• DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
• Skyshield: Event-Driven Submillimetre Thin Obstacle Detection for Drone Flight Safety
• Autonomous AI Bird Feeder for Backyard Biodiversity Monitoring
• Waymo-3DSkelMo: A Multi-Agent 3D Skeletal Motion Dataset for Pedestrian Interaction Modeling in Autonomous Driving
• Decoding Neural Emotion Patterns through Natural Language Processing Embeddings
• Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling
• Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models
• Leveraging Zipformer Model for Effective Language Identification in Code-Switched Child-Directed Speech
• From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
• User-centric Subjective Leaderboard by Customizable Reward Modeling
• LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation
• Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges
• UWBa at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
• The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
• AINL-Eval 2025 Shared Task: Detection of AI-Generated Scientific Abstracts in Russian
• EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization
• Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation
• The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models
• Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
• Echoes of Agreement: Argument Driven Opinion Shifts in Large Language Models
• UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
• BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
• Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
• A Survey of Cognitive Distortion Detection and Classification in NLP
• Language of Persuasion and Misrepresentation in Business Communication: A Textual Detection Approach
• Shaping Event Backstories to Estimate Potential Emotion Contexts
• Performance of GPT-5 Frontier Models in Ophthalmology Question Answering
• Which one Performs Better? Wav2Vec or Whisper? Applying both in Badini Kurdish Speech to Text (BKSTT)
• IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding
• Enhancing Deep Hedging of Options with Implied Volatility Surface Feedback Information
• VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs
• On the Robustness of Kernel Goodness-of-Fit Tests
• Leveraging Reviewer Experience in Code Review Comment Generation
• A spectral method for multi-view subspace learning using the product of projections
• Improving Multimodal Large Language Models Using Continual Learning
• Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulator
• A2SB: Audio-to-Audio Schrodinger Bridges
• Gradient Descent Algorithm in Hilbert Spaces under Stationary Markov Chains with $\phi$- and $\beta$-Mixing
• RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
• Verifying Quantized Graph Neural Networks is PSPACE-complete
• Generative Active Adaptation for Drifting and Imbalanced Network Intrusion Detection
• Cryo-em images are intrinsically low dimensional
• ParkDiffusion: Heterogeneous Multi-Agent Multi-Modal Trajectory Prediction for Automated Parking using Diffusion Models
• Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs
• M-learner:A Flexible And Powerful Framework To Study Heterogeneous Treatment Effect In Mediation Model
• MoCA: Multi-modal Cross-masked Autoencoder for Digital Health Measurements
• AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
• MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs
• Efficient Visual Appearance Optimization by Learning from Prior Preferences
• Understanding Nonlinear Implicit Bias via Region Counts in Input Space
• Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
• Mini-Game Lifetime Value Prediction in WeChat
• Leveraging Predictive Equivalence in Decision Trees
• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges
• Faster Diffusion Models via Higher-Order Approximation
• Quantum Machine Learning in Transportation: A Case Study of Pedestrian Stress Modelling
• Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
• PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification
• Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy
• Importance Corrected Neural JKO Sampling
• MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI
• Causal Graph Profiling via Structural Divergence for Robust Anomaly Detection in Cyber-Physical Systems
• Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach
• Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoring
• SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification
• Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
• Online Prediction with Limited Selectivity
• Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs
• Thermal Tracks: A Gaussian process-based framework for universal melting curve analysis enabling unconstrained hit identification in thermal proteome profiling experiments
• Global Convergence Analysis of Vanilla Gradient Descent for Asymmetric Matrix Completion
• Temporal Anchoring in Deepening Embedding Spaces: Event-Indexed Projections, Drift, Convergence, and an Internal Computational Architecture
• Combating Noisy Labels via Dynamic Connection Masking
• GraphTreeGen: Subtree-Centric Approach to Efficient and Supervised Graph Generation
• Generative Modeling with Multi-Instance Reward Learning for E-commerce Creative Optimization
• HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
• A Machine Learning Approach to Predict Biological Age and its Longitudinal Drivers
• $\mu$-Parametrization for Mixture of Experts
• TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional Specialization
• Bayesian autoregression to optimize temporal Mat\'ern kernel Gaussian process hyperparameters
• Feature Impact Analysis on Top Long-Jump Performances with Quantile Random Forest and Explainable AI Techniques
• RankList -- A Listwise Preference Learning Framework for Predicting Subjective Preferences
• FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness
• Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping?
• Prototype-Guided Diffusion: Visual Conditioning without External Memory
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
• Dynamic Mixture-of-Experts for Incremental Graph Learning
• RadioMamba: Breaking the Accuracy-Efficiency Trade-off in Radio Map Construction via a Hybrid Mamba-UNet
• GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning
• Exploring Molecular Odor Taxonomies for Structure-based Odor Predictions using Machine Learning
• Objective Soups: Multilingual Multi-Task Modeling for Speech Processing
• Forecasting Binary Economic Events in Modern Mercantilism: Traditional methodologies coupled with PCA and K-means Quantitative Analysis of Qualitative Sentimental Data
• Harnessing Input-Adaptive Inference for Efficient VLN
• A Generative Imputation Method for Multimodal Alzheimer's Disease Diagnosis
• Teaching Code Refactoring Using LLMs
• Classifying Cool Dwarfs: Comprehensive Spectral Typing of Field and Peculiar Dwarfs Using Machine Learning
• ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs
• A pseudo-inverse of a line graph
• HyperKD: Distilling Cross-Spectral Knowledge in Masked Autoencoders via Inverse Domain Shift with Spatial-Aware Masking and Specialized Loss
• CWFBind: Geometry-Awareness for Fast and Accurate Protein-Ligand Docking
• DeepWKB: Learning WKB Expansions of Invariant Distributions for Stochastic Systems
• Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective
• HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
• Scalable h-adaptive probabilistic solver for time-independent and time-dependent systems
• Personalized Product Search Ranking: A Multi-Task Learning Approach with Tabular and Non-Tabular Data
• Improving Diversity in Language Models: When Temperature Fails, Change the Loss
• Social-Sensor Identity Cloning Detection Using Weakly Supervised Deep Forest and Cryptographic Authentication
• DeputyDev -- AI Powered Developer Assistant: Breaking the Code Review Logjam through Contextual AI to Boost Developer Productivity
• NEURAL: Attention-Guided Pruning for Unified Multimodal Resource-Constrained Clinical Evaluation
• Multimodal Sheaf-based Network for Glioblastoma Molecular Subtype Prediction
• Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA
• Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
• Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning
• On the Generalization Limits of Quantum Generative Adversarial Networks with Pure State Generators
• Stable Diffusion Models are Secretly Good at Visual In-Context Learning
• Neural Bandit Based Optimal LLM Selection for a Pipeline of Tasks
• Story2Board: A Training-Free Approach for Expressive Storyboard Generation
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Semi-Bandit Learning for Monotone Stochastic Optimization
• Discrete Neural Algorithmic Reasoning
• No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and Hardness of Adversarial Full-Information Setting
• Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
• Distributed Lag Transformer based on Time-Variable-Aware Learning for Explainable Multivariate Time Series Forecasting
• Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities
• Differentiation Through Black-Box Quadratic Programming Solvers
• Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
• Generative Feature Training of Thin 2-Layer Networks
• Scalable Out-of-distribution Robustness in the Presence of Unobserved Confounders
• Indirect Query Bayesian Optimization with Integrated Feedback
• MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations
• Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
• Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
• LEAPS: A discrete neural sampler via locally equivariant networks
• Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
• Underdamped Diffusion Bridges with Applications to Sampling
• Dequantified Diffusion-Schr{\"o}dinger Bridge for Density Ratio Estimation
• Leveraging Audio and Text Modalities in Mental Health: A Study of LLMs Performance
• SLTNet: Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks
• Evaluation of Bio-Inspired Models under Different Learning Settings For Energy Efficiency in Network Traffic Prediction
• Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
• GenAI Confessions: Black-box Membership Inference for Generative Image Models
• Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions
• Conformal Prediction of Classifiers with Many Classes based on Noisy Labels
• One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
• RIZE: Regularized Imitation Learning via Distributional Reinforcement Learning
• Simulating the Real World: A Unified Survey of Multimodal Generative Models
• Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
• The Illusory Normativity of Rights-Based AI Regulation
• FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention
• CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
• Mosaic: Composite Projection Pruning for Resource-efficient LLMs
• GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes
• AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation
• FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments
• EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting
• Deep Learning Warm Starts for Trajectory Optimization on the International Space Station
• Halting Recurrent GNNs and the Graded $\mu$-Calculus
• Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
• MapStory: Prototyping Editable Map Animations with LLM Agents
• Exploring Scaling Laws for EHR Foundation Models
• Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
• Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
• Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems
• MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection
• Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
• Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning
• HVL: Semi-Supervised Segmentation leveraging Hierarchical Vision-Language Synergy with Dynamic Text-Spatial Query Alignment
• Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models
• The Importance of Being Lazy: Scaling Limits of Continual Learning
• SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving
• OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness
• Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents
• Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding
• WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks
• GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• A multi-strategy improved snake optimizer for three-dimensional UAV path planning and engineering problems
• MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
• Presenting DiaData for Research on Type 1 Diabetes
• An Unsupervised Deep XAI Framework for Localization of Concurrent Replay Attacks in Nuclear Reactor Signals
• Generating Feasible and Diverse Synthetic Populations Using Diffusion Models
• Masked Training for Robust Arrhythmia Detection from Digitalized Multiple Layout ECG Images
• SVGen: Interpretable Vector Graphics Generation with Large Language Models
• Breath as a biomarker: A survey of contact and contactless applications and approaches in respiratory monitoring
• Building Safer Sites: A Large-Scale Multi-Level Dataset for Construction Safety Research
• The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair
• Blockchain Network Analysis using Quantum Inspired Graph Neural Networks & Ensemble Models
• LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data
• Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
• Constrained Black-Box Attacks Against Multi-Agent Reinforcement Learning
• Pattern-based Knowledge Component Extraction from Student Code Using Representation Learning
• Distilling Reinforcement Learning into Single-Batch Datasets
• Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
• Integrating Feature Attention and Temporal Modeling for Collaborative Financial Risk Assessment
• Graph Neural Network and Transformer Integration for Unsupervised System Anomaly Discovery
• NEXICA: Discovering Road Traffic Causality (Extended arXiv Version)
• Open-Set Fault Diagnosis in Multimode Processes via Fine-Grained Deep Feature Representation
• Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation
• EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models
• Multi-Step Reasoning with Large Language Models, a Survey
• Probing Mechanical Reasoning in Large Vision Language Models
• Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation
• Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
• MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models
• Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving
• GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments
• AgentOrchestra: A Hierarchical Multi-Agent Framework for General-Purpose Task Solving
• MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines
• Game-Theoretic Multiagent Reinforcement Learning
• LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning
• Learning to Defer in Congested Systems: The AI-Human Interplay
• From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap
• Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs
• Towards Black-Box Membership Inference Attack for Diffusion Models
• LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data
• Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the 7-Point Checklist
• Towards flexible perception with visual memory
• SpectralEarth: Training Hyperspectral Foundation Models at Scale
• Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions
• CTRQNets & LQNets: Continuous Time Recurrent and Liquid Quantum Neural Networks
• Pediatric brain tumor classification using digital histopathology and deep learning: evaluation of SOTA methods on a multi-center Swedish cohort
• Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
• Downscaling Extreme Precipitation with Wasserstein Regularized Diffusion
• Retrieval-Augmented Decision Transformer: External Memory for In-context RL
• Depth-Guided Self-Supervised Human Keypoint Detection via Cross-Modal Distillation
• Learning Characteristics of Reverse Quaternion Neural Network
• What Can We Learn from Inter-Annotator Variability in Skin Lesion Segmentation?
• X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents
• Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
• RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata
• Domain-Generalization to Improve Learning in Meta-Learning Algorithms
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• What-Meets-Where: Unified Learning of Action and Contact Localization in a New Dataset
• Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
• A Unified Contrastive-Generative Framework for Time Series Classification
• Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis
• RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
• Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy
• DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries
• NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
• Episodic Memory Representation for Long-form Video Understanding
• Large-Small Model Collaborative Framework for Federated Continual Learning
• Learning Facts at Scale with Active Reading
• From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation
• Verify Distributed Deep Learning Model Implementation Refinement with Iterative Relation Inference
• SMART-OC: A Real-time Time-risk Optimal Replanning Algorithm for Dynamic Obstacles and Spatio-temporally Varying Currents
• COMPEER: Controllable Empathetic Reinforcement Reasoning for Emotional Support Conversation
• Generation of Indian Sign Language Letters, Numbers, and Words
• Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks
• COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
• AI Blob! LLM-Driven Recontextualization of Italian Television Archives
• Your Coding Intent is Secretly in the Context and You Should Deliberately Infer It Before Completion
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation
• CaRoBio: 3D Cable Routing with a Bio-inspired Gripper Fingernail
• Hierarchical Brain Structure Modeling for Predicting Genotype of Glioma
• A Lightweight Learned Cardinality Estimation Model
• How Persuasive Could LLMs Be? A First Study Combining Linguistic-Rhetorical Analysis and User Experiments
• MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
• Interpretable Robot Control via Structured Behavior Trees and Large Language Models
• Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
• TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling
• AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?
• Preacher: Paper-to-Video Agentic System
• A Close Reading Approach to Gender Narrative Biases in AI-Generated Stories
• Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
• On Negative-aware Preference Optimization for Recommendation
• Anomaly Detection for IoT Global Connectivity
• Surg-InvNeRF: Invertible NeRF for 3D tracking and reconstruction in surgical vision
• Evaluating the Role of Large Language Models in Legal Practice in India
• Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
• Region-to-Region: Enhancing Generative Image Harmonization with Adaptive Regional Injection
• NEUBORN: The Neurodevelopmental Evolution framework Using BiOmechanical RemodelliNg
• Enhance the machine learning algorithm performance in phishing detection with keyword features
• Counting Short Trajectories in Elementary Cellular Automata using the Transfer Matrix Method
• Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
• Combinative Matching for Geometric Shape Assembly
• Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges
• Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations
• LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations
• Explainable Ensemble Learning for Graph-Based Malware Detection
• Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology
• A Comprehensive Survey of Datasets for Clinical Mental Health AI Systems
• TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos
• Provable In-Context Vector Arithmetic via Retrieving Task Concepts
• RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
• Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification
• Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
• PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
• Perceptual Reality Transformer: Neural Architectures for Simulating Neurological Perception Conditions
• STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports
• Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
• Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning
• COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets
• Rare anomalies require large datasets: About proving the existence of anomalies
• Beyond Na\"ive Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
• T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis
• Residual Reservoir Memory Networks
• A Comprehensive Evaluation framework of Alignment Techniques for LLMs
• VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
• Specialised or Generic? Tokenization Choices for Radiology Language Models
• GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
• January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis
• Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics Model
• Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation
• Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
• The Othello AI Arena: Evaluating Intelligent Systems Through Limited-Time Adaptation to Unseen Boards
• An Automated Multi-Modal Evaluation Framework for Mobile Intelligent Assistants
• EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making
• UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles
• MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
• UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge
• The PacifAIst Benchmark:Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety?
• Reasoning About Knowledge on Regular Expressions is 2EXPTIME-complete
• Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation
• AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving
• RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
• Mathematical Computation and Reasoning Errors by Large Language Models
• QuickGrasp: Lightweight Antipodal Grasp Planning with Point Clouds
• User-Intent-Driven Semantic Communication via Adaptive Deep Understanding
• Bayesian-Driven Graph Reasoning for Active Radio Map Construction
• Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer
• To Theoretically Understand Transformer-Based In-Context Learning for Optimizing CSMA
• Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
• Motif 2.6B Technical Report
• 5G Core Fault Detection and Root Cause Analysis using Machine Learning and Generative AI
• JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis
• Peer Effect Estimation in the Presence of Simultaneous Feedback and Unobserved Confounders
• A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
• Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
• EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
• Agoran: An Agentic Open Marketplace for 6G RAN Automation
• Physics-Guided Memory Network for Building Energy Modeling
• Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
• Multimodal RAG Enhanced Visual Description
• webMCP: Efficient AI-Native Client-Side Interaction for Agent-Ready Web Design
• FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective
• A Context-aware Attention and Graph Neural Network-based Multimodal Framework for Misogyny Detection
• DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic
• Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation
• IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection
• scAGC: Learning Adaptive Cell Graphs with Contrastive Guidance for Single-Cell Clustering
• Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach
• Quantum-Efficient Reinforcement Learning Solutions for Last-Mile On-Demand Delivery
• HiSTM: Hierarchical Spatiotemporal Mamba for Cellular Traffic Forecasting
• A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
• RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System
• Hybrid(Transformer+CNN)-based Polyp Segmentation
• Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks
• From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
• Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
• Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
• Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments
• impuTMAE: Multi-modal Transformer with Masked Pre-training for Missing Modalities Imputation in Cancer Survival Prediction
• FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation
• MX-AI: Agentic Observability and Control Platform for Open and AI-RAN
• ADT4Coupons: An Innovative Framework for Sequential Coupon Distribution in E-commerce
• $\Delta$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
• Zero-shot self-supervised learning of single breath-hold magnetic resonance cholangiopancreatography (MRCP) reconstruction
• Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models: A Unified and Accurate Approach
• Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
• MoQE: Improve Quantization Model performance via Mixture of Quantization Experts
• From Explainable to Explained AI: Ideas for Falsifying and Quantifying Explanations
• CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge
• Quantum-Enhanced Generative Adversarial Networks: Comparative Analysis of Classical and Hybrid Quantum-Classical Generative Adversarial Networks
• MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
• Deep Generative Models for Discrete Genotype Simulation
• Real-time deep learning phase imaging flow cytometer reveals blood cell aggregate biomarkers for haematology diagnostics
• Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity
• Understanding Ethical Practices in AI: Insights from a Cross-Role, Cross-Region Survey of AI Development Teams
• Towards Scalable Training for Handwritten Mathematical Expression Recognition
• Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation
• From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
• AMRG: Extend Vision Language Models for Automatic Mammography Report Generation
• GSMT: Graph Fusion and Spatiotemporal TaskCorrection for Multi-Bus Trajectory Prediction
• Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference
• Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
• Beyond Technocratic XAI: The Who, What & How in Explanation Design
• PETLP: A Privacy-by-Design Pipeline for Social Media Data in AI Research
• Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
• NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation
• Cross-BCI, A Cross-BCI-Paradigm Classifica-tion Model Towards Universal BCI Applications
• Detection of Odor Presence via Deep Neural Networks
• Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMs
• Ethical Medical Image Synthesis
• Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative
• Based AI improves human decision-making but reduces trust
• Decentralized Weather Forecasting via Distributed Machine Learning and Blockchain-Based Model Validation
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
• TPTP World Infrastructure for Non-classical Logics
• Exact Verification of Graph Neural Networks with Incremental Constraint Solving
• Leveraging Large Language Models for Rare Disease Named Entity Recognition
• TEN: Table Explicitization, Neurosymbolically
• SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement Learning
• Synaptic Pruning: A Biological Inspiration for Deep Learning Regularization
• RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs
• Collective dynamics of strategic classification
• The Human-AI Hybrid Delphi Model: A Structured Framework for Context-Rich, Expert Consensus in Complex Domains
• FusionEnsemble-Net: An Attention-Based Ensemble of Spatiotemporal Networks for Multimodal Sign Language Recognition
• A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition
• APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification