AI Research News Feeds for August 15th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Informed protein–ligand docking via geodesic guidance in translational, rotational and torsional spaces
• AI helps assemble ‘brain’ of future quantum computer
• Integrating CNN and transformer architectures for superior Arabic printed and handwriting characters classification
• A mind–reading brain implant that comes with password protection
• Curated CYP450 Interaction Dataset: Covering the Majority of Phase I Drug Metabolism
• Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
• Automated insect detection and biomass monitoring via AI and electrical field sensor technology
• HIBRID: histology-based risk-stratification with deep learning and ctDNA in colorectal cancer
• Transparent artificial intelligence-enabled interpretable and interactive sleep apnea assessment across flexible monitoring scenarios
• Expert evaluation of ChatGPT accuracy and reliability for basic celiac disease frequently asked questions
• Scan-rescan reliability assessment of brain volumetric analysis across scanners and software solutions
• Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
• Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions
• Combining Machine Learning Defenses without Conflicts
• Using machine learning to inform harvest control rule design in complex fishery settings
• Bi-Sparse Unsupervised Feature Selection
• TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion
• Neuronal correlations shape the scaling behavior of memory capacity and nonlinear computational capability of reservoir recurrent neural networks
• Sequential QCQP for Bilevel Optimization with Line Search
• Competitive Algorithms for Multi-Agent Ski-Rental Problems
• GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generation
• EDAPT: Towards Calibration-Free BCIs with Continual Online Adaptation
• Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures
• Nonlocal Monte Carlo via Reinforcement Learning
• Projected Coupled Diffusion for Test-Time Constrained Joint Generation
• Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot
• GNN-based Unified Deep Learning
• Self-Supervised Temporal Super-Resolution of Energy Data using Generative Adversarial Transformer
• Oops!... They Stole it Again: Attacks on Split Learning
• Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning
• Beyond Random Sampling: Instance Quality-Based Data Partitioning via Item Response Theory
• Energy-Based Models for Predicting Mutational Effects on Proteins
• Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
• Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
• IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data
• Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee
• SoK: Data Minimization in Machine Learning
• Efficiently Verifiable Proofs of Data Attribution
• A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
• Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression
• zERExtractor:An Automated Platform for Enzyme-Catalyzed Reaction Data Extraction from Scientific Literature
• Neural Network-Based Detection and Multi-Class Classification of FDI Attacks in Smart Grid Home Energy Systems
• Dynamical Alignment: A Principle for Adaptive Neural Computation
• Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History
• In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
• Machine Learning for Cloud Detection in IASI Measurements: A Data-Driven SVM Approach with Physical Constraints
• Pre-trained Transformer-models using chronic invasive electrophysiology for symptom decoding without patient-individual training
• Estimating carbon pools in the shelf sea environment: reanalysis or model-informed machine learning?
• Flexible Personalized Split Federated Learning for On-Device Fine-Tuning of Foundation Models
• Clicks Versus Conversion: Choosing a Recommender's Training Objective in E-Commerce
• Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching
• Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT Modules
• Mitigating Exponential Mixed Frequency Growth through Frequency Selection and Dimensional Separation in Quantum Machine Learning
• Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
• Reproducible Physiological Features in Affective Computing: A Preliminary Analysis on Arousal Modeling
• Advancing Autonomous Incident Response: Leveraging LLMs and Cyber Threat Intelligence
• Symmetry-Constrained Multi-Scale Physics-Informed Neural Networks for Graphene Electronic Band Structure Prediction
• Memorisation and forgetting in a learning Hopfield neural network: bifurcation mechanisms, attractors and basins
• Parity Cross-Resonance: A Multiqubit Gate
• Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations
• Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
• CrossDenoise: Denoising Implicit Feedback via a Lightweight Entity-Aware Synergistic Framework
• Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards
• Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
• HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning
• FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
• Efficient Distributed Optimization under Heavy-Tailed Noise
• A Market for Accuracy: Classification under Competition
• Learning Classifiers That Induce Markets
• From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
• Rethinking Client-oriented Federated Graph Learning
• Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
• Transferable Parasitic Estimation via Graph Contrastive Learning and Label Rebalancing in AMS Circuits
• Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
• DiRW: Path-Aware Digraph Learning for Heterophily
• Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Need
• A Training-Free Approach for Music Style Transfer with Latent Diffusion Models
• Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
• CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization
• Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
• Delayed Feedback Modeling with Influence Functions
• Rhythmic sharing: A bio-inspired paradigm for zero-shot adaptive learning in neural networks
• Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
• Advancing MAPF towards the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)
• VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models
• FinSage: A Multi-aspect RAG System for Financial Filings Question Answering
• Goal-Oriented Time-Series Forecasting: Foundation Framework Design
• Adaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints
• Unraveling the iterative CHAD
• Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing
• Security Concerns for Large Language Models: A Survey
• PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation
• Discrepancy-Aware Graph Mask Auto-Encoder
• AmpLyze: A Deep Learning Model for Predicting the Hemolytic Concentration
• Class-Proportional Coreset Selection for Difficulty-Separable Data
• A Personalized Exercise Assistant using Reinforcement Learning (PEARL): Results from a four-arm Randomized-controlled Trial
• Measuring Time Series Forecast Stability for Demand Planning
• Constrained Decoding of Diffusion LLMs with Context-Free Grammars
• Characterizing Evolution in Expectation-Maximization Estimates for Overspecified Mixed Linear Regression
• Benchmark-Driven Selection of AI: Evidence from DeepSeek-R1
• Interpretable Machine Learning Model for Early Prediction of Acute Kidney Injury in Critically Ill Patients with Cirrhosis: A Retrospective Study
• Can Transformers Break Encryption Schemes via In-Context Learning?
• Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models
• Convergence Analysis of Max-Min Exponential Neural Network Operators in Orlicz Space
• Multi-Agent Reinforcement Learning for Adaptive Resource Orchestration in Cloud-Native Clusters
• Federated Anomaly Detection for Multi-Tenant Cloud Platforms with Personalized Modeling
• Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
• A Hierarchical IDS for Zero-Day Attack Detection in Internet of Medical Things Networks
• Semantic Communication with Distribution Learning through Sequential Observations
• A Unified Evaluation Framework for Multi-Annotator Tendency Learning
• XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
• SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
• Estimating Covariance for Global Minimum Variance Portfolio: A Decision-Focused Learning Approach
• The SET Perceptual Factors Framework: Towards Assured Perception for Autonomous Systems
• A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
• TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning
• Empirical Investigation into Configuring Echo State Networks for Representative Benchmark Problem Domains
• Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval
• A Random-Key Optimizer for Combinatorial Optimization
• FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory
• Communication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functions
• An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach
• Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
• Advancing Data Equity: Practitioner Responsibility and Accountability in NLP Data Practices
• Less is More: Learning Graph Tasks with Just LLMs
• rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data
• Out-of-Distribution Detection using Counterfactual Distance
• CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market
• An Explainable AI based approach for Monitoring Animal Health
• No Free Lunch from Audio Pretraining in Bioacoustics: A Benchmark Study of Embeddings
• Facilitating Longitudinal Interaction Studies of AI Systems
• A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
• Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech
• Welfare-Centric Clustering
• eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing
• AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design
• MCP2OSC: Parametric Control by Natural Language
• MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion
• Alternating Approach-Putt Models for Multi-Stage Speech Enhancement
• RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations
• X-Node: Self-Explanation is All We Need
• Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
• Contrastive ECOC: Learning Output Codes for Adversarial Defense
• A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation
• Advances in Logic-Based Entity Resolution: Enhancing ASPEN with Local Merges and Optimality Criteria
• Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform
• FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
• SPHENIC: Topology-Informed Multi-View Clustering for Spatial Transcriptomics
• Deep Learning in Classical and Quantum Physics
• REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations
• Electromagnetic Simulations of Antennas on GPUs for Machine Learning Applications
• APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squares
• Natively Trainable Sparse Attention for Hierarchical Point Cloud Datasets
• FROGENT: An End-to-End Full-process Drug Design Agent
• A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection
• Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
• Improving and Evaluating Open Deep Research Agents
• Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
• KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
• Extending the Entropic Potential of Events for Uncertainty Quantification and Decision-Making in Artificial Intelligence
• Why Cannot Large Language Models Ever Make True Correct Reasoning?
• Promoting Efficient Reasoning with Verifiable Stepwise Reward
• A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
• Multi-Agent Trust Region Policy Optimisation: A Joint Constraint Approach
• What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles
• LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
• HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation
• FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs
• SEQ-GPT: LLM-assisted Spatial Query via Example
• PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning
• MSRS: Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
• STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
• GenOM: Ontology Matching with Description Generation and Large Language Model
• Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
• Modeling Human Responses to Multimodal AI Content
• The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
• Who Benefits from AI Explanations? Towards Accessible and Interpretable Systems
• OpenFPL: An open-source forecasting method rivaling state-of-the-art Fantasy Premier League services
• A Robust Pipeline for Differentially Private Federated Learning on Imbalanced Clinical Data using SMOTETomek and FedProx
• Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7
• Jet Image Tagging Using Deep Learning: An Ensemble Model
• Certifiably robust malware detectors by design
• Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
• Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning
• FIDELIS: Blockchain-Enabled Protection Against Poisoning Attacks in Federated Learning
• Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System
• Generative AI for Cybersecurity of Energy Management Systems: Methods, Challenges, and Future Directions
• SABIA: An AI-Powered Tool for Detecting Opioid-Related Behaviors on Social Media
• Legal Zero-Days: A Novel Risk Vector for Advanced AI Systems
• NetMoniAI: An Agentic AI Framework for Network Security & Monitoring
• Prediction-Powered Inference with Inverse Probability Weighting
• Mo' Memory, Mo' Problems: Stream-Native Machine Unlearning
• Dimension-Free Bounds for Generalized First-Order Methods via Gaussian Coupling
• An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
• Conic Formulations of Transport Metrics for Unbalanced Measure Networks and Hypernetworks
• xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
• Bayesian Models for Joint Selection of Features and Auto-Regressive Lags: Theory and Applications in Environmental and Financial Forecasting
• Comparison of D-Wave Quantum Annealing and Markov Chain Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machine
• The Conditional Regret-Capacity Theorem for Batch Universal Prediction
• Uncertainty-Aware Prediction of Parkinson's Disease Medication Needs: A Two-Stage Conformal Prediction Approach
• Online selective conformal inference: adaptive scores, convergence rate and optimality
• Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
• BKP: An R Package for Beta Kernel Process Modeling
• Confounding is a Pervasive Problem in Real World Recommender Systems
• Nonlinear filtering based on density approximation and deep BSDE prediction
• A Guide to Bayesian Optimization in Bioprocess Engineering
• MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
• Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detection
• Comparison of Data Reduction Criteria for Online Gaussian Processes
• Continuous Parallel Relaxation for Finding Diverse Solutions in Combinatorial Optimization Problems
• Hypothesis Spaces for Deep Learning
• A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set
• Online Distributional Regression
• Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early-Stopping
• A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
• Hyperflux: Pruning Reveals the Importance of Weights
• MIRRAMS: Learning Robust Tabular Models under Unseen Missingness Shifts
• Minimax Optimality in Contextual Dynamic Pricing with General Valuation Models
• A Parametric Contextual Online Learning Theory of Brokerage
• Neural Networks Generalize on Low Complexity Data
• Responsible Machine Learning via Mixed-Integer Optimization
• Identifying Causal Direction via Variational Bayesian Compression
• Reinforcement Learning with Random Time Horizons
• Optimistic critics can empower small actors
• MAP Estimation with Denoisers: Convergence Rates and Guarantees
• Improved Regularization and Robustness for Fine-tuning in Neural Networks
• Unifying Self-Supervised Clustering and Energy-Based Models
• Detection and Tracking of MAVs Using a Rosette Scanning Pattern LiDAR
• Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization
• Visual SLAMMOT Considering Multiple Motion Models
• INSIGHT: Explainable Weakly-Supervised Medical Image Analysis
• Bootstrapping, Autonomous Testing, and Initialization System for Si/SiGe Multi-quantum Dot Devices
• Robotic Ultrasound-Guided Femoral Artery Reconstruction of Anatomically-Representative Phantoms
• EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement
• Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
• CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
• Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
• Data Pruning by Information Maximization
• Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
• Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images
• Semantic Structure-Aware Generative Attacks for Enhanced Adversarial Transferability
• VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
• Deblurring in the Wild: A Real-World Dataset from Smartphone High-Speed Videos
• EXAONE Path 2.0: Pathology Foundation Model with End-to-End Supervision
• Common Data Properties Limit Object-Attribute Binding in CLIP
• M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
• Warehouse Spatial Question Answering with LLM Agent
• Hierarchical Cross-modal Prompt Learning for Vision-Language Models
• STAMP: Multi-pattern Attention-aware Multiple Instance Learning for STAS Diagnosis in Multi-center Histopathology Images
• TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
• Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting
• A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
• EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba
• Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies
• Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network For Salient Object Detection in Optical Remote Sensing Images
• PSScreen: Partially Supervised Multiple Retinal Disease Screening
• AR Surgical Navigation With Surface Tracing: Comparing In-SitVisualization with Tool-Tracking Guidance for Neurosurgical Applications
• Retrieval-Augmented Prompt for OOD Detection
• PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks
• HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
• SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous Driving
• Adapting SAM via Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detection
• Towards Agentic AI for Multimodal-Guided Video Object Segmentation
• HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
• EvTurb: Event Camera Guided Turbulence Removal
• Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
• Fourier-Guided Attention Upsampling for Image Super-Resolution
• FIND-Net -- Fourier-Integrated Network with Dictionary Kernels for Metal Artifact Reduction
• Increasing the Utility of Synthetic Images through Chamfer Guidance
• ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation
• Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
• Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
• SemPT: Semantic Prompt Tuning for Vision-Language Models
• Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking
• AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models
• Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation
• HyperTea: A Hypergraph-based Temporal Enhancement and Alignment Network for Moving Infrared Small Target Detection
• Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping
• IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
• Novel View Synthesis using DDIM Inversion
• Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios
• CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation
• NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
• Lightweight CNNs for Embedded SAR Ship Target Detection and Classification
• Revisiting Cross-View Localization from Image Matching
• Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
• EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
• Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
• Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
• Axis-level Symmetry Detection with Group-Equivariant Representation
• Forgery Guided Learning Strategy with Dual Perception Network for Deepfake Cross-domain Detection
• An Efficient Model-Driven Groupwise Approach for Atlas Construction
• From Diagnosis to Improvement: Probing Spatio-Physical Reasoning in Vision Language Models
• AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
• Video-BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
• Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior
• Cooperative Face Liveness Detection from Optical Flow
• VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
• Object Fidelity Diffusion for Remote Sensing Image Generation
• Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops
• UI-Venus Technical Report: Building High-performance UI Agents with RFT
• Self-Supervised Stereo Matching with Multi-Baseline Contrastive Learning
• Generalizable Federated Learning using Client Adaptive Focal Modulation
• Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
• Performance of GPT-5 in Brain Tumor MRI Reasoning
• TexVerse: A Universe of 3D Objects with High-Resolution Textures
• Medico 2025: Visual Question Answering for Gastrointestinal Imaging
• ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
• STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
• MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
• ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
• Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning
• Puppeteer: Rig and Animate Your 3D Models
• Quantum Visual Fields with Neural Amplitude Encoding
• Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
• From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
• Explainable AI Technique in Lung Cancer Detection Using Convolutional Neural Networks
• Data-Efficient Learning for Generalizable Surgical Video Understanding
• AI-Driven Detection and Analysis of Handwriting on Seized Ivory: A Tool to Uncover Criminal Networks in the Illicit Wildlife Trade
• DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy
• SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
• Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuning
• Efficient Image Denoising Using Global and Local Circulant Representation
• ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
• MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance
• We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
• On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
• On Spectral Properties of Gradient-based Explanation Methods
• DIVA-VQA: Detecting Inter-frame Variations in UGC Video Quality
• Geospatial Diffusion for Land Cover Imperviousness Change Forecasting
• Agentic Design Review System
• Insights from the Algonauts 2025 Winners
• When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images
• GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
• Video-based automatic lameness detection of dairy cows using pose estimation and multiple locomotion traits
• Debiasing Multimodal Large Language Models via Penalization of Language Priors
• VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction
• MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset
• CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
• Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understanding
• MyTimeMachine: Personalized Facial Age Transformation
• Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
• DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction
• DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
• Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness
• Understanding Transformer-based Vision Models through Inversion
• A Lightweight Transformer with Phase-Only Cross-Attention for Illumination-Invariant Biometric Authentication
• Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation
• Leveraging Motion Estimation for Efficient Bayer-Domain Computer Vision
• NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning
• MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching
• Just Functioning as a Hook for Two-Stage Referring Multi-Object Tracking
• Continual Learning for Multiple Modalities
• UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
• Scaling Open-Vocabulary Action Detection
• OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM
• A Rose by Any Other Name Would Smell as Sweet: Categorical Homotopy Theory for Large Language Models
• Decoupling Understanding from Reasoning via Problem Space Mapping for Small-scale Model Reasoning
• FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models
• LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients
• Conformal P-Value in Multiple-Choice Question Answering Tasks with Provable Risk Control
• RTTC: Reward-Guided Collaborative Test-Time Compute
• Detecting and explaining postpartum depression in real-time with generative artificial intelligence
• SABER: Switchable and Balanced Training for Efficient LLM Reasoning
• LLMCARE: Alzheimer's Detection via Transformer Models Enhanced by LLM-Generated Synthetic Data
• PREF: Reference-Free Evaluation of Personalised Text Generation in LLMs
• Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
• Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models
• The Cost of Thinking: Increased Jailbreak Risk in Large Language Models
• Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
• mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning
• Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
• LaajMeter: A Framework for LaaJ Evaluation
• Estimating Machine Translation Difficulty
• Efficient Forward-Only Data Valuation for Pretrained LLMs and VLMs
• PakBBQ: A Culturally Adapted Bias Benchmark for QA
• Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models
• Understanding Textual Emotion Through Emoji Prediction
• Using Large Language Models to Measure Symptom Severity in Patients At Risk for Schizophrenia
• A Computational Approach to Analyzing Language Change and Variation in the Constructed Language Toki Pona
• Inductive Bias Extraction and Matching for LLM Prompts
• Yet another algorithmic bias: A Discursive Analysis of Large Language Models Reinforcing Dominant Discourses on Gender and Race
• ReviewRL: Towards Automated Scientific Review with RL
• From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis
• Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
• Cross-Prompt Encoder for Low-Performing Languages
• Making Qwen3 Think in Korean with Reinforcement Learning
• Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
• Large Language Models for Summarizing Czech Historical Documents and Beyond
• Improving Generative Cross-lingual Aspect-Based Sentiment Analysis with Constrained Decoding
• Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
• Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
• ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
• Evaluating LLMs on Chinese Idiom Translation
• Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
• DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales
• When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
• When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
• eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM
• Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages
• Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
• Learning from Natural Language Feedback for Personalized Question Answering
• Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
• Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
• Reinforced Language Models for Sequential Decision Making
• Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
• From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
• SSRL: Self-Search Reinforcement Learning
• A Survey on Diffusion Language Models
• Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
• Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning
• SaraCoder: Orchestrating Semantic and Structural Cues for Profit-Oriented Repository-Level Code Completion
• Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development
• Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
• Personalized Real-time Jargon Support for Online Meetings
• Improving OCR for Historical Texts of Multiple Languages
• CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
• Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model
• Diversity First, Quality Later: A Two-Stage Assumption for Language Model Alignment
• Improving Value-based Process Verifier via Low-Cost Variance Reduction
• Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
• Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
• Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Technical Solutions
• Searching for Privacy Risks in LLM Agents via Simulation
• Knowledge-based Consistency Testing of Large Language Models
• This Candidate is [MASK]. Prompt-based Sentiment Extraction and Reference Letters
• Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
• Measuring Diversity in Synthetic Datasets
• LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
• TikZero: Zero-Shot Text-Guided Graphics Program Synthesis
• Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning
• Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models
• ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
• CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring
• Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition
• AF-MAT: Aspect-aware Flip-and-Fuse xLSTM for Aspect-based Sentiment Analysis
• Meanings are like Onions: a Layered Approach to Metaphor Processing
• CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
• DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base
• A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry
• BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache
• CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
• Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free
• FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
• MAPS: A Multilingual Benchmark for Global Agent Performance and Security
• Evaluation of Cultural Competence of Vision-Language Models
• Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
• LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
• Stochastic-based Patch Filtering for Few-Shot Learning
• DINOv3
• Empowering Morphing Attack Detection using Interpretable Image-Text Foundation Model
• Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs
• Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
• MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
• Improving watermelon (Citrullus lanatus) disease classification with generative artificial intelligence (GenAI)-based synthetic and real-field images via a custom EfficientNetV2-L model
• SynSpill: Improved Industrial Spill Detection With Synthetic Data
• EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting
• CellSymphony: Deciphering the molecular and phenotypic orchestration of cells with single-cell pathomics
• Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets
• MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
• Pose-Robust Calibration Strategy for Point-of-Gaze Estimation on Mobile Phones
• High Fidelity Text to Image Generation with Contrastive Alignment and Structural Guidance
• VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation
• JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics
• A Sub-Pixel Multimodal Optical Remote Sensing Images Matching Method
• InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild
• From Pixel to Mask: A Survey of Out-of-Distribution Segmentation
• Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances
• Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models
• Glo-DMU: A Deep Morphometry Framework of Ultrastructural Characterization in Glomerular Electron Microscopic Images
• AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging
• Contrast Sensitivity Function of Multimodal Vision-Language Models
• Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models
• Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noise
• PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection
• Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models
• SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection
• NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer
• STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes
• CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation
• DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations
• SkeySpot: Automating Service Key Detection for Digital Electrical Layout Plans in the Construction Industry
• From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution
• Multi-Label Plant Species Prediction with Metadata-Enhanced Multi-Head Vision Transformers
• SingleStrip: learning skull-stripping from a single labeled example
• Enhanced Sparse Point Cloud Data Processing for Privacy-aware Human Action Recognition
• A Transparent Fairness Evaluation Protocol for Open-Source Language Model Benchmarking on the Blockchain
• Thematic and Task-Based Categorization of K-12 GenAI Usages with Hierarchical Topic Modeling
• INTIMA: A Benchmark for Human-AI Companionship Behavior
• XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs
• AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification
• HiFACTMix: A Code-Mixed Benchmark and Graph-Aware Model for EvidenceBased Political Claim Verification in Hinglish
• Semantic Structure in Large Language Model Embeddings
• User Perception of Attention Visualizations: Effects on Interpretability Across Evidence-Based Medical Documents
• From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
• Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models
• Multidimensional classification of posts for online course discussion forum curation
• Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
• An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs
• Evaluation of GPT-based large language generative AI models as study aids for the national licensure examination for registered dietitians in Japan
• Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs
• Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis
• PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?
• RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction Analysis
• Training-Free Multimodal Large Language Model Orchestration
• Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry