AI Research News Feeds for October 3rd, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Machine learning for accuracy in density functional approximations
• Multi-Scale Node Embeddings for Graph Modeling and Generation
• Learning Low-Dimensional Embeddings for Black-Box Optimization
• GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering
• Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
• Interpretable Machine Learning for Urban Heat Mitigation: Attribution and Weighting of Multi-Scale Drivers
• Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning
• Enhancing Electricity-System Resilience with Adaptive Robust Optimization and Conformal Uncertainty Characterization
• A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
• Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
• Learning Equivariant Models by Discovering Symmetries with Learnable Augmentations
• Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir Computing
• Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior
• Scaling Laws for Optimal Data Mixtures
• Synthetic Blips: Generalizing Synthetic Controls for Dynamic Treatment Effects
• CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection
• Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
• PRESOL: a web-based computational setting for feature-based flare forecasting
• Microscaling Floating Point Formats for Large Language Models
• Smooth Quasar-Convex Optimization with Constraints
• Bias beyond Borders: Global Inequalities in AI-Generated Music
• Multi-bit Audio Watermarking
• ShapeGen3DCP: A Deep Learning Framework for Layer Shape Prediction in 3D Concrete Printing
• Variational Secret Common Randomness Extraction
• Multidata Causal Discovery for Statistical Hurricane Intensity Forecasting
• SoundReactor: Frame-level Online Video-to-Audio Generation
• High-Fidelity Speech Enhancement via Discrete Audio Tokens
• Quantum Fisher information matrices from R\'enyi relative entropies
• Consistent End-to-End Estimation for Counterfactual Fairness
• Development and Validation of a Dynamic Kidney Failure Prediction Model based on Deep Learning: A Real-World Study with External Validation
• Neuro-Symbolic AI for Analytical Solutions of Differential Equations
• Riemannian Variational Flow Matching for Material and Protein Design
• Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study
• Policy Gradient Guidance Enables Test Time Control
• Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
• C2AL: Cohort-Contrastive Auxiliary Learning for Large-scale Recommendation Systems
• xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
• PUL-Inter-slice Defender: An Anomaly Detection Solution for Distributed Slice Mobility Attacks
• Transformers Discover Molecular Structure Without Graph Priors
• Diffusion^2: Turning 3D Environments into Radio Frequency Heatmaps
• Fine-Grained Urban Traffic Forecasting on Metropolis-Scale Road Networks
• Knowledge Distillation Detection for Open-weights Models
• Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
• KaVa: Latent Reasoning via Compressed KV-Cache Distillation
• Hybrid Predictive Modeling of Malaria Incidence in the Amhara Region, Ethiopia: Integrating Multi-Output Regression and Time-Series Forecasting
• Combining complex Langevin dynamics with score-based and energy-based diffusion models
• Learning to Play Multi-Follower Bayesian Stackelberg Games
• Financial Stability Implications of Generative AI: Taming the Animal Spirits
• Comparative Field Deployment of Reinforcement Learning and Model Predictive Control for Residential HVAC
• Universal Dynamic Regret and Constraint Violation Bounds for Constrained Online Convex Optimization
• Randomized Gradient Subspaces for Efficient Large Language Model Training
• Multi-marginal temporal Schr\"odinger Bridge Matching for video generation from unpaired data
• A Methodology for Transparent Logic-Based Classification Using a Multi-Task Convolutional Tsetlin Machine
• StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
• Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection
• Private Federated Multiclass Post-hoc Calibration
• PepCompass: Navigating peptide embedding spaces using Riemannian Geometry
• Normality Calibration in Semi-supervised Graph Anomaly Detection
• FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
• Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
• Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions
• Learning Model Representations Using Publicly Available Model Hubs
• PENEX: AdaBoost-Inspired Neural Network Regularization
• Hybrid Deep Learning Modeling Approach to Predict Natural Gas Consumption of Home Subscribers on Limited Data
• DAG DECORation: Continuous Optimization for Structure Learning under Hidden Confounding
• Posterior Collapse as a Phase Transition in Variational Autoencoders
• CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning
• Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking
• Support Basis: Fast Attention Beyond Bounded Entries
• PASTA: A Unified Framework for Offline Assortment Learning
• ActiNet: Activity intensity classification of wrist-worn accelerometers using self-supervised deep learning
• Accelerating Attention with Basis Decomposition
• Finite-Time Bounds for Distributionally Robust TD Learning with Linear Function Approximation
• Workplace Location Choice Model based on Deep Neural Network
• Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD
• Learning Regularization Functionals for Inverse Problems: A Comparative Study
• Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX
• Neural non-canonical Hamiltonian dynamics for long-time simulations
• Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation
• Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
• Learning Representations Through Contrastive Neural Model Checking
• Explicit Discovery of Nonlinear Symmetries from Dynamic Data
• Compositional meta-learning through probabilistic task inference
• How Well Can Preference Optimization Generalize Under Noisy Feedback?
• Fine-tuning LLMs with variational Bayesian last layer for high-dimensional Bayesian optimzation
• PEL-NAS: Search Space Partitioned Architecture Prompt Co-Evolutionary LLM-driven Hardware-Aware Neural Architecture Search
• Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets
• Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control
• Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
• CarbonX: An Open-Source Tool for Computational Decarbonization Using Time Series Foundation Models
• On Integer Programming for the Binarized Neural Network Verification Problem
• Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
• NVIDIA AI Aerial: AI-Native Wireless Communications
• TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
• Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
• MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
• Large-Scale Bayesian Causal Discovery with Interventional Data
• TetriServe: Efficient DiT Serving for Heterogeneous Image Generation
• Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
• Securing generative artificial intelligence with parallel magnetic tunnel junction true randomness
• Machines are more productive than humans until they aren't, and vice versa
• Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting
• ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
• Network-Level Vehicle Delay Estimation at Heterogeneous Signalized Intersections
• Quantum-inspired Benchmark for Estimating Intrinsic Dimension
• Self-Supervised Representation Learning as Mutual Information Maximization
• RheOFormer: A generative transformer model for simulation of complex fluids and flows
• Selective Underfitting in Diffusion Models
• Fine-Tuning Masked Diffusion for Provable Self-Correction
• Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
• SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
• SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion
• Fixing That Free Lunch: When, Where, and Why Synthetic Data Fails in Model-Based Policy Optimization
• Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
• Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
• PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection
• What happens when generative AI models train recursively on each others' outputs?
• Enhanced DACER Algorithm with High Diffusion Efficiency
• CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
• Localized Forest Fire Risk Prediction: A Department-Aware Approach for Operational Decision Support
• MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
• PlaceFM: A Training-free Geospatial Foundation Model of Places using Large-Scale Point of Interest Data
• Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
• VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks
• nDNA -- the Semantic Helix of Artificial Cognition
• R2 v2: The Pareto-compliant R2 Indicator for Better Benchmarking in Bi-objective Optimization
• QSpec: Speculative Decoding with Complementary Quantization Schemes
• Faster LLM Inference using DBMS-Inspired Preemption and Cache Replacement Policies
• Unraveling Indirect In-Context Learning Using Influence Functions
• Paper Quality Assessment based on Individual Wisdom Metrics from Open Peer Review
• Forget Forgetting: Continual Learning in a World of Abundant Memory
• CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation
• Knowledge-guided machine learning for county-level corn yield prediction under drought
• When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
• Towards Effective E-Participation of Citizens in the European Union: The Development of AskThePublic
• AI-Powered Inverse Design of Ku-Band SIW Resonant Structures by Iterative Residual Correction Network
• How to Find Fantastic Papers: Self-Rankings as a Powerful Predictor of Scientific Impact Beyond Peer Review
• Comparing Contrastive and Triplet Loss in Audio-Visual Embedding: Intra-Class Variance and Greediness Analysis
• SIEVE: Towards Verifiable Certification for Code-datasets
• Go witheFlow: Real-time Emotion Driven Audio Effects Modulation
• GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
• Detection of Chagas Disease from the ECG: The George B. Moody PhysioNet Challenge 2025
• DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
• How to Combat Reactive and Dynamic Jamming Attacks with Reinforcement Learning
• Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
• A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
• Towards end-to-end ASP computation
• Forms of Understanding for XAI-Explanations
• Goal Recognition Design for General Behavioral Agents using Machine Learning
• A Flexible Method for Behaviorally Measuring Alignment Between Human and Artificial Intelligence Using Representational Similarity Analysis
• AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
• Neurosymbolic Association Rule Mining from Tabular Data
• Schema Generation for Large Knowledge Graphs Using Large Language Models
• Latency-aware Multimodal Federated Learning over UAV Networks
• Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement
• Rethinking the shape convention of an MLP
• SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment
• Pre-Hoc Predictions in AutoML: Leveraging LLMs to Enhance Model Selection and Benchmarking for Tabular datasets
• NGGAN: Noise Generation GAN Based on the Practical Measurement Dataset for Narrowband Powerline Communications
• A Modular Theory of Subjective Consciousness for Natural and Artificial Minds
• FINCH: Financial Intelligence using Natural language for Contextualized SQL Handling
• Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection
• HRTFformer: A Spatially-Aware Transformer for Personalized HRTF Upsampling in Immersive Audio Rendering
• Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement
• Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement
• Clarifying Semantics of In-Context Examples for Unit Test Generation
• The Current State of AI Bias Bounties: An Overview of Existing Programmes and Research
• KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network
• VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
• BioinfoMCP: A Unified Platform Enabling MCP Interfaces in Agentic Bioinformatics
• Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
• The Three Regimes of Offline-to-Online Reinforcement Learning
• RealClass: A Framework for Classroom Speech Simulation with Public Datasets and Game Engines
• Pharmacophore-Guided Generative Design of Novel Drug-Like Molecules
• Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
• Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
• Predictive Modeling and Explainable AI for Veterinary Safety Profiles, Residue Assessment, and Health Outcomes Using Real-World Data and Physicochemical Properties
• Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization
• From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?
• Enhancing Noise Robustness of Parkinson's Disease Telemonitoring via Contrastive Feature Augmentation
• BioBlobs: Differentiable Graph Partitioning for Protein Representation Learning
• Source-Free Cross-Domain Continual Learning
• The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
• Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
• Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing
• Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value
• Representational Alignment Across Model Layers and Brain Regions with Hierarchical Optimal Transport
• BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals
• Quantum-Assisted Correlation Clustering
• Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
• Kant: An Efficient Unified Scheduling System for Large-Scale AI Clusters
• IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
• RSTGCN: Railway-centric Spatio-Temporal Graph Convolutional Network for Train Delay Prediction
• Budgeted Broadcast: An Activity-Dependent Pruning Rule for Neural Network Efficiency
• Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations
• Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
• An Analysis of the New EU AI Act and A Proposed Standardization Framework for Machine Learning Fairness
• Emergent evaluation hubs in a decentralizing large language model ecosystem
• Evaluating New AI Cell Foundation Models on Challenging Kidney Pathology Cases Unaddressed by Previous Foundation Models
• Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours
• Enhancing the development of Cherenkov Telescope Array control software with Large Language Models
• DeMuon: A Decentralized Muon for Matrix Optimization over Graphs
• Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence
• Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems
• BioVERSE: Representation Alignment of Biomedical Modalities to LLMs for Multi-Modal Reasoning
• Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning
• To Mask or to Mirror: Human-AI Alignment in Collective Reasoning
• Zero-shot reasoning for simulating scholarly peer-review
• ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection
• Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning
• FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models
• LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning
• Step-Aware Policy Optimization for Reasoning in Diffusion Large Language Models
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
• AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence
• Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CDMPs
• Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective
• GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents
• MetaboT: AI-based agent for natural language-based interaction with metabolomics knowledge graphs
• A cybersecurity AI agent selection and decision support framework
• REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
• Human-AI Teaming Co-Learning in Military Operations
• OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
• Modeling Others' Minds as Code
• Cyber Academia-Chemical Engineering (CA-ChemE): A Living Digital Town for Self-Directed Research Evolution and Emergent Scientific Discovery
• The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
• Retrieval-Augmented Framework for LLM-Based Clinical Decision Support
• Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents
• OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models
• A Tale of LLMs and Induced Small Proxies: Scalable Agents for Knowledge Mining
• AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance
• Lateral Tree-of-Thoughts Surpasses ToT by Incorporating Logically-Consistent, Low-Utility Candidates
• Towards Interpretable and Inference-Optimal COT Reasoning with Sparse Autoencoder-Guided Generation
• Differentially Private Clustering in Data Streams
• Authentication Security of PRF GNSS Ranging
• An efficient quantum algorithm for computing $S$-units and its applications
• Privacy-Aware Sequential Learning
• Odontoceti: Ultra-Fast DAG Consensus with Two Round Commitment
• Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks
• Bypassing Prompt Guards in Production with Controlled-Release Prompting
• TAIBOM: Bringing Trustworthiness to AI-Enabled Systems
• FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
• Reproducible Builds for Quantum Computing
• A Quantitative Security Analysis of S-boxes in the NIST Lightweight Cryptography Finalists
• Differentially Private Federated Learning: A Systematic Review
• Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks
• It's not Easy: Applying Supervised Machine Learning to Detect Malicious Extensions in the Chrome Web Store
• Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
• Integrated Security Mechanisms for Weight Protection in Memristive Crossbar Arrays
• Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
• E-FuzzEdge: Optimizing Embedded Device Security with Scalable In-Place Fuzzing
• Securing IoT Devices in Smart Cities: A Review of Proposed Solutions
• POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
• Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
• Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
• Constructions of Efficiently Implementable Boolean Functions with Provable Nonlinearity/Resiliency/Algebraic Immunity Trade-Offs
• Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
• Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems
• NoMod: A Non-modular Attack on Module Learning With Errors
• Testing Stability and Robustness in Three Cryptographic Chaotic Systems
• TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling
• Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
• Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
• Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
• Handling Heterophily in Recommender Systems with Wavelet Hypergraph Diffusion
• REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
• Shilling Recommender Systems by Generating Side-feature-aware Fake User Profiles
• Gendered Inequalities in Online Harms: Fear, Safety Work, and Online Participation
• The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims
• MIRAGE: Patient-Specific Mixed Reality Coaching for MRI via Depth-Only Markerless Registration and Immersive VR
• Automatic inference of a anatomically meaningful solid wood texture from a single photograph
• ViscoReg: Neural Signed Distance Functions via Viscosity Solutions
• Location Matters: Leveraging Multi-Resolution Geo-Embeddings for Housing Search
• Are LLMs ready to help non-expert users to make charts of official statistics data?
• Optimal signals assignment for eBay View Item page
• MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
• IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data
• Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely
• Who is responsible? Social Identity, Robot Errors and Blame Attribution
• Komitee Equal Shares: Choosing Together as Voters and as Groups with a Co-designed Virtual Budget Algorithm
• Human-Robo-advisor collaboration in decision-making: Evidence from a multiphase mixed methods experimental study
• Agentic Reasoning and Refinement through Semantic Interaction
• EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioning
• A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation
• Multimodal Feedback for Task Guidance in Augmented Reality
• Multimodal Foundation Models for Early Disease Detection
• Understanding Dynamic Human-Robot Proxemics in the Case of Four-Legged Canine-Inspired Robots
• How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study
• Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies
• Software Engineering for Self-Adaptive Robotics: A Research Agenda
• Manim for STEM Education: Visualizing Complex Problems Through Animation
• Beyond Divergence: Characterizing Co-exploration Patterns in Collaborative Design Processes
• An Anthropologist LLM to Elicit Users' Moral Preferences through Role-Play
• An Optical Measurement System for Open-Source Tracking of Jaw Motions
• How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
• LegiScout: A Visual Tool for Understanding Complex Legislation
• Theory is Shapes
• The Command Line GUIde: Graphical Interfaces from Man Pages via AI
• From keywords to semantics: Perceptions of large language models in data discovery
• Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skills
• TimeGazer: Temporal Modeling of Predictive Gaze Stabilization for AR Interaction
• LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control
• One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion
• Safe Navigation of Bipedal Robots via Koopman Operator-Based Model Predictive Control
• A Tactile Feedback Approach to Path Recovery after High-Speed Impacts for Collision-Resilient Drones
• Interactive Expressive Motion Generation Using Dynamic Movement Primitives
• FalconWing: An Ultra-Light Indoor Fixed-Wing UAV Platform for Vision-Based Autonomy
• Physics-Constrained Robot Grasp Planning for Dynamic Tool Use
• DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
• ReactEMG: Zero-Shot, Low-Latency Intent Detection via sEMG
• CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks
• An effective control of large systems of active particles: An application to evacuation problem
• Sliced Distribution Matching based on Cumulative Distribution Functions with Applications to Control
• Model Evaluation of a Transformable CubeSat for Nonholonomic Attitude Reorientation Using a Drop Tower
• SCANS: A Soft Gripper with Curvature and Spectroscopy Sensors for In-Hand Material Differentiation
• Product Digital Twin Supporting End-of-life Phase of Electric Vehicle Batteries Utilizing Product-Process-Resource Asset Network
• Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0
• Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
• ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation
• Better Than "Better Than Nothing": Design Strategies for Enculturated Empathetic AI Robot Companions for Older Adults
• A Framework for Scalable Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLab
• A Robust Neural Control Design for Multi-drone Slung Payload Manipulation with Control Contraction Metrics
• Predictive Preference Learning from Human Interventions
• Cooperative Guidance for Aerial Defense in Multiagent Systems
• Data-Driven Distributionally Robust Optimal Control with State-Dependent Noise
• Statistical Uncertainty Learning for Robust Visual-Inertial State Estimation
• Symskill: Symbol and Skill Co-Invention for Data-Efficient and Real-Time Long-Horizon Manipulation
• Geometric Backstepping Control of Omnidirectional Tiltrotors Incorporating Servo-Rotor Dynamics for Robustness against Sudden Disturbances
• PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization
• Contrastive Representation Regularization for Vision-Language-Action Models
• Dual-Mode Magnetic Continuum Robot for Targeted Drug Delivery
• An Anytime, Scalable and Complete Algorithm for Embedding a Manufacturing Procedure in a Smart Factory
• Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
• What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
• Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots
• GreenhouseSplat: A Dataset of Photorealistic Greenhouse Simulations for Mobile Robotics
• TACOS: Task Agnostic COordinator of a multi-drone System
• SPARC: Spine with Prismatic and Revolute Compliance for Quadruped Robot
• Reducing Discomfort in Driving Simulators: Motion Cueing for Motion Sickness Mitigation
• EC3R-SLAM: Efficient and Consistent Monocular Dense SLAM with Feed-Forward 3D Reconstruction
• LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions
• Stand Up, NAO! Increasing the Reliability of Stand-Up Motions Through Error Compensation in Position Control
• Kilometer-Scale GNSS-Denied UAV Navigation via Heightmap Gradients: A Winning System from the SPRIN-D Challenge
• Safe Motion Planning and Control Using Predictive and Adaptive Barrier Methods for Autonomous Surface Vessels
• A Stochastic Framework for Continuous-Time State Estimation of Continuum Robots
• INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models
• Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions
• How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?
• AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation
• Differentiable Skill Optimisation for Powder Manipulation in Laboratory Automation
• Touching the tumor boundary: A pilot study on ultrasound based virtual fixtures for breast-conserving surgery
• VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs
• Pose Estimation of a Thruster-Driven Bioinspired Multi-Link Robot
• Online Hierarchical Policy Learning using Physics Priors for Robot Navigation in Unknown Environments
• Real-time Multi-Plane Segmentation Based on GPU Accelerated High-Resolution 3D Voxel Mapping for Legged Robot Locomotion
• MiniBEE: A New Form Factor for Compact Bimanual Dexterity
• FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
• Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
• Neural Network Parameter-optimization of Gaussian pmDAGs
• Asymptotic theory of in-context learning by linear attention
• Policy-Oriented Binary Classification: Improving (KD-)CART Final Splits for Subpopulation Targeting
• Golden Ratio Weighting Prevents Model Collapse
• Online Multivariate Regularized Distributional Regression for High-dimensional Probabilistic Electricity Price Forecasting
• SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation
• WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection
• A fast and effective kernel two-sample test for large-scale data
• Weighted Sequential Bayesian Inference for Non-Stationary Linear Contextual Bandits
• Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization
• Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
• Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity
• Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
• To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
• A theoretical framework for M-posteriors: frequentist guarantees and robustness properties
• DiffKnock: Diffusion-based Knockoff Statistics for Neural Networks Inference
• Scalable Asynchronous Federated Modeling for Spatial Data
• Predictively Oriented Posteriors
• Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
• Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference
• Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
• Ensemble Threshold Calibration for Stable Sensitivity Control
• Reinforcement Learning with Action-Triggered Observations
• Flatness-Aware Stochastic Gradient Langevin Dynamics
• Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
• Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models
• Drop-Muon: Update Less, Converge Faster
• Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
• AI Foundation Model for Time Series with Innovations Representation
• A reproducible comparative study of categorical kernels for Gaussian process regression, with new clustering-based nested kernels
• Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero
• Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
• Uniform-in-time convergence bounds for Persistent Contrastive Divergence Algorithms
• Adaptive Kernel Selection for Stein Variational Gradient Descent
• Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
• Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale
• Efficient Probabilistic Visualization of Local Divergence of 2D Vector Fields with Independent Gaussian Uncertainty
• Safe Reinforcement Learning-Based Vibration Control: Overcoming Training Risks with LQR Guidance
• Low Rank Gradients and Where to Find Them
• On the Identifiability of Latent Action Policies
• Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity
• Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
• How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
• Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion
• NeoARCADE: Robust Calibration for Distance Estimation to Support Assistive Drones for the Visually Impaired
• Feature Representation Transferring to Lightweight Models via Perception Coherence
• Learning to Weight Parameters for Training Data Attribution
• AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation
• Development of a Mobile Application for at-Home Analysis of Retinal Fundus Images
• Towards Methane Detection Onboard Satellites
• SUPER-Net: Trustworthy Image Segmentation via Uncertainty Propagation in Encoder-Decoder Networks
• Grasp Pre-shape Selection by Synthetic Training: Eye-in-hand Shared Control on the Hannes Prosthesis
• Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
• Hierarchical place recognition with omnidirectional images and curriculum learning-based loss functions
• Subspace Node Pruning
• NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields
• Continuous Wrist Control on the Hannes Prosthesis: a Vision-based Shared Autonomy Framework
• Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations
• One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
• RGS-DR: Deferred Reflections and Residual Shading in 2D Gaussian Splatting
• LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition
• Fusing Foveal Fixations Using Linear Retinal Transformations and Bayesian Experimental Design
• PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
• Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
• GARLIC: GAussian Representation LearnIng for spaCe partitioning
• Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
• LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR
• Concept Unlearning by Modeling Key Steps of Diffusion Process
• VITA: Vision-to-Action Flow Matching Policy
• LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
• Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution
• There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
• What Makes a Good Dataset for Knowledge Distillation?
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
• Post-hoc Probabilistic Vision-Language Models
• DreamOmni: Unified Image Generation and Editing
• A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
• Diffusion Adversarial Post-Training for One-Step Video Generation
• Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning
• L4P: Towards Unified Low-Level 4D Vision Perception
• How far can we go with ImageNet for Text-to-Image generation?
• What are You Looking at? Modality Contribution in Multimodal Medical Deep Learning
• An Improved Pure Fully Connected Neural Network for Rice Grain Classification
• Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
• VaPR -- Vision-language Preference alignment for Reasoning
• Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models
• Unsupervised Dynamic Feature Selection for Robust Latent Spaces in Vision Tasks
• GFSR-Net: Guided Focus via Segment-Wise Relevance Network for Interpretable Deep Learning in Medical Imaging
• ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKs
• ROI-GS: Interest-based Local Quality 3D Gaussian Splatting
• $\text{G}^2$RPO: Granular GRPO for Precise Reward in Flow Models
• A Multicentric Dataset for Training and Benchmarking Breast Cancer Segmentation in H&E Slides
• Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects
• SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
• DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
• Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
• Measurement-Guided Consistency Model Sampling for Inverse Problems
• Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning
• Test-Time Anchoring for Discrete Diffusion Posterior Sampling
• Continual Personalization for Diffusion Models
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
• Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
• On the Role of Domain Experts in Creating Effective Tutoring Systems
• Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning
• ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations
• MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
• Median2Median: Zero-shot Suppression of Structured Noise in Images
• Beyond Simple Fusion: Adaptive Gated Fusion for Robust Multimodal Sentiment Analysis
• Inferring Dynamic Physical Properties from Video Foundation Models
• Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions
• StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
• Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity
• Development and Evaluation of an AI-Driven Telemedicine System for Prenatal Healthcare
• JaneEye: A 12-nm 2K-FPS 18.9-$\mu$J/Frame Event-based Eye Tracking Accelerator
• Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
• From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Review
• MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
• An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence
• VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
• Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
• GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation
• Cross-Breed Pig Identification Using Auricular Vein Pattern Recognition: A Machine Learning Approach for Small-Scale Farming Applications
• MMDEW: Multipurpose Multiclass Density Estimation in the Wild
• TempoControl: Temporal Attention Guidance for Text-to-Video Models
• RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
• DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
• From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding
• Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities
• NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes
• microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
• VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL
• Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
• Learning to Generate Object Interactions with Physics-Guided Video Diffusion
• MultiModal Action Conditioned Video Generation
• VideoNSA: Native Sparse Attention Scales Video Understanding
• NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation
• Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction
• Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
• ClustViT: Clustering-based Token Merging for Semantic Segmentation
• Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
• TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
• 4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
• Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution
• Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using GPT-4o: Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework
• LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstruction
• kabr-tools: Automated Framework for Multi-Species Behavioral Monitoring
• GaussianMorphing: Mesh-Guided 3D Gaussians for Semantic-Aware Object Morphing
• Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
• VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and Segmentation
• Mapping Historic Urban Footprints in France: Balancing Quality, Scalability and AI Techniques
• When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos
• FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation
• FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
• LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition
• VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
• Discrete Facial Encoding: : A Framework for Data-driven Facial Display Discovery
• Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale
• UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
• An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution
• Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
• Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring
• FreeViS: Training-free Video Stylization with Inconsistent References
• MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
• Holistic Order Prediction in Natural Scenes
• PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning
• LOBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction
• Pack and Force Your Memory: Long-form and Consistent Video Generation
• Calibrating the Full Predictive Class Distribution of 3D Object Detectors for Autonomous Driving
• Leveraging Prior Knowledge of Diffusion Model for Person Search
• DisCo: Reinforcement with Diversity Constraints for Multi-Human Generation
• GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
• Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
• Purrception: Variational Flow Matching for Vector-Quantized Image Generation
• AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging
• WALT: Web Agents that Learn Tools
• MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
• Towards Better Optimization For Listwise Preference in Diffusion Models
• Growing Visual Generative Capacity for Pre-Trained MLLMs
• Robust Classification of Oral Cancer with Limited Training Data
• Consistent Assistant Domains Transformer for Source-free Domain Adaptation
• Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations
• ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models
• NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
• Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics
• VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
• Joint Deblurring and 3D Reconstruction for Macrophotography
• Synergizing LLMs and Knowledge Graphs: A Novel Approach to Software Repository-Related Question Answering
• MathArena: Evaluating LLMs on Uncontaminated Math Competitions
• Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization
• DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
• Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
• Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
• Efficient Whole Slide Pathology VQA via Token Compression
• LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration
• Image Generation Based on Image Style Extraction
• EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels
• SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs
• Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation
• MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
• Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
• No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem
• Reason to Rote: Rethinking Memorization in Reasoning
• Flexible Feature Distillation for Large Language Models
• Reasoning Models are Test Exploiters: Rethinking Multiple-Choice
• AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs
• Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
• Interpretable Text Embeddings and Text Similarity Explanation: A Survey
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements
• FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4
• Probabilistic Reasoning with LLMs for k-anonymity Estimation
• TLUE: A Tibetan Language Understanding Evaluation Benchmark
• Boundless Byte Pair Encoding: Breaking the Pre-tokenization Barrier
• Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
• WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
• Design and Application of Multimodal Large Language Model Based System for End to End Automation of Accident Dataset Generation
• OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learning
• LEXam: Benchmarking Legal Reasoning on 340 Law Exams
• ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
• MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
• BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators
• Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation
• Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead
• When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy
• StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
• The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
• Study on LLMs for Promptagator-Style Dense Retriever Training
• ExGRPO: Learning to Reason from Experience
• The Unreasonable Effectiveness of Scaling Agents for Computer Use
• RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
• Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
• Interactive Training: Feedback-Driven Neural Network Optimization
• Superficial Safety Alignment Hypothesis
• Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
• Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations
• Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting
• Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
• Adapting Large Language Models for Character-based Augmentative and Alternative Communication
• Out-of-Distribution Detection using Synthetic Data Generation
• From Videos to Indexed Knowledge Graphs -- Framework to Marry Methods for Multimodal Content Analysis and Understanding
• Information Seeking for Robust Decision Making under Partial Observability
• InvThink: Towards AI Safety via Inverse Reasoning
• Synthetic Prefixes to Mitigate Bias in Real-Time Neural Query Autocomplete
• Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
• Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
• PychoBench: Evaluating the Psychology Intelligence of Large Language Models
• LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing
• Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
• Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls
• Position: Privacy Is Not Just Memorization!
• Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
• Improving AGI Evaluation: A Data Science Perspective
• Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction
• Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
• Constrained Adaptive Rejection Sampling
• Do AI Models Perform Human-like Abstract Reasoning Across Modalities?
• A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports
• Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge
• Utilizing Modern Large Language Models (LLM) for Financial Trend Analysis and Digest Creation
• Automated Extraction of Material Properties using LLM-based AI Agents
• RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
• RLP: Reinforcement as a Pretraining Objective
• LLM-based Multi-Agent Blackboard System for Information Discovery in Data Science
• Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
• Aristotle: IMO-level Automated Theorem Proving
• MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments
• WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
• Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
• Fine-tuning with RAG for Improving LLM Learning of New Skills
• Optimal Stopping vs Best-of-$N$ for Inference Time Optimization
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning
• LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning
• Extracting O*NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data
• Style Over Story: A Process-Oriented Study of Authorial Creativity in Large Language Models
• Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
• Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
• The Disparate Impacts of Speculative Decoding
• RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
• Learning to Reason for Hallucination Span Detection
• ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
• Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
• More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
• Enhanced Arabic-language cyberbullying detection: deep embedding and transformer (BERT) approaches
• AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications
• Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
• InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
• Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
• From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
• F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
• Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
• Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
• How Do Language Models Compose Functions?
• Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
• What MLLMs Learn about When they Learn about Multimodal Reasoning: Perception, Reasoning, or their Integration?
• Machine-interpretable Engineering Design Standards for Valve Specification
• Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
• Comparison of Unsupervised Metrics for Evaluating Judicial Decision Extraction
• Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
• Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors
• SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
• Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
• REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
• Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
• Inverse Language Modeling towards Robust and Grounded LLMs
• Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning
• Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations
• Exploring Database Normalization Effects on SQL Generation
• LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
• TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
• Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing
• HiSpec: Hierarchical Speculative Decoding for LLMs
• TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
• A-VERT: Agnostic Verification with Embedding Ranking Targets
• One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning
• ReSSFormer: A Recursive Sparse Structured Transformer for Scalable and Long-Context Reasoning
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
• A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
• RAG-BioQA Retrieval-Augmented Generation for Long-Form Biomedical Question Answering
• Efficient Training of Robust Traditional Chinese LLaMA-1B on a Single Consumer GPU: Continual Pre-training, SFT, and DPO
• AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System
• NLP Methods for Detecting Novel LLM Jailbreaks and Keyword Analysis with BERT
• Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention
• SoK: Measuring What Matters for Closed-Loop Security Agents
• MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
• FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol
• A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering
• Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports
• SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
• LOCA: Logical Chain Augmentation for Scientific Corpus Cleaning
• GemDetox at TextDetox CLEF 2025: Enhancing a Massively Multilingual Model for Text Detoxification on Low-resource Languages
• Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data
• GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models
• Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs
• Longitudinal Monitoring of LLM Content Moderation of Social Issues
• RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
• Measuring Algorithmic Partisanship via Zero-Shot Classification and Its Implications on Political Discourse
• In AI Sweet Harmony: Sociopragmatic Guardrail Bypasses and Evaluation-Awareness in OpenAI gpt-oss-20b
• OpenAI's GPT-OSS-20B Model and Safety Alignment Issues in a Low-Resource Language
• AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
• Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection
• TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
• LLM Based Sentiment Classification From Bangladesh E-Commerce Reviews
• EEFSUVA: A New Mathematical Olympiad Benchmark
• Who is In Charge? Dissecting Role Conflicts in Instruction Following
• Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based Supervision
• Geometric Structures and Patterns of Meaning: A PHATE Manifold Analysis of Chinese Character Embeddings
• Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models
• Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
• Computational Social Linguistics for Telugu Cultural Preservation: Novel Algorithms for Chandassu Metrical Pattern Recognition
• LLMRank: Understanding LLM Strengths for Model Routing
• GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings
• Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation
• Silent Tokens, Loud Effects: Padding in LLMs
• CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM
• SKYLENAGE Technical Report: Mathematical Reasoning and Contest-Innovation Benchmarks for Multi-Level Math Evaluation
• Redundancy-as-Masking: Formalizing the Artificial Age Score (AAS) to Model Memory Aging in Generative AI
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
• Feasibility of Structuring Stress Documentation Using an Ontology-Guided Large Language Model
• SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction
• Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset
• Towards Open-Ended Discovery for Low-Resource NLP
• Discourse vs emissions: Analysis of corporate narratives, symbolic practices, and mimicry through LLMs
• Context Matters: Comparison of commercial large language tools in veterinary medicine
• ClaimCheck: Real-Time Fact-Checking with Small Language Models