AI Research News Feeds for September 5th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• We Have It Covered: A Resampling-based Method for Uplift Model Comparison
• Estimation of High-Dimensional Markov-Switching VAR Models with an Approximate EM Algorithm
• Bootstrapping the Cross-Validation Estimate
• FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
• Improved sampling algorithms and Poincar\'e inequalities for non-log-concave distributions
• Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification
• POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation
• Completing Spatial Transcriptomics Data for Gene Expression Prediction Benchmarking
• Res-MoCoDiff: Residual-guided diffusion models for motion artifact correction in brain MRI
• Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directions
• From Embeddings to Accuracy: Comparing Foundation Models for Radiographic Classification
• Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
• Vision-Based Autonomous MM-Wave Reflector Using ArUco-Driven Angle-of-Arrival Estimation
• Towards Controllable Real Image Denoising with Camera Parameters
• Ecological Legacies of Pre-Columbian Settlements Evident in Palm Clusters of Neotropical Mountain Forests
• Spatial-aware Transformer-GRU Framework for Enhanced Glaucoma Diagnosis from 3D OCT Imaging
• A Framework for Supervised and Unsupervised Segmentation and Classification of Materials Microstructure Images
• Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
• Simulation-based Inference via Langevin Dynamics with Score Matching
• Prob-GParareal: A Probabilistic Numerical Parallel-in-Time Solver for Differential Equations
• Towards understanding Accelerated Stein Variational Gradient Flow -- Analysis of Generalized Bilinear Kernels for Gaussian target distributions
• Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes
• AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search
• Aesthetic Image Captioning with Saliency Enhanced MLLMs
• Learning neural representations for X-ray ptychography reconstruction with unknown probes
• Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
• Durian: Dual Reference-guided Portrait Animation with Attribute Transfer
• From Lines to Shapes: Geometric-Constrained Segmentation of X-Ray Collimators via Hough Transform
• One Flight Over the Gap: A Survey from Perspective to Panoramic Vision
• Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
• TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
• Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields
• ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
• SMooGPT: Stylized Motion Generation using Large Language Models
• Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
• OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection
• Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking
• Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
• Replication Study and Benchmarking of Real-Time Object Detection Models
• BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
• SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid Registration
• FADE: A Dataset for Detecting Falling Objects around Buildings in Video
• Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance
• OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs
• Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision
• ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
• Fast rigid alignment of heterogeneous images in sliced Wasserstein distance
• Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
• A Generative Foundation Model for Chest Radiography
• LMVC: An End-to-End Learned Multiview Video Coding Framework
• TopoSculpt: Betti-Steered Topological Sculpting of 3D Fine-grained Tubular Shapes
• ANTS: Shaping the Adaptive Negative Textual Space by MLLM for OOD Detection
• Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training
• SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation
• Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
• Millisecond-Response Tracking and Gazing System for UAVs: A Domestic Solution Based on "Phytium + Cambricon"
• A Re-ranking Method using K-nearest Weighted Fusion for Person Re-identification
• TEn-CATS: Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
• TriLiteNet: Lightweight Model for Multi-Task Visual Perception
• DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
• TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
• Revisiting Simple Baselines for In-The-Wild Deepfake Detection
• Differential Morphological Profile Neural Networks for Semantic Segmentation
• TauGenNet: Plasma-Driven Tau PET Image Synthesis via Text-Guided 3D Diffusion Models
• Dual-Scale Volume Priors with Wasserstein-Based Consistency for Semi-Supervised Medical Image Segmentation
• PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
• Noisy Label Refinement with Semantically Reliable Synthetic Images
• Efficient Odd-One-Out Anomaly Detection
• GeoArena: An Open Platform for Benchmarking Large Vision-language Models on WorldWide Image Geolocalization
• MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
• Stitching the Story: Creating Panoramic Incident Summaries from Body-Worn Footage
• DAPFAM: A Domain-Aware Family-level Dataset to benchmark cross domain patent retrieval
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling
• Teacher-Student Model for Detecting and Classifying Mitosis in the MIDOG 2025 Challenge
• Multi Attribute Bias Mitigation via Representation Learning
• Lightweight image segmentation for echocardiography
• Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding
• QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception
• Transfer Learning-Based CNN Models for Plant Species Identification Using Leaf Venation Patterns
• LayoutGKN: Graph Similarity Learning of Floor Plans
• SLENet: A Guidance-Enhanced Network for Underwater Camouflaged Object Detection
• Fitting Image Diffusion Models on Video Datasets
• MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting
• Causality-guided Prompt Learning for Vision-language Models via Visual Granulation
• EGTM: Event-guided Efficient Turbulence Mitigation
• Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
• OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction
• Weakly-Supervised Learning of Dense Functional Correspondences
• Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
• Can Language Models Handle a Non-Gregorian Calendar?
• Singular Value Few-shot Adaptation of Vision-Language Models
• Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
• SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
• LibriQuote: A Speech Dataset of Fictional Character Utterances for Expressive Zero-Shot Speech Synthesis
• Contextualized Token Discrimination for Speech Search Query Correction
• Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
• The Telephone Game: Evaluating Semantic Drift in Unified Models
• MyProfessors: Mining Turkish Student Reviews
• Mitigating Bias in Text Classification via Prompt-Based Text Transformation
• Exploring Linguistic Features for Turkish Text Readability
• R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models
• DynaSaur: Large Language Agents Beyond Predefined Actions
• Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts
• HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agents
• HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection
• Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
• Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
• Explicit Learning and the LLM in Machine Translation
• EQ-Knight: A Memory-Augmented LLM Agent for Strategic Affective Gaming in Debt Recovery
• Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
• MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions
• NoteBar: An AI-Assisted Note-Taking System for Personal Knowledge Management
• Semantic Analysis of SNOMED CT Concept Co-occurrences in Clinical Documentation using MIMIC-IV
• NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
• Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth
• False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
• MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation
• Exploring NLP Benchmarks in an Extremely Low-Resource Setting
• A RoBERTa-Based Functional Syntax Annotation Model for Chinese Texts
• Synthesizing Sheet Music Problems for Evaluation and Reinforcement Learning
• Improving Narrative Classification and Explanation via Fine Tuned Language Models
• Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
• MultiWikiQA: A Reading Comprehension Benchmark in 300+ Languages
• Joint Modeling of Entities and Discourse Relations for Coherence Assessment
• Explicit and Implicit Data Augmentation for Social Event Detection
• Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
• Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models
• The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation
• A theoretical basis for model collapse in recursive training
• Machine Intelligence on Wireless Edge Networks
• Asymptotic convexity of wide and shallow neural networks
• Enhancing Speech Large Language Models through Reinforced Behavior Alignment
• Reading Between the Signs: Predicting Future Suicidal Ideation from Adolescent Social Media Texts
• ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
• Understanding sparse autoencoder scaling in the presence of feature manifolds
• Straighter Flow Matching via a Diffusion-Based Coupling Prior
• Vision-based Manipulation from Single Human Video with Open-World Object Graphs
• Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
• ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
• dsld: A Socially Relevant Tool for Teaching Statistics
• Hardware-Friendly Diffusion Models with Fixed-Size Reusable Structures for On-Device Image Generation
• Exposing Synthetic Speech: Model Attribution and Detection of AI-generated Speech via Audio Fingerprints
• An Unsupervised Natural Language Processing Pipeline for Assessing Referral Appropriateness
• Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study
• T-cell receptor specificity landscape revealed through de novo peptide design
• FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article
• Short-video Propagation Influence Rating: A New Real-world Dataset and A New Large Graph Model
• Deliberate Planning of 3D Bin Packing on Packing Configuration Trees
• Closed-Loop Neural Operator-Based Observer of Traffic Density
• Revealing the empirical flexibility of gas units through deep clustering
• A dynamic view of some anomalous phenomena in SGD
• Enhancing Text2Cypher with Schema Filtering
• Text2Cypher: Data Pruning using Hard Example Selection
• DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
• Batched Stochastic Matching Bandits
• COBRA: Multimodal Sensing Deep Learning Framework for Remote Chronic Obesity Management via Wrist-Worn Activity Monitoring
• Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
• Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology
• SAFE--MA--RRT: Multi-Agent Motion Planning with Data-Driven Safety Certificates
• Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image -- Technical Preview
• Reservoir kernels and Volterra series
• Towards Robust Graph Structural Learning Beyond Homophily via Preserving Neighbor Similarity
• Moco: A Learnable Meta Optimizer for Combinatorial Optimization
• Explaining Length Bias in LLM-Based Preference Evaluations
• Uncertainty-Guided Likelihood Tree Search
• Retrieval-Augmented Generation with Estimation of Source Reliability
• Zero-shot Generalization in Inventory Management: Train, then Estimate and Decide
• MARS: Unleashing the Power of Variance Reduction for Training Large Models
• Multi-Label Bayesian Active Learning with Inter-Label Relationships
• Dataset Distillation as Pushforward Optimal Quantization
• IC-Cache: Efficient Large Language Model Serving via In-context Caching
• Probabilistic QoS Metric Forecasting in Delay-Tolerant Networks Using Conditional Diffusion Models on Latent Dynamics
• Technology prediction of a 3D model using Neural Network
• Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer
• Federated Isolation Forest for Efficient Anomaly Detection on Edge IoT Systems
• Plugging Attention into Power Grids: Towards Transparent Forecasting
• Recursive Reward Aggregation
• Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneck
• An exact multiple-time-step variational formulation for the committor and the transition rate
• Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
• Predicting Antimicrobial Resistance (AMR) in Campylobacter, a Foodborne Pathogen, and Cost Burden Analysis Using Machine Learning
• Exoplanetary atmospheres retrieval via a quantum extreme learning machine
• Accurate and scalable deep Maxwell solvers using multilevel iterative methods
• ACT: Automated Constraint Targeting for Multi-Objective Recommender Systems
• Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
• Hypothesis Selection: A High Probability Conundrum
• LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest
• Deficiency of equation-finding approach to data-driven modeling of dynamical systems
• Testing for correlation between network structure and high-dimensional node covariates
• Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves
• Reservoir Predictive Path Integral Control for Unknown Nonlinear Dynamics
• Hardware-Aware Data and Instruction Mapping for AI Tasks: Balancing Parallelism, I/O and Memory Tradeoffs
• Sample Efficient Certification of Discrete-Time Control Barrier Functions
• An invertible generative model for forward and inverse problems
• Decoding the Poetic Language of Emotion in Korean Modern Poetry: Insights from a Human-Labeled Dataset and AI Modeling
• LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding
• Divergence-Kernel method for linear responses and diffusion models
• What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
• TensoIS: A Step Towards Feed-Forward Tensorial Inverse Subsurface Scattering for Perlin Distributed Heterogeneous Media
• Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
• Gromov-Wasserstein and optimal transport: from assignment problems to probabilistic numeric
• Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees
• Unobtrusive In-Situ Measurement of Behavior Change by Deep Metric Similarity Learning of Motion Patterns
• KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis
• Formal Verification of Local Robustness of a Classification Algorithm for a Spatial Use Case
• On Aligning Prediction Models with Clinical Experiential Learning: A Prostate Cancer Case Study
• FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
• Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference
• Who Pays for Fairness? Rethinking Recourse under Social Burden
• Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference
• Comment on "A Note on Over-Smoothing for Graph Neural Networks"
• Set Block Decoding is a Language Model Inference Accelerator
• One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
• Why Can't I See My Clusters? A Precision-Recall Approach to Dimensionality Reduction Validation
• Rethinking the long-range dependency in Mamba/SSM and transformer models
• Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
• Synthetic Survival Data Generation for Heart Failure Prognosis Using Deep Generative Models
• RL's Razor: Why Online Reinforcement Learning Forgets Less
• An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy
• A Primer on Causal and Statistical Dataset Biases for Fair and Robust Image Analysis
• Using causal abstractions to accelerate decision-making in complex bandit problems
• Characteristic Energy Behavior Profiling of Non-Residential Buildings
• When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
• PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
• Transition Models: Rethinking the Generative Learning Objective
• Interpretable Clustering with Adaptive Heterogeneous Causal Structure Learning in Mixed Observational Data
• Echo State Networks as State-Space Models: A Systems Perspective
• Unveiling the Role of Data Uncertainty in Tabular Deep Learning
• Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
• A Small Dataset May Go a Long Way: Process Duration Prediction in Clinical Settings
• The ProLiFIC dataset: Leveraging LLMs to Unveil the Italian Lawmaking Process
• First Order Model-Based RL through Decoupled Backpropagation
• AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generation
• EZhouNet:A framework based on graph neural network and anchor interval for the respiratory sound event detection
• AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation
• Nonnegative matrix factorization and the principle of the common cause
• Semi-decentralized Federated Time Series Prediction with Client Availability Budgets
• AutoGrid AI: Deep Reinforcement Learning Framework for Autonomous Microgrid Management
• SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
• A Machine Learning-Based Study on the Synergistic Optimization of Supply Chain Management and Financial Supply Chains from an Economic Perspective
• A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games
• Graph Random Features for Scalable Gaussian Processes
• EmbedOR: Provable Cluster-Preserving Visualizations with Curvature-Based Stochastic Neighbor Embeddings
• Online Learning of Optimal Sequential Testing Policies
• Mapping on a Budget: Optimizing Spatial Data Collection for ML
• Learning functions through Diffusion Maps
• Online time series prediction using feature adjustment
• Machine Learning for LiDAR-Based Indoor Surface Classification in Intelligent Wireless Environments
• Predicting Traffic Accident Severity with Deep Neural Networks
• Vehicle-to-Infrastructure Collaborative Spatial Perception via Multimodal Large Language Models
• Data-Augmented Quantization-Aware Knowledge Distillation
• Topotein: Topological Deep Learning for Protein Representation Learning
• Mistake-bounded online learning with operation caps
• Breaking the Context Bottleneck on Long Time Series Forecasting
• A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
• Is an Ultra Large Natural Image-Based Foundation Model Superior to a Retina-Specific Model for Detecting Ocular and Systemic Diseases?
• Image Embedding Sampling Method for Diverse Captioning
• CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection
• FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response
• KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
• Beyond holography: the entropic quantum gravity foundations of image processing
• Robust Offline Imitation Learning Through State-level Trajectory Stitching
• RBT4DNN: Requirements-based Testing of Neural Networks
• Transferable Mask Transformer: Cross-domain Semantic Segmentation with Region-adaptive Transferability Estimation
• Optimization of Module Transferability in Single Image Super-Resolution: Universality Assessment and Cycle Residual Blocks
• Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling
• MiniCPM4: Ultra-Efficient LLMs on End Devices
• Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation
• Stochastic Parameter Decomposition
• An Analysis of Action-Value Temporal-Difference Methods That Learn State Values
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
• Conditional Video Generation for High-Efficiency Video Compression
• (Ir)rationality in AI: State of the Art, Research Challenges and Open Questions
• PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
• Transferable Belief Model on Quantum Circuits
• WASP: A Weight-Space Approach to Detecting Learned Spuriousness
• Enhancing FKG.in: automating Indian food composition analysis
• Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers
• Computational Basis of LLM's Decision Making in Social Simulation
• DMN-Guided Prompting: A Framework for Controlling LLM Behavior
• Axiomatics of Restricted Choices by Linear Orders of Sets with Minimum as Fallback
• CP-Bench: Evaluating Large Language Models for Constraint Modelling
• Autonomation, Not Automation: Activities and Needs of European Fact-checkers as a Basis for Designing Human-Centered AI Systems
• Style Transfer to Calvin and Hobbes comics using Stable Diffusion
• Diffusion on language model encodings for protein sequence generation
• MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming
• Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
• Long Input Sequence Network for Long Time Series Forecasting
• AutoPETIII: The Tracer Frontier. What Frontier?
• Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
• Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss
• Quantifying Calibration Error in Neural Networks Through Evidence-Based Theory
• Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
• ACING: Actor-Critic for Instruction Learning in Black-Box LLMs
• Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
• EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding
• MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation
• Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Synthesis
• Enhancing Technical Documents Retrieval for RAG
• TAGAL: Tabular Data Generation using Agentic LLM Methods
• Attention as an Adaptive Filter
• YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components
• Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds
• VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision
• MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions
• Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding
• How many patients could we save with LLM priors?
• An Empirical Study of Vulnerabilities in Python Packages and Their Detection
• Reinforcement Learning for Robust Ageing-Aware Control of Li-ion Battery Systems with Data-Driven Formal Verification
• HumAIne-Chatbot: Real-Time Personalized Conversational AI via Reinforcement Learning
• Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models
• Decoupled Entity Representation Learning for Pinterest Ads Ranking
• From Editor to Dense Geometry Estimator
• AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
• PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
• Parking Availability Prediction via Fusing Multi-Source Data with A Self-Supervised Learning Enhanced Spatio-Temporal Inverted Transformer
• SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer
• IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation
• No Thoughts Just AI: Biased LLM Recommendations Limit Human Agency in Resume Screening
• Towards a Unified View of Large Language Model Post-Training
• DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation
• Delta Activations: A Representation for Finetuned Large Language Models
• ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset
• Intelligence Primer
• Gravity Well Echo Chamber Modeling With An LLM-Based Confirmation Bias Model
• From Leiden to Pleasure Island: The Constant Potts Model for Community Detection as a Hedonic Game
• INGRID: Intelligent Generative Robotic Design Using Large Language Models
• Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables
• MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting
• A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
• SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition
• Peptidomic-Based Prediction Model for Coronary Heart Disease Using a Multilayer Perceptron Neural Network
• Reactive In-Air Clothing Manipulation with Confidence-Aware Dense Correspondence and Visuotactile Affordance
• Diffusion Generative Models Meet Compressed Sensing, with Applications to Image Data and Financial Time Series
• MTQA:Matrix of Thought for Enhanced Reasoning in Complex Question Answering
• SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
• SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
• VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents
• Chest X-ray Pneumothorax Segmentation Using EfficientNet-B4 Transfer Learning in a U-Net Architecture
• CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking
• Multimodal Feature Fusion Network with Text Difference Enhancement for Remote Sensing Change Detection
• Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
• SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification
• NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
• Promptception: How Sensitive Are Large Multimodal Models to Prompts?
• RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
• Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
• NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
• On Robustness and Reliability of Benchmark-Based Evaluation of LLMs
• Neural Video Compression with In-Loop Contextual Filtering and Out-of-Loop Reconstruction Enhancement
• Keypoint-based Diffusion for Robotic Motion Planning on the NICOL Robot
• RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models
• QuesGenie: Intelligent Multimodal Question Generation
• AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
• Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
• A software security review on Uganda's Mobile Money Services: Dr. Jim Spire's tweets sentiment analysis
• The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
• E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition
• treeX: Unsupervised Tree Instance Segmentation in Dense Forest Point Clouds
• CEHR-GPT: A Scalable Multi-Task Foundation Model for Electronic Health Records
• Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
• Efficient Virtuoso: A Latent Diffusion Transformer Model for Goal-Conditioned Trajectory Planning
• Insights from Gradient Dynamics: Gradient Autoscaled Normalization
• LuxDiT: Lighting Estimation with Video Diffusion Transformer
• Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures
• From Federated Learning to $\mathbb{X}$-Learning: Breaking the Barriers of Decentrality Through Random Walks
• MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
• Differentiable Entropy Regularization for Geometry and Neural Networks
• Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces
• Designing Gaze Analytics for ELA Instruction: A User-Centered Dashboard with Conversational AI Support
• STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
• ARDO: A Weak Formulation Deep Neural Network Method for Elliptic and Parabolic PDEs Based on Random Differences of Test Functions
• Learning an Adversarial World Model for Automated Curriculum Generation in MARL
• Natural Latents: Latent Variables Stable Across Ontologies
• What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
• SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation
• SAMVAD: A Multi-Agent System for Simulating Judicial Deliberation Dynamics in India
• Measuring How (Not Just Whether) VLMs Build Common Ground
• Align-then-Slide: A complete evaluation framework for Ultra-Long Document-Level Machine Translation
• Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model
• Multimodal Proposal for an AI-Based Tool to Increase Cross-Assessment of Messages
• Real-Time Detection of Hallucinated Entities in Long-Form Generation
• A Multidimensional AI-powered Framework for Analyzing Tourist Perception in Historic Urban Quarters: A Case Study in Shanghai
• Continuous Monitoring of Large-Scale Generative AI via Deterministic Knowledge Graph Structures
• Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata
• FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace
• A Foundation Model for Chest X-ray Interpretation with Grounded Reasoning via Online Reinforcement Learning
• Handling Infinite Domain Parameters in Planning Through Best-First Search with Delayed Partial Expansions
• World Model Implanting for Test-time Adaptation of Embodied Agents
• Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
• AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
• CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
• Oruga: An Avatar of Representational Systems Theory
• Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
• Hybrid Reinforcement Learning and Search for Flight Trajectory Planning
• Analysis of Bluffing by DQN and CFR in Leduc Hold'em Poker
• The human biological advantage over AI
• Towards an Action-Centric Ontology for Cooking Procedures Using Temporal Graphs
• Domain size asymptotics for Markov logic networks
• Evaluating Quality of Gaming Narratives Co-created with AI
• EvoEmo: Towards Evolved Emotional Policies for LLM Agents in Multi-Turn Negotiation
• Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
• Psychologically Enhanced AI Agents
• ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
• BiND: A Neural Discriminator-Decoder for Accurate Bimanual Trajectory Prediction in Brain-Computer Interfaces
• Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
• PG-Agent: An Agent Powered by Page Graph
• Multilinear and Linear Programs for Partially Identifiable Queries in Quasi-Markovian Structural Causal Models
• Diffusion-RL Based Air Traffic Conflict Detection and Resolution Method
• Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
• Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE
• CausalARC: Abstract Reasoning with Causal World Models
• Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
• An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification
• PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
• The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
• Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
• RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
• Leveraging LLM-Based Agents for Intelligent Supply Chain Planning
• Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
• What Would an LLM Do? Evaluating Policymaking Capabilities of Large Language Models
• An Agentic Model Context Protocol Framework for Medical Concept Standardization