AI Research News Feeds for August 21st, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Discovery of tumour indicating morphological changes in benign prostate biopsies through AI
• Explainable AI reveals tissue pathology and psychosocial drivers of opioid prescription for non-specific chronic low back pain
• An improved elastic net clustering algorithm with dynamic parameter strategy
• Two pathways to resolve relational inconsistencies
• Integrating artificial intelligence and optogenetics for Parkinson’s disease diagnosis and therapeutics in male mice
• Successes and limitations of pretrained YOLO detectors applied to unseen time-lapse images for automated pollinator monitoring
• A lightweight and explainable CNN model for empowering plant disease diagnosis
• Finding spatially variable ligand-receptor interactions with functional support from downstream genes
• Systematic selection of best performing mathematical models for in vitro gas production using machine learning across diverse feeds
• Data Fusion for High-Resolution Estimation
• Simplifying Random Forests' Probabilistic Forecasts
• Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat
• UnZipLoRA: Separating Content and Style from a Single Image
• Dynamic watermarks in images generated by diffusion models
• Real-time Neural Rendering of LiDAR Point Clouds
• DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
• Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion
• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
• CoMatcher: Multi-View Collaborative Feature Matching
• Reconstruction-Free Anomaly Detection with Diffusion Models
• Enhanced Anomaly Detection for Capsule Endoscopy Using Ensemble Learning Strategies
• Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression
• Improving Token-based Object Detection with Video
• CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning
• Explicit Context Reasoning with Supervision for Visual Tracking
• Cherenkov Imaged Bio-morphological Features Verify Patient Positioning with Deformable Tissue Translocation in Breast Radiotherapy
• 3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds
• HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation
• FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
• MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion
• Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting
• Generalizable Engagement Estimation in Conversation via Domain Prompting and Parallel Attention
• D^3-Talker: Dual-Branch Decoupled Deformation Fields for Few-Shot 3D Talking Head Synthesis
• Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
• DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
• LookOut: Real-World Humanoid Egocentric Navigation
• Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
• WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification
• SATURN: Autoregressive Image Generation Guided by Scene Graphs
• Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
• WISE-FUSE: Efficient Whole Slide Image Encoding via Coarse-to-Fine Patch Selection with VLM and LLM Knowledge Fusion
• A Comprehensive Review of Agricultural Parcel and Boundary Delineation from Remote Sensing Images: Recent Progress and Future Perspectives
• Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
• Locality-aware Concept Bottleneck Model
• GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels
• Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Dataset
• Controllable Latent Space Augmentation for Digital Pathology
• Reliable Smoke Detection via Optical Flow-Guided Feature Fusion and Transformer-Based Uncertainty Modeling
• Incremental Object Detection with Prompt-based Methods
• SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videos
• AnchorSync: Global Consistency Optimization for Long Video Editing
• Towards PerSense++: Advancing Training-Free Personalized Instance Segmentation in Dense Images
• GeMS: Efficient Gaussian Splatting for Extreme Motion Blur
• Seeing Further on the Shoulders of Giants: Knowledge Inheritance for Vision Foundation Models
• GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
• Multiscale Video Transformers for Class Agnostic Segmentation in Autonomous Driving
• Improved Mapping Between Illuminations and Sensors for RAW Images
• Fusing Monocular RGB Images with AIS Data to Create a 6D Pose Estimation Dataset for Marine Vessels
• 6-DoF Object Tracking with Event-based Optical Flow and Frames
• Adversarial Hospital-Invariant Feature Learning for WSI Patch Classification
• Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
• Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives
• EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
• Lifespan Pancreas Morphology for Control vs Type 2 Diabetes using AI on Largescale Clinical Imaging
• MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition
• GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects
• Hallucinations in medical devices
• OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos
• Physics-Constrained Diffusion Reconstruction with Posterior Correction for Quantitative and Fast PET Imaging
• A Real-world Display Inverse Rendering Dataset
• Fine-grained Image Quality Assessment for Perceptual Image Restoration
• Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysis
• From Slices to Structures: Unsupervised 3D Reconstruction of Female Pelvic Anatomy from Freehand Transvaginal Ultrasound
• Virtual Multiplex Staining for Histological Images using a Marker-wise Conditioned Diffusion Model
• Rule-based Key-Point Extraction for MR-Guided Biomechanical Digital Twins of the Spine
• MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
• Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds
• Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration
• RNDiff: Rainfall nowcasting with Condition Diffusion Model
• Consistent and Optimal Solution to Camera Motion Estimation
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
• What Makes for Good Image Captions?
• FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
• MMAD: Multi-label Micro-Action Detection in Videos
• VisioPhysioENet: Visual Physiological Engagement Detection Network
• Dark Miner: Defend against undesirable generation for text-to-image diffusion models
• Efficient Long-duration Talking Video Synthesis with Linear Diffusion Transformer under Multimodal Guidance
• A comparative study of some wavelet and sampling operators on various features of an image
• CLIPSym: Delving into Symmetry Detection with CLIP
• Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models
• GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting
• Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference
• MoVieDrive: Multi-Modal Multi-View Urban Scene Video Generation
• Deep Learning for Taxol Exposure Analysis: A New Cell Image Dataset and Attention-Based Baseline Model
• Taming Transformer for Emotion-Controllable Talking Face Generation
• FastTracker: Real-Time and Accurate Visual Tracking
• TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network
• QuadINR: Hardware-Efficient Implicit Neural Representations Through Quadratic Activation
• Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learning
• CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities
• MoCHA-former: Moir\'e-Conditioned Hybrid Adaptive Transformer for Video Demoir\'eing
• From Image Captioning to Visual Storytelling
• Benchmarking Sociolinguistic Diversity in Swahili NLP: A Taxonomy-Guided Approach
• Contrastive Analysis of Constituent Order Preferences Within Adverbial Roles in English and Chinese News: A Large-Language-Model-Driven Approach
• Confidence Estimation for Text-to-SQL in Large Language Models
• MMReview: A Multidisciplinary and Multimodal Benchmark for LLM-Based Peer Review Automation
• Comparing energy consumption and accuracy in text classification inference
• Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper
• GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs
• Tokens with Meaning: A Hybrid Tokenization Approach for NLP
• A Joint Multitask Model for Morpho-Syntactic Parsing
• SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing
• Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
• ISCA: A Framework for Interview-Style Conversational Agents
• Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
• Reasoning is about giving reasons
• EmoTale: An Enacted Speech-emotion Dataset in Danish
• Filling the Gap for Uzbek: Creating Translation Resources for Southern Uzbek
• Continuous sentiment scores for literary and multilingual contexts
• Improving in-context learning with a better scoring function
• The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
• MedReseacher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework
• RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition
• MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis
• Measuring LLM Code Generation Stability via Structural Entropy
• MultiFuzz: A Dense Retrieval-based Multi-Agent System for Network Protocol Fuzzing
• The Prompting Brain: Neurocognitive Markers of Expertise in Guiding Large Language Models
• Virtual Community: An Open World for Humans, Robots, and Society
• G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
• Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model
• ChuLo: Chunk-Level Key Information Representation for Long Document Understanding
• Task-Oriented Automatic Fact-Checking with Frame-Semantics
• Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization
• Chain of Correction for Full-text Speech Recognition with Large Language Models
• Customizing Speech Recognition Model with Large Language Model Feedback
• ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs
• MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata
• The Spectral Barycentre of a Set of Graphs with Community Structure
• GenVC: Self-Supervised Zero-Shot Voice Conversion
• Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
• Learning to Solve Related Linear Systems
• Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
• Multi-scale species richness estimation with deep learning
• SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
• The C-index Multiverse
• Fluorescence molecular optomic signatures improve identification of tumors in head and neck specimens
• Behind the Myth of Exploration in Policy Gradients
• Sample Selection Bias in Machine Learning for Healthcare
• Improving Actor-Critic Training with Steerable Action-Value Approximation Errors
• Adaptive Experiments Under Data Sparse Settings: Applications for Educational Platforms
• Generalizable Spectral Embedding with an Application to UMAP
• No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
• Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
• Low-rank bias, weight decay, and model merging in neural networks
• Redundant feature screening method for human activity recognition based on attention purification mechanism
• LLM4FS: Leveraging Large Language Models for Feature Selection
• Evaluating Autoencoders for Parametric and Invertible Multidimensional Projections
• Bi-directional Model Cascading with Proxy Confidence
• Learnable Kernel Density Estimation for Graphs
• AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption
• Near Optimal Non-asymptotic Sample Complexity of 1-Identification
• Fragile, Robust, and Antifragile: A Perspective from Parameter Responses in Reinforcement Learning Under Stress
• The calculus of variations of the Transformer on the hyperspherical tangent bundle
• The Kikuchi Hierarchy and Tensor PCA
• Diffusion MRI with Machine Learning
• Comparison of parallel SMC and MCMC for Bayesian deep learning
• Is The Watermarking Of LLM-Generated Code Robust?
• Ranking by Lifts: A Cost-Benefit Approach to Large-Scale A/B Tests
• Coupling without Communication and Drafter-Invariant Speculative Decoding
• Parallelly Tempered Generative Adversarial Nets: Toward Stabilized Gradients
• Measuring IIA Violations in Similarity Choices with Bayesian Models
• A Fuzzy-Enhanced Explainable AI Framework for Flight Continuous Descent Operations Classification
• Clinical semantics for lung cancer prediction
• Understanding Data Influence with Differential Approximation
• Improving Fairness in Graph Neural Networks via Counterfactual Debiasing
• Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum
• CaTE Data Curation for Trustworthy AI
• MissionHD: Data-Driven Refinement of Reasoning Graph Structure through Hyperdimensional Causal Path Encoding and Decoding
• HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
• Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
• Context Steering: A New Paradigm for Compression-based Embeddings by Synthesizing Relevant Information Features
• Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method
• A Guide for Manual Annotation of Scientific Imagery: How to Prepare for Large Projects
• Source-Guided Flow Matching
• Enhancing Contrastive Link Prediction With Edge Balancing Augmentation
• Successive Halving with Learning Curve Prediction via Latent Kronecker Gaussian Processes
• On Defining Neural Averaging
• Multimodal Quantum Vision Transformer for Enzyme Commission Classification from Biochemical Representations
• Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
• Squeezed Diffusion Models
• Compute-Optimal Scaling for Value-Based Deep RL
• Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
• Activity Coefficient-based Channel Selection for Electroencephalogram: A Task-Independent Approach
• Personalized Contest Recommendation in Fantasy Sports
• Punctuation and Predicates in Language Models
• Systematic FAIRness Assessment of Open Voice Biomarker Datasets for Mental Health and Neurodegenerative Diseases
• 3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models
• EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition
• DPad: Efficient Diffusion Language Models with Suffix Dropout
• RewardRank: Optimizing True Learning-to-Rank Utility
• Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer
• Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
• Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams
• Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors
• Comparing Model-agnostic Feature Selection Methods through Relative Efficiency
• HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation
• Evaluation and Optimization of Leave-one-out Cross-validation for the Lasso
• Hilbert geometry of the symmetric positive-definite bicone: Application to the geometry of the extended Gaussian family
• Action-Constrained Imitation Learning
• Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations
• Improving OCR using internal document redundancy
• Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning
• Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis
• Distributional Adversarial Attacks and Training in Deep Hedging
• Learning from user's behaviour of some well-known congested traffic networks
• Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
• One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks
• Common Data Format (CDF): A Standardized Format for Match-Data in Football (Soccer)
• Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data
• Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
• Spore in the Wild: A Case Study of Spore.fun as an Open-Environment Evolution Experiment with Sovereign AI Agents on TEE-Secured Blockchains
• Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting
• MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis
• Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning
• Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization
• LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization
• DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning
• Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning
• Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students
• Load Forecasting on A Highly Sparse Electrical Load Dataset Using Gaussian Interpolation
• Multi-Objective Bayesian Optimization with Independent Tanimoto Kernel Gaussian Processes for Diverse Pareto Front Exploration
• Out-of-Sample Hydrocarbon Production Forecasting: Time Series Machine Learning using Productivity Index-Driven Features and Inductive Conformal Prediction
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
• KnowDR-REC: A Benchmark for Referring Expression Comprehension with Real-World Knowledge
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
• Toward Generalist Semi-supervised Regression via Decoupled Representation Distillation
• Parameter-Aware Ensemble SINDy for Interpretable Symbolic SGS Closure
• EEGDM: EEG Representation Learning via Generative Diffusion Model
• Physics-Informed Reward Machines
• Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action Spaces
• From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
• Comparison of derivative-free and gradient-based minimization for multi-objective compositional design of shape memory alloys
• Towards Agent-based Test Support Systems: An Unsupervised Environment Design Approach
• Topological Data Analysis for Unsupervised Anomaly Detection and Customer Segmentation on Banking Data
• Learning to Learn the Macroscopic Fundamental Diagram using Physics-Informed and meta Machine Learning techniques
• Beyond Turing: Memory-Amortized Inference as a Foundation for Cognitive Computation
• Noise Robust One-Class Intrusion Detection on Dynamic Graphs
• Reliability comparison of vessel trajectory prediction models via Probability of Detection
• Graph Concept Bottleneck Models
• FedRAIN-Lite: Federated Reinforcement Algorithms for Improving Idealised Numerical Weather and Climate Models
• Multi-view Graph Condensation via Tensor Decomposition
• NeRC: Neural Ranging Correction through Differentiable Moving Horizon Location Estimation
• On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
• A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
• SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
• Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
• Personalized Counterfactual Framework: Generating Potential Outcomes from Wearable Data
• DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
• Fast Symbolic Regression Benchmarking
• On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines
• Semantic Energy: Detecting LLM Hallucination Beyond Entropy
• Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services
• Great GATsBi: Hybrid, Multimodal, Trajectory Forecasting for Bicycles using Anticipation Mechanism
• FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning
• Cooperative SGD with Dynamic Mixing Matrices
• A Comprehensive Evaluation of the Sensitivity of Density-Ratio Estimation Based Fairness Measurement in Regression
• DualNILM: Energy Injection Identification Enabled Disaggregation with Deep Multi-Task Learning
• Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization
• Credence Calibration Game? Calibrating Large Language Models through Structured Play
• DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
• NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding
• Cognitive Surgery: The Awakening of Implicit Territorial Awareness in LLMs
• Detecting Reading-Induced Confusion Using EEG and Eye Tracking
• NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
• In2x at WMT25 Translation Task
• Synaptic bundle theory for spike-driven sensor-motor system: More than eight independent synaptic bundles collapse reward-STDP learning
• Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes
• PB-IAD: Utilizing multimodal foundation models for semantic industrial anomaly detection in dynamic manufacturing environments
• MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation
• EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
• Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
• Post-hoc LLM-Supported Debugging of Distributed Processes
• Adaptively Robust LLM Inference Optimization under Prediction Uncertainty
• Towards LLM-generated explanations for Component-based Knowledge Graph Question Answering Systems
• Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions
• An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems
• UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling
• A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References
• Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
• OneLoc: Geo-Aware Generative Recommender Systems for Local Life Service
• ELATE: Evolutionary Language model for Automated Time-series Engineering
• ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signal
• Foe for Fraud: Transferable Adversarial Attacks in Credit Card Fraud Detection
• Learning in Repeated Multi-Objective Stackelberg Games with Payoff Manipulation
• ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine
• Transplant Then Regenerate: A New Paradigm for Text Data Augmentation
• Emerson-Lei and Manna-Pnueli Games for LTLf+ and PPLTL+ Synthesis
• AFABench: A Generic Framework for Benchmarking Active Feature Acquisition
• Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
• Cross-Modality Controlled Molecule Generation with Diffusion Language Model
• Reliable generation of isomorphic physics problems using ChatGPT with prompt-chaining and tool use
• PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
• TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting
• MF-LPR$^2$: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow
• DINOv3 with Test-Time Training for Medical Image Registration
• TransLight: Image-Guided Customized Lighting Control with Generative Decoupling
• Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs
• From Passive Tool to Socio-cognitive Teammate: A Conceptual Framework for Agentic AI in Human-AI Collaborative Learning
• Long Chain-of-Thought Reasoning Across Languages
• $TIME[t] \subseteq SPACE[O(\sqrt{t})]$ via Tree Height Compression
• Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
• Benchmarking graph construction by large language models for coherence-driven inference
• Reference-Aligned Retrieval-Augmented Question Answering over Heterogeneous Proprietary Documents
• Unsupervised Learning for Quadratic Assignment
• Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs
• The NordDRG AI Benchmark for Large Language Models
• Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)
• Nash Convergence of Mean-Based Learning Algorithms in First-Price Auctions
• Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users
• Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning
• Estimation of Energy-dissipation Lower-bounds for Neuromorphic Learning-in-memory
• Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Tracking
• LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
• Social Debiasing for Fair Multi-modal LLMs
• Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources
• A Little Human Data Goes A Long Way
• SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
• Identity Preserving 3D Head Stylization with Multiview Score Distillation
• The importance of visual modelling languages in generative software engineering
• Action Engine: Automatic Workflow Generation in FaaS
• Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?
• Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving
• Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions
• Generative AI in K-12 Education: The CyberScholar Initiative
• JudgeLRM: Large Reasoning Models as a Judge
• Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement
• PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models
• Hands-On: Segmenting Individual Signs from Continuous Sequences
• A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures
• Computing-In-Memory Dataflow for Minimal Buffer Traffic
• ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities
• Large Language Models are Highly Aligned with Human Ratings of Emotional Stimuli
• Explaining Hitori Puzzles: Neurosymbolic Proof Staging for Sequential Decisions
• Automated Optimization Modeling through Expert-Guided Large Language Model Reasoning
• The Agent Behavior: Model, Governance and Challenges in the AI Digital Age
• Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs
• LeanGeo: Formalizing Competitional Geometry problems in Lean
• Entropy-Constrained Strategy Optimization in Urban Floods: A Multi-Agent Framework with LLM and Knowledge Graph Integration
• MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
• Data-Driven Probabilistic Evaluation of Logic Properties with PAC-Confidence on Mealy Machines
• Privileged Self-Access Matters for Introspection in AI
• The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget
• FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
• MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging
• T-REX: Table -- Refute or Entail eXplainer
• Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks
• Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models
• A Multi-Agent Approach to Neurological Clinical Reasoning
• An automatic patent literature retrieval system based on LLM-RAG
• Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation
• Revisit Choice Network for Synthesis and Technology Mapping
• Special-Character Adversarial Attacks on Open-Source Language Model
• Edge-Selector Model Applied for Local Search Neighborhood for Solving Vehicle Routing Problems
• MCLPD:Multi-view Contrastive Learning for EEG-based PD Detection Across Datasets
• GEPD:GAN-Enhanced Generalizable Model for EEG-Based Detection of Parkinson's Disease
• Explainable Graph Spectral Clustering For Text Embeddings
• PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning
• Label Smoothing is a Pragmatic Information Bottleneck
• GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values
• FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics
• CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection
• DLLMQuant: Quantizing Diffusion-based Large Language Models
• Logical Expressivity and Explanations for Monotonic GNNs with Scoring Functions
• Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation Budgets
• Non-Dissipative Graph Propagation for Non-Local Community Detection
• No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
• Domain Translation of a Soft Robotic Arm using Conditional Cycle Generative Adversarial Network
• Implicit Hypergraph Neural Network
• You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation
• High-Throughput Low-Cost Segmentation of Brightfield Microscopy Live Cell Images
• SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
• PAPPL: Personalized AI-Powered Progressive Learning Platform
• Surya: Foundation Model for Heliophysics
• Federated Action Recognition for Smart Worker Assistance Using FastPose
• Ambiguity Resolution with Human Feedback for Code Writing Tasks
• Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings
• Enriching Moral Perspectives on AI: Concepts of Trust amongst Africans
• Documenting Deployment with Fabric: A Repository of Real-World AI Governance
• SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning
• AI Agents for Photonic Integrated Circuit Design Automation
• A Cost-Effective Framework for Predicting Parking Availability Using Geospatial Data and Machine Learning
• CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection
• Fracture Detection and Localisation in Wrist and Hand Radiographs using Detection Transformer Variants
• An Improved Multi-Agent Algorithm for Cooperative and Competitive Environments by Identifying and Encouraging Cooperation among Agents
• Automated surgical planning with nnU-Net: delineation of the anatomy in hepatobiliary phase MRI
• ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification
• STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers
• The Statistical Validation of Innovation Lens
• Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs
• A Systematic Study of Deep Learning Models and xAI Methods for Region-of-Interest Detection in MRI Scans
• LENS: Learning to Segment Anything with Unified Reinforced Reasoning
• RynnEC: Bringing MLLMs into Embodied World
• A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment
• New Insights into Automatic Treatment Planning for Cancer Radiotherapy Using Explainable Artificial Intelligence
• Incident Analysis for AI Agents
• Effect of Data Augmentation on Conformal Prediction for Diabetic Retinopathy
• Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
• Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning
• Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models
• OccluNet: Spatio-Temporal Deep Learning for Occlusion Detection on DSA
• Pixels to Play: A Foundation Model for 3D Gameplay
• GLASS: Test-Time Acceleration for LLMs via Global-Local Neural Importance Aggregation
• Learning Time-Varying Convexifications of Multiple Fairness Measures
• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
• Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
• Power Stabilization for AI Training Datacenters
• A Comparative Evaluation of Teacher-Guided Reinforcement Learning Techniques for Autonomous Cyber Operations
• Generative AI Against Poaching: Latent Composite Flow Matching for Wildlife Conservation
• Inter-Class Relational Loss for Small Object Detection: A Case Study on License Plates
• Organ-Agents: Virtual Human Physiology Simulator via LLMs
• Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation