AI Research News Feeds for August 20th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Nanopore sequencing of intact aminoacylated tRNAs
• What counts as plagiarism? AI-generated papers pose new risks
• The importance of negative training data for robust antibody binding prediction
• Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol
• SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration
• Training data composition determines machine learning generalization and biological rule discovery
• AI-based diagnosis of acute aortic syndrome from noncontrast CT
• A comprehensive deep learning approach to improve enchondroma detection on X-ray images
• Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition
• Diffusion-Driven High-Dimensional Variable Selection
• LEARNER: A Transfer Learning Method for Low-Rank Matrix Estimation
• RadGPT: Constructing 3D Image-Text Tumor Datasets
• Rapid Urban Visibility Hotspots: Quantifying Building Vertex Visibility from Connected Vehicle Trajectories using Spatial Indexing
• BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet
• UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis
• Colon Polyps Detection from Colonoscopy Images Using Deep Learning
• Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology
• PediDemi -- A Pediatric Demyelinating Lesion Segmentation Dataset
• InnerGS: Internal Scenes Rendering via Factorized 3D Gaussian Splatting
• Susceptibility Distortion Correction of Diffusion MRI with a single Phase-Encoding Direction
• Towards Understanding and Harnessing the Transferability of Prognostic Knowledge in Computational Pathology
• ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environments
• State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability
• Model-based Multi-object Visual Tracking: Identification and Standard Model Limitations
• subCellSAM: Zero-Shot (Sub-)Cellular Segmentation for Hit Validation in Drug Discovery
• Deep Biomechanically-Guided Interpolation for Keypoint-Based Brain Shift Registration
• Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing
• Is-NeRF: In-scattering Neural Radiance Field for Blurred Images
• Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction
• Multimodal Data Storage and Retrieval for Embodied AI: A Survey
• Learning to See Through Flare
• MMIS-Net for Retinal Fluid Segmentation and Detection
• Real-Time, Population-Based Reconstruction of 3D Bone Models via Very-Low-Dose Protocols
• Augmenting cobots for sheet-metal SMEs with 3D object recognition and localisation
• UNICON: UNIfied CONtinual Learning for Medical Foundational Models
• Advancing Toward Robust and Scalable Fingerprint Orientation Estimation: From Gradients to Deep Learning
• Diffusion Noise Feature: Accurate and Fast Generated Image Detection
• A global optimization SAR image segmentation model can be easily transformed to a general ROF denoising model
• SAR image segmentation algorithms based on I-divergence-TV model
• Active contours driven by local and global intensity fitting energy with application to SAR image segmentation and its fast solvers
• Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
• ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection
• HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model
• WHALES: A Multi-Agent Scheduling Dataset for Enhanced Cooperation in Autonomous Driving
• ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation
• Image Augmentation Agent for Weakly Supervised Semantic Segmentation
• MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition
• Towards Vision Zero: The TUM Traffic Accid3nD Dataset
• AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs
• Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
• DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting
• EmoSEM: Segment and Explain Emotion Stimuli in Visual Art
• Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer
• ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
• Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Weighted Intermediate Feature Divergence
• MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation
• FreqDGT: Frequency-Adaptive Dynamic Graph Networks with Transformer for Cross-subject EEG Emotion Recognition
• Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers
• Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline
• Regional quality estimation for echocardiography using deep learning
• SEA-LION: Southeast Asian Languages in One Network
• Crossing Borders Without Crossing Boundaries: How Sociolinguistic Awareness Can Optimize User Engagement with Localized Spanish AI Models Across Hispanophone Countries
• Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization
• Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
• MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation
• YOLO11-CR: a Lightweight Convolution-and-Attention Framework for Accurate Fatigue Driving Detection
• DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model
• Exploration of Deep Learning Based Recognition for Urdu Text
• Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
• Automated Assessment of Aesthetic Outcomes in Facial Plastic Surgery
• Applications of Small Language Models in Medical Imaging Classification with a Focus on Prompt Strategies
• AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report
• EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis
• Revisiting MLLM Token Technology through the Lens of Classical Visual Coding
• MINR: Efficient Implicit Neural Representations for Multi-Image Encoding
• Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations
• AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results
• Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations
• FAMNet: Integrating 2D and 3D Features for Micro-expression Recognition via Multi-task Learning and Hierarchical Attention
• AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes
• Bridging the Gap: Doubles Badminton Analysis with Singles-Trained Models
• 2D Gaussians Meet Visual Tokenizer
• GazeProphet: Software-Only Gaze Prediction for VR Foveated Rendering
• A Lightweight Dual-Mode Optimization for Generative Face Video Coding
• Color Spike Data Generation via Bio-inspired Neuron-like Encoding with an Artificial Photoreceptor Layer
• DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup
• Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics
• Generative Model-Based Feature Attention Module for Video Action Analysis
• Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model
• Bridging Clear and Adverse Driving Conditions
• Towards Efficient Vision State Space Models via Token Merging
• Unleashing Semantic and Geometric Priors for 3D Scene Completion
• PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction
• Two-Factor Authentication Smart Entryway Using Modified LBPH Algorithm
• TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis
• RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance
• DiffIER: Optimizing Diffusion Models with Iterative Error Reduction
• OmniTry: Virtual Try-On Anything without Masks
• DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction
• HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
• Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
• Hierarchical Vision-Language Retrieval of Educational Metaverse Content in Agriculture
• Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance
• MR6D: Benchmarking 6D Pose Estimation for Mobile Robots
• Shape-from-Template with Generalised Camera
• VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization
• Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
• Self-Aware Adaptive Alignment: Enabling Accurate Perception for Intelligent Transportation Systems
• SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation
• RED.AI Id-Pattern: First Results of Stone Deterioration Patterns with Multi-Agent Systems
• RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
• In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
• Forecasting Smog Events Using ConvLSTM: A Spatio-Temporal Approach for Aerosol Index Prediction in South Asia
• SCRNet: Spatial-Channel Regulation Network for Medical Ultrasound Image Segmentation
• PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
• DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts
• ViT-FIQA: Assessing Face Image Quality using Vision Transformers
• ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving
• OmViD: Omni-supervised active learning for video action detection
• Physics-Based 3D Simulation for Synthetic Data Generation and Failure Analysis in Packaging Stability Assessment
• Self-Supervised Sparse Sensor Fusion for Long Range Perception
• ResPlan: A Large-Scale Vector-Graph Dataset of 17,000 Residential Floor Plans
• Online 3D Gaussian Splatting Modeling with Novel View Selection
• Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
• InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing
• Distilled-3DGS:Distilled 3D Gaussian Splatting
• Beyond Simple Edits: Composed Video Retrieval with Dense Modifications
• LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
• Query Logs Analytics: A Aystematic Literature Review
• BQA: Body Language Question Answering Dataset for Video Large Language Models
• Consolidating and Developing Benchmarking Datasets for the Nepali Natural Language Understanding Tasks
• Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain
• Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
• Basic Category Usage in Vision Language Models
• Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora
• Stands to Reason: Investigating the Effect of Reasoning on Idiomaticity Detection
• MATA (m\=ata): Mindful Assessment of the Telugu Abilities of Large Language Models
• AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
• CRISP: Persistent Concept Unlearning via Sparse Autoencoders
• EEG-MedRAG: Enhancing EEG-based Clinical Decision-Making via Hierarchical Hypergraph Retrieval-Augmented Generation
• Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA
• MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
• Can Large Language Models (LLMs) Describe Pictures Like Children? A Comparative Corpus Study
• TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domain
• Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding
• MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models
• ReviewGraph: A Knowledge Graph Embedding Based Framework for Review Rating Prediction with Sentiment Features
• Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
• The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities
• Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
• Breaking (Global) Barriers in Parallel Stochastic Optimization with Wait-Avoiding Group Averaging
• Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines
• Finite Expression Method for Solving High-Dimensional Partial Differential Equations
• Active Learning of Mealy Machines with Timers
• Contrastive Learning on Multimodal Analysis of Electronic Health Records
• Robustly estimating heterogeneity in factorial data using Rashomon Partitions
• Disciplined Geodesically Convex Programming
• Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection
• Parallel Network Reconstruction with Multi-directional Regularization
• Development of Pre-Trained Transformer-based Models for the Nepali Language
• TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations
• Investigating the importance of county-level characteristics in opioid-related mortality across the United States
• Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation
• Hybrid Machine Learning Model with a Constrained Action Space for Trajectory Prediction
• Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
• Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments
• Rectifying Conformity Scores for Better Conditional Coverage
• MR-EEGWaveNet: Multiresolutional EEGWaveNet for Seizure Detection from Long EEG Recordings
• Cross-Modal Characterization of Thin Film MoS$_2$ Using Generative Models
• BLIPs: Bayesian Learned Interatomic Potentials
• Learning from Preferences and Mixed Demonstrations in General Settings
• FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
• Sex-Specific Vascular Score: A Novel Perfusion Biomarker from Supervoxel Analysis of 3D pCASL MRI
• Modeling GRNs with a Probabilistic Categorical Framework
• The Course Difficulty Analysis Cookbook
• Structural Foundations for Leading Digit Laws: Beyond Probabilistic Mixtures
• Automated Cervical Cancer Detection through Visual Inspection with Acetic Acid in Resource-Poor Settings with Lightweight Deep Learning Models Deployed on an Android Device
• CLoE: Curriculum Learning on Endoscopic Images for Robust MES Classification
• DAASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
• Flow Matching-Based Generative Modeling for Efficient and Scalable Data Assimilation
• A Risk Manager for Intrusion Tolerant Systems: Enhancing HAL 9000 with New Scoring and Data Sources
• OrbitChain: Orchestrating In-orbit Real-time Analytics of Earth Observation Data
• Vision Transformers for Kidney Stone Image Classification: A Comparative Study with CNNs
• Multi-view Clustering via Bi-level Decoupling and Consistency Learning
• Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation
• Compressed Models are NOT Trust-equivalent to Their Large Counterparts
• Understanding Distribution Structure on Calibrated Recommendation Systems
• Towards safe control parameter tuning in distributed multi-agent systems
• ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?
• Know Me by My Pulse: Toward Practical Continuous Authentication on Wearable Devices via Wrist-Worn PPG
• Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms
• Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering
• Smooth Flow Matching
• Online Conformal Selection with Accept-to-Reject Changes
• Generalisation and benign over-fitting for linear regression onto random functional covariates
• A PC Algorithm for Max-Linear Bayesian Networks
• Uncertainty-Aware PCA for Arbitrarily Distributed Data Modeled by Gaussian Mixture Models
• Machine Learning H-theorem
• Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
• Disentangled Representation Learning with the Gromov-Monge Gap
• Correlations Are Ruining Your Gradient Descent
• FDR-SVM: A Federated Distributionally Robust Support Vector Machine via a Mixture of Wasserstein Balls Ambiguity Set
• A Causal Graph-Enhanced Gaussian Process Regression for Modeling Engine-out NOx
• Rethinking Weight-Averaged Model-merging
• High-Order Tensor Regression in Sparse Convolutional Neural Networks
• Environmental Feature Engineering and Statistical Validation for ML-Based Path Loss Prediction
• Closed-Form Feedback-Free Learning with Forward Projection
• Joint Learning of Energy-based Models and their Partition Function
• Enhancing Cost Efficiency in Active Learning with Candidate Set Query
• Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization
• A kinetic-based regularization method for data science applications
• Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design
• Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data
• Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning
• Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing
• Can Masked Autoencoders Also Listen to Birds?
• MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
• Always Skip Attention
• Epistemic Wrapping for Uncertainty Quantification
• Quiet Feature Learning in Algorithmic Tasks
• Good Things Come in Pairs: Paired Autoencoders for Inverse Problems
• Bidirectional Information Flow (BIF) -- A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
• Flexible Operator Fusion for Fast Sparse Transformer with Diverse Masking on GPU
• SymMatika: Structure-Aware Symbolic Discovery
• PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform
• Improving DAPO from a Mixed-Policy Perspective
• A Comprehensive Re-Evaluation of Biometric Modality Properties in the Modern Era
• Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
• Automated Energy-Aware Time-Series Model Deployment on Embedded FPGAs for Resilient Combined Sewer Overflow Management
• How Usable is Automated Feature Engineering for Tabular Data?
• Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem
• AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics
• Multi-User Contextual Cascading Bandits for Personalized Recommendation
• Formal Algorithms for Model Efficiency
• GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
• Typed Topological Structures Of Datasets
• Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models
• Recipes for Pre-training LLMs with MXFP8
• PlantDeBERTa: An Open Source Language Model for Plant Science
• ConTextTab: A Semantics-Aware Tabular In-Context Learner
• Scaling Intelligence: Designing Data Centers for Next-Gen Language Models
• Neural Cellular Automata for ARC-AGI
• Segment Anything in Pathology Images with Natural Language
• Tensor Program Optimization for the RISC-V Vector Extension Using Probabilistic Programs
• Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation
• Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
• Spatial-Temporal Transformer with Curriculum Learning for EEG-Based Emotion Recognition
• BERT-VQA: Visual Question Answering on Plots
• Strategies for training point distributions in physics-informed neural networks
• A Recurrent Neural Network based Clustering Method for Binary Data Sets in Education
• RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
• Data driven feedback linearization of nonlinear control systems via Lie derivatives and stacked regression approach
• Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation
• Towards Human-AI Complementarity in Matching Tasks
• Efficient Constraint-Aware Flow Matching via Randomized Exploration
• Decoding Communications with Partial Information
• X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms
• Dimension lower bounds for linear approaches to function approximation
• Adaptive Conformal Prediction Intervals Over Trajectory Ensembles
• Batching-Aware Joint Model Onloading and Offloading for Hierarchical Multi-Task Inference
• NovoMolGen: Rethinking Molecular Language Model Pretraining
• Decentralized Contextual Bandits with Network Adaptivity
• MAVIS: Multi-Objective Alignment via Value-Guided Inference-Time Search
• ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate
• Hierarchy-Consistent Learning and Adaptive Loss Balancing for Hierarchical Multi-Label Classification
• Classifying Clinical Outcome of Epilepsy Patients with Ictal Chirp Embeddings
• DyMixOp: Guiding Neural Operator Design for PDEs from a Complex Dynamics Perspective with Local-Global-Mixing
• Uncertainty Tube Visualization of Particle Trajectories
• Explainability of Algorithms
• MuFlex: A Scalable, Physics-based Platform for Multi-Building Flexibility Analysis and Coordination
• CALYPSO: Forecasting and Analyzing MRSA Infection Patterns with Community and Healthcare Transmission Dynamics
• Prediction of Hospital Associated Infections During Continuous Hospital Stays
• A Generalized Learning Framework for Self-Supervised Contrastive Learning
• Approximate Bayesian Inference via Bitstring Representations
• Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
• Explainable Learning Rate Regimes for Stochastic Optimization
• Personalized Subgraph Federated Learning with Sheaf Collaboration
• MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning
• Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
• Minimizing the Weighted Number of Tardy Jobs: Data-Driven Heuristic for Single-Machine Scheduling
• Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
• DREAMS: Preserving both Local and Global Structure in Dimensionality Reduction
• Order Optimal Regret Bounds for Sharpe Ratio Optimization in the Bandit Setting
• Communication-Efficient Federated Learning with Adaptive Number of Participants
• Reinforcement Learning-based Adaptive Path Selection for Programmable Networks
• Disentangled Deep Smoothed Bootstrap for Fair Imbalanced Regression
• FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
• The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats
• Generics and Default Reasoning in Large Language Models
• Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
• On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
• Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks
• Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
• COMPASS: A Multi-Dimensional Benchmark for Evaluating Code Generation in Large Language Models
• PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
• Agentic DraCor and the Art of Docstring Engineering: Evaluating MCP-empowered LLM Usage of the DraCor API
• Comparing Conditional Diffusion Models for Synthesizing Contrast-Enhanced Breast MRI from Pre-Contrast Images
• DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer
• BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web
• A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports
• Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs
• Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
• The illusion of a perfect metric: Why evaluating AI's words is harder than it looks
• Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling
• One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
• UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler
• Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer
• Fisher-Orthogonal Projection Methods for Natural Gradient Descent with Large Batches
• Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control
• InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems
• Prompt Orchestration Markup Language
• A Mechanism for Mutual Fairness in Cooperative Games with Replicable Resources -- Extended Version
• Learning to Use AI for Learning: How Can We Effectively Teach and Measure Prompting Literacy for K-12 Students?
• RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
• The Social Context of Human-Robot Interactions
• Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
• Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
• ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis and Biomarker Discovery
• Evaluating Identity Leakage in Speaker De-Identification Systems
• Efficient Knowledge Graph Unlearning with Zeroth-order Information
• Ask Good Questions for Large Language Models
• Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
• GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
• LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
• Where to Go Next Day: Multi-scale Spatial-Temporal Decoupled Model for Mid-term Human Mobility Prediction
• VRoPE: Rotary Position Embedding for Video Large Language Models
• The StudyChat Dataset: Student Dialogues With ChatGPT in an Artificial Intelligence Course
• GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas
• Hawkeye:Efficient Reasoning with Model Collaboration
• Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
• Trust, but verify
• Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots
• It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics
• Language-Guided Multi-Agent Learning in Simulations: A Unified Framework and Evaluation
• Modeling the Diachronic Evolution of Legal Norms: An LRMoo-Based, Component-Level Approach
• Efficient Network Automatic Relevance Determination
• Dispositions and Roles of Generically Dependent Entities
• Towards Urban Planing AI Agent in the Age of Agentic AI
• Data-Efficient Safe Policy Improvement Using Parametric Structure
• Adaptation and Optimization of Automatic Speech Recognition (ASR) for the Maritime Domain in the Field of VHF Communication
• LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds
• "I see models being a whole other thing": An Empirical Study of Pre-Trained Model Naming Conventions and A Tool for Enhancing Naming Consistency
• Radio Map Estimation: Empirical Validation and Analysis
• Joint Problems in Learning Multiple Dynamical Systems
• Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification
• iTBLS: A Dataset of Interactive Conversations Over Tabular Information
• Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy
• Boolean Matrix Logic Programming on the GPU
• Vision Backbone Efficient Selection for Image Classification in Low-Data Regimes
• SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation
• Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy
• DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework
• Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Users
• Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
• Parameter-Efficient Continual Fine-Tuning: A Survey
• POPri: Private Federated Learning using Preference-Optimized Synthetic Data
• Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models
• Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors
• Position: We Need Responsible, Application-Driven (RAD) AI Research
• "Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs
• Sample Complexity of Diffusion Model Training Without Empirical Risk Minimizer Access
• G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• Piano: A Multi-Constraint Pin Assignment-Aware Floorplanner
• Sustainable AI Training via Hardware-Software Co-Design on NVIDIA, AMD, and Emerging GPU Architectures
• White-Box Reasoning: Synergizing LLM Strategy and gm/Id Data for Automated Analog Circuit Design
• Toward an African Agenda for AI Safety
• Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios
• MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
• Combating Homelessness Stigma with LLMs: A New Multi-Modal Dataset for Bias Detection
• Preference Models assume Proportional Hazards of Utilities
• Contextual Attention-Based Multimodal Fusion of LLM and CNN for Sentiment Analysis
• The Rise of Generative AI for Metal-Organic Framework Design and Synthesis
• Benchmarking LLM-based Agents for Single-cell Omics Analysis
• Utilizing the RAIN method and Graph SAGE Model to Identify Effective Drug Combinations for Gastric Neoplasm Treatment
• Research on Conversational Recommender System Considering Consumer Types
• Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions
• Deep Graph Neural Point Process For Learning Temporal Interactive Networks
• MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
• MIRAGE: Towards AI-Generated Image Detection in the Wild
• PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
• Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
• The Role of AI in Facilitating Interdisciplinary Collaboration: Evidence from AlphaFold
• Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Ray
• Quantifying Loss Aversion in Cyber Adversaries via LLM Analysis
• Involuntary Jailbreak
• Goal-Directedness is in the Eye of the Beholder
• ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models
• Hierarchical Conformal Classification
• GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis
• Diff-MSM: Differentiable MusculoSkeletal Model for Simultaneous Identification of Human Muscle and Bone Parameters
• A Surveillance Based Interactive Robot
• A Dual-Attention Graph Network for fMRI Data Classification
• Counterfactual Probabilistic Diffusion with Expert Models
• Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT
• Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
• Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis
• Semi-Supervised Anomaly Detection Pipeline for SOZ Localization Using Ictal-Related Chirp
• AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System
• ALIGN: Word Association Learning for Cross-Cultural Generalization in Large Language Models
• Mitigating Easy Option Bias in Multiple-Choice Question Answering
• AlphaX: An AI-Based Value Investing Strategy for the Brazilian Stock Market
• EventTSF: Event-Aware Non-Stationary Time Series Forecasting
• SVDformer: Direction-Aware Spectral Graph Embedding Learning via SVD and Transformer
• Dynamic Design of Machine Learning Pipelines via Metalearning
• Structured Prompting and Multi-Agent Knowledge Distillation for Traffic Video Interpretation and Risk Inference
• Consumer Autonomy or Illusion? Rethinking Consumer Agency in the Age of Algorithms
• STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models
• CORENet: Cross-Modal 4D Radar Denoising Network with LiDAR Supervision for Autonomous Driving
• LLM-Enhanced Linear Autoencoders for Recommendation
• ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
• Heterogeneous Influence Maximization in User Recommendation
• Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
• DDoS Attacks in Cloud Computing: Detection and Prevention
• Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models
• MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence
• EAvatar: Expression-Aware Head Avatar Reconstruction with Generative Geometry Priors
• FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
• Collapsing ROC approach for risk prediction research on both common and rare variants
• Physics-Informed Neural Networks for Programmable Origami Metamaterials with Controlled Deployment
• The 9th AI City Challenge
• End-to-End Audio-Visual Learning for Cochlear Implant Sound Coding in Noisy Environments
• A Comparative Study of Decoding Strategies in Medical Text Generation
• Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
• Bounding Causal Effects and Counterfactuals
• Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
• GRAFT: Gradient-Aware Fast MaxVol Technique for Dynamic Data Sampling
• Input Time Scaling
• In-Context Decision Making for Optimizing Complex AutoML Pipelines
• Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks
• Knowledge Graph Completion for Action Prediction on Situational Graphs -- A Case Study on Household Tasks
• MHSNet:An MoE-based Hierarchical Semantic Representation Network for Accurate Duplicate Resume Detection with Large Language Model
• Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
• The DeepLog Neurosymbolic Machine
• CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
• Expertise-aware Multi-LLM Recruitment and Collaboration for Medical Decision-Making
• Quantifier Instantiations: To Mimic or To Revolt?
• Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
• Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
• Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback
• The Collaboration Paradox: Why Generative AI Requires Both Strategic Intelligence and Operational Stability in Supply Chain Management
• ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
• A Biased Random Key Genetic Algorithm for Solving the Longest Run Subsequence Problem
• ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
• Preliminary suggestions for rigorous GPAI model evaluations
• TaoSR1: The Thinking Model for E-commerce Relevance Search
• EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code
• Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlists
• Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
• Cognitive Workspace: Active Memory Management for LLMs -- An Empirical Study of Functional Infinite Context
• AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining
• Fitting Ontologies and Constraints to Relational Structures
• A Hardware-oriented Approach for Efficient Active Inference Computation and Deployment
• The Interpretability Analysis of the Model Can Bring Improvements to the Text-to-SQL Task
• Search-Time Data Contamination
• QuickMerge++: Fast Token Merging with Autoregressive Prior
• AI sustains higher strategic tension than humans in chess
• Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
• "DIVE" into Hydrogen Storage Materials Discovery with AI Agents
• CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support
• Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention
• HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
• LOOP: A Plug-and-Play Neuro-Symbolic Framework for Enhancing Planning in Autonomous Systems
• SPANER: Shared Prompt Aligner for Multimodal Semantic Representation
• TASER: Table Agents for Schema-guided Extraction and Recommendation
• Virtuous Machines: Towards Artificial General Science
• STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting
• Discrete Optimization of Min-Max Violation and its Applications Across Computational Sciences
• LM Agents May Fail to Act on Their Own Risk Knowledge
• CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
• Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance
• Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
• V2P: From Background Suppression to Center Peaking for Robust GUI Grounding Task
• Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
• ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings