AI Research News Feeds for December 16th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• AgentIAD: Tool-Augmented Single-Agent for Industrial Anomaly Detection
• JoVA: Unified Multimodal Learning for Joint Video-Audio Generation
• LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
• I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners
• Recurrent Video Masked Autoencoders
• Towards Scalable Pre-training of Visual Tokenizers for Generation
• LitePT: Lighter Yet Stronger Point Transformer
• Benchmarking Tesla's Traffic Light and Stop Sign Control: Field Dataset and Behavior Insights
• A Reproducible Workflow for Scraping, Structuring, and Segmenting Legacy Archaeological Artifact Images
• ReGlove: A Soft Pneumatic Glove for Activities of Daily Living Assistance via Wrist-Mounted Vision
• Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics
• Pre-training vision models for the classification of alerts from wide-field time-domain surveys
• AutoMV: An Automatic Multi-Agent System for Music Video Generation
• Navigation Around Unknown Space Objects Using Visible-Thermal Image Fusion
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT
• JPEG-Inspired Cloud-Edge Holography
• Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering
• JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation
• SLIM-VDB: A Real-Time 3D Probabilistic Semantic Mapping Framework
• Leveraging Compression to Construct Transferable Bitrate Ladders
• Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving
• Self-Supervised Ultrasound Representation Learning for Renal Anomaly Prediction in Prenatal Imaging
• RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics
• We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature
• ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
• An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration
• TimeWalker: Personalized Neural Space for Lifelong Head Avatars
• Deep priors for satellite image restoration with accurate uncertainties
• GeoTexDensifier: Geometry-Texture-Aware Densification for High-Quality Photorealistic 3D Gaussian Splatting
• Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection and Simulation
• VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
• Counting Hallucinations in Diffusion Models
• Tau Anomaly Detection in PET Imaging via Bilateral-Guided Deterministic Diffusion Model
• From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields
• More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models
• Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention
• Anatomy Guided Coronary Artery Segmentation from CCTA Using Spatial Frequency Joint Modeling
• From Tokens to Photons: Test-Time Physical Prompting for Vison-Language Models
• StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
• Automatic Wire-Harness Color Sequence Detector
• Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation
• Geometry-Aware Scene-Consistent Image Generation
• No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching
• Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
• D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation
• Cross-modal Fundus Image Registration under Large FoV Disparity
• CogDoc: Towards Unified thinking in Documents
• InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation
• Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning
• Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation
• $\beta$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
• Spinal Line Detection for Posture Evaluation through Train-ing-free 3D Human Body Reconstruction with 2D Depth Images
• GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
• FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning
• Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior
• L-STEC: Learned Video Compression with Long-term Spatio-Temporal Enhanced Context
• DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
• Learning Common and Salient Generative Factors Between Two Image Datasets
• Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal
• Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection
• Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification
• Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection
• Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery
• UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction
• SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer
• VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
• Scaling Up AI-Generated Image Detection via Generator-Aware Prototypes
• Few-Step Distillation for Text-to-Image Generation: A Practical Guide
• Light Field Based 6DoF Tracking of Previously Unobserved Objects
• TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading
• JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion
• What Happens Next? Next Scene Prediction with a Unified Video Model
• SneakPeek: Future-Guided Instructional Streaming Video Generation
• Comprehensive Evaluation of Rule-Based, Machine Learning, and Deep Learning in Human Estimation Using Radio Wave Sensing: Accuracy, Spatial Generalization, and Output Granularity Trade-offs
• Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
• Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing
• Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
• FID-Net: A Feature-Enhanced Deep Learning Network for Forest Infestation Detection
• LeafTrackNet: A Deep Learning Framework for Robust Leaf Tracking in Top-Down Plant Phenotyping
• StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completion
• Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation
• MMDrive: Interactive Scene Understanding Beyond Vision with Multi-representational Fusion
• CoRA: A Collaborative Robust Architecture with Hybrid Fusion for Efficient Perception
• POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modeling
• Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance
• STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
• Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection
• CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing
• Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?
• CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Images
• ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
• KlingAvatar 2.0 Technical Report
• Automated User Identification from Facial Thermograms with Siamese Networks
• Unlocking Generalization in Polyp Segmentation with DINO Self-Attention "keys"
• Beyond the Visible: Disocclusion-Aware Editing via Proxy Dynamic Graphs
• Computer vision training dataset generation for robotic environments using Gaussian splatting
• USTM: Unified Spatial and Temporal Modeling for Continuous Sign Language Recognition
• Learning to Generate Cross-Task Unexploitable Examples
• RecTok: Reconstruction Distillation along Rectified Flow
• A Domain-Adapted Lightweight Ensemble for Resource-Efficient Few-Shot Plant Disease Classification
• IMILIA: interpretable multiple instance learning for inflammation prediction in IBD from H&E whole slide images
• Test-Time Modification: Inverse Domain Transformation for Robust Perception
• PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence
• Transform Trained Transformer: Accelerating Naive 4K Video Generation Over 10$\times$
• Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation
• Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
• TARA: Simple and Efficient Time Aware Retrieval Adaptation of MLLMs for Video Understanding
• 3D Human-Human Interaction Anomaly Detection
• MMhops-R1: Multimodal Multi-hop Reasoning
• Lighting in Motion: Spatiotemporal HDR Lighting Estimation
• LongVie 2: Multimodal Controllable Ultra-Long Video World Model
• DBT-DINO: Towards Foundation model based analysis of Digital Breast Tomosynthesis
• SCR2-ST: Combine Single Cell with Spatial Transcriptomics for Efficient Active Sampling via Reinforcement Learning
• MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
• Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
• Grab-3D: Detecting AI-Generated Videos from 3D Geometric Temporal Consistency
• PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation
• Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
• A stylometric analysis of speaker attribution from speech transcripts
• Towards Effective Model Editing for LLM Personalization
• Beyond surface form: A pipeline for semantic analysis in Alzheimer's Disease detection from spontaneous speech
• VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
• From Human Intention to Action Prediction: A Comprehensive Benchmark for Intention-driven End-to-End Autonomous Driving
• VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
• The Morphemic Origin of Zipf's Law: A Factorized Combinatorial Framework
• Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings
• Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
• ERA-IT: Aligning Semantic Models with Revealed Economic Preference for Real-Time and Explainable Patent Valuation
• Heart Disease Prediction using Case Based Reasoning (CBR)
• SIGMA: An AI-Empowered Training Stack on Early-Life Hardware
• Fine-tuned LLM-based Code Migration Framework
• Towards Interactive Intelligence for Digital Humans
• DABL: Detecting Semantic Anomalies in Business Processes Using Large Language Models
• Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
• DeBERTa-KC: A Transformer-Based Classifier for Knowledge Construction in Online Learning Discourse
• Temporal-Anchor3DLane: Enhanced 3D Lane Detection with Multi-Task Losses and LSTM Fusion
• Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training
• Generalization vs. Specialization: Evaluating Segment Anything Model (SAM3) Zero-Shot Segmentation Against Fine-Tuned YOLO Detectors
• Hot H\'em: S\`ai G\`on Gi\~ua C\'ai N\'ong H\^ong C\`ong B\`ang -- Saigon in Unequal Heat
• Microscopic Vehicle Trajectory Datasets from UAV-collected Video for Heterogeneous, Area-Based Urban Traffic
• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
• Smartphone monitoring of smiling as a behavioral proxy of well-being in everyday life
• TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder
• Contextual Peano Scan and Fast Image Segmentation Using Hidden and Evidential Markov Chains
• A Comparative Analysis of Semiconductor Wafer Map Defect Detection with Image Transformer
• CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
• Adaptive federated learning for ship detection across diverse satellite imagery sources
• Enhancing deep learning performance on burned area delineation from SPOT-6/7 imagery for emergency management
• RePack: Representation Packing of Vision Foundation Model Features Enhances Diffusion Transformer
• EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography
• Open Horizons: Evaluating Deep Models in the Wild
• Audio-Visual Camera Pose Estimationn with Passive Scene Sounds and In-the-Wild Video
• SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation
• A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Spatio-Temporal Drift Detection
• A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction
• CineLOG: A Training Free Approach for Cinematic Long Video Generation
• Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
• ProImage-Bench: Rubric-Based Evaluation for Professional Image Generation
• Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
• Moment and Highlight Detection via MLLM Frame Segmentation
• MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
• Feature Aggregation for Efficient Continual Learning of Complex Facial Expressions
• Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection
• RealDrag: The First Dragging Benchmark with Real Target Image
• OMUDA: Omni-level Masking for Unsupervised Domain Adaptation in Semantic Segmentation
• MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding
• WeDetect: Fast Open-Vocabulary Object Detection as Retrieval
• TCLeaf-Net: a transformer-convolution framework with global-local attention for robust in-field lesion-level plant leaf disease detection
• STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
• V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping
• M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
• Speedrunning ImageNet Diffusion
• ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States
• BokehDepth: Enhancing Monocular Depth Estimation through Bokeh Generation
• Endless World: Real-Time 3D-Aware Long Video Generation
• Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training
• Comparative Analysis of Wave Scattering Numerical Modeling Using the Boundary Element Method and Physics-Informed Neural Networks
• CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
• The prediction of the quality of results in Logic Synthesis using Transformer and Graph Neural Networks
• An Anytime Algorithm for Good Arm Identification
• "All of Me": Mining Users' Attributes from their Public Spotify Playlists
• CIC: Circular Image Compression
• Deep-ER: Deep Learning ECCENTRIC Reconstruction for fast high-resolution neurometabolic imaging
• WALINET: A water and lipid identification convolutional Neural Network for nuisance signal removal in 1H MR Spectroscopic Imaging
• On the physics of nested Markov models: a generalized probabilistic theory perspective
• QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain
• Self-test loss functions for learning weak-form operators and gradient flows
• Navigating AI to Unpack Youth Privacy Concerns: An In-Depth Exploration and Systematic Review
• A Physics-Embedded Dual-Learning Imaging Framework for Electrical Impedance Tomography
• Compact Neural Network Algorithm for Electrocardiogram Classification
• Multipole Attention for Efficient Long Context Reasoning
• A PyTorch Framework for Scalable Non-Crossing Quantile Regression
• AQCat25: Unlocking spin-aware, high-fidelity machine learning potentials for heterogeneous catalysis
• Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
• Benchmarking Contextual Understanding for In-Car Conversational Systems
• BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
• Market-Bench: Evaluating Large Language Models on Introductory Quantitative Trading and Market Dynamics
• F5-TTS-RO: Extending F5-TTS to Romanian TTS via Lightweight Input Adaptation
• Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors
• Large language models have learned to use language
• The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting
• NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data
• StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning
• Which Pieces Does Unigram Tokenization Really Need?
• LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases
• CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
• Curi\'o-Edu 7B: Examining Data Selection Impacts in LLM Continued Pretraining
• Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions
• What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story Evaluation
• QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
• Authors Should Annotate
• An Open and Reproducible Deep Research Agent for Long-Form Question Answering
• AIR: Post-training Data Selection for Reasoning via Attention Head Influence
• Integrating Causal Reasoning into Automated Fact-Checking
• Large language models are not about language
• Scaling Laws for Code: Every Programming Language Matters
• Advancing Bangla Machine Translation Through Informal Datasets
• CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videos
• VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
• BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models
• SPDMark: Selective Parameter Displacement for Robust Video Watermarking
• AI-Augmented Pollen Recognition in Optical and Holographic Microscopy for Veterinary Imaging
• A Novel Patch-Based TDA Approach for Computed Tomography
• Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context
• Modeling Dabrafenib Response Using Multi-Omics Modality Fusion and Protein Network Embeddings Based on Graph Convolutional Networks
• Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
• Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking
• Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy
• Hellinger loss function for Generative Adversarial Networks
• Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecture
• Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates
• GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
• Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall
• Unified Control for Inference-Time Guidance of Denoising Diffusion Models
• Towards a pretrained deep learning estimator of the Linfoot informational correlation
• ElasticVR: Elastic Task Computing in Multi-User Multi-Connectivity Wireless Virtual Reality (VR) Systems
• ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics
• Data-driven modelling of autonomous and forced dynamical systems
• Co-Hub Node Based Multiview Graph Learning with Theoretical Guarantees
• Efficient Level-Crossing Probability Calculation for Gaussian Process Modeled Data
• Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
• Understanding Overparametrization in Survival Models through Double-Descent
• Generative Spatiotemporal Data Augmentation
• Animus3D: Text-driven 3D Animation via Motion Score Distillation
• HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
• Supervised Contrastive Frame Aggregation for Video Representation Learning
• Iterative Sampling Methods for Sinkhorn Distributionally Robust Optimization
• Mind the Jumps: A Scalable Robust Local Gaussian Process for Multidimensional Response Surfaces with Discontinuities
• Scalable Quantum Error Mitigation with Neighbor-Informed Learning
• ceLLMate: Sandboxing Browser AI Agents
• CoLSE: A Lightweight and Robust Hybrid Learned Model for Single-Table Cardinality Estimation using Joint CDF
• Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks
• Robust Variational Bayes by Min-Max Median Aggregation
• Efficient Vision-Language Reasoning via Adaptive Token Pruning
• Practical Hybrid Quantum Language Models with Observable Readout on Real Hardware
• Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity
• Limits To (Machine) Learning
• Transport Reversible Jump Markov Chain Monte Carlo with proposals generated by Variational Inference with Normalizing Flows
• Flow-matching Operators for Residual-Augmented Probabilistic Learning of Partial Differential Equations
• An End-to-End Approach for Microgrid Probabilistic Forecasting and Robust Operation via Decision-focused Learning
• HaShiFlex: A High-Throughput Hardened Shifter DNN Accelerator with Fine-Tuning Flexibility
• KANEL\'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation
• Qonvolution: Towards Learning High-Frequency Signals with Queried Convolution
• PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
• Evaluating Singular Value Thresholds for DNN Weight Matrices based on Random Matrix Theory
• Continuous Edit Distance, Geodesics and Barycenters of Time-varying Persistence Diagrams
• VoroLight: Learning Quality Volumetric Voronoi Meshes from General Inputs
• General OOD Detection via Model-aware and Subspace-aware Variable Priority
• Comprehensive Deployment-Oriented Assessment for Cross-Environment Generalization in Deep Learning-Based mmWave Radar Sensing
• Motus: A Unified Latent Action World Model
• Progressive Refinement of E-commerce Search Ranking Based on Short-Term Activities of the Buyer
• DiRe: Diversity-promoting Regularization for Dataset Condensation
• PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
• ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning
• Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
• Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
• Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models
• Iterative Tuning of Nonlinear Model Predictive Control for Robotic Manufacturing Tasks
• MicroPhaseNO: Adapting an Earthquake-Trained Phase Neural Operator for Microseismic Phase Picking
• Rethinking Physics-Informed Regression Beyond Training Loops and Bespoke Architectures
• Better LMO-based Momentum Methods with Second-Order Information
• AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
• Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles
• rNCA: Self-Repairing Segmentation Masks
• MineTheGap: Automatic Mining of Biases in Text-to-Image Models
• Real-Time AI-Driven Milling Digital Twin Towards Extreme Low-Latency
• From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis
• A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
• Enhancing lithological interpretation from petrophysical well log of IODP expedition 390/393 using machine learning
• Actively Learning Joint Contours of Multiple Computer Experiments
• Adaptive Sampling for Hydrodynamic Stability
• Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
• A Nonparametric Statistics Approach to Feature Selection in Deep Neural Networks with Theoretical Guarantees
• Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization
• Do-Undo: Generating and Reversing Physical Actions in Vision-Language Models
• Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models
• Universality of high-dimensional scaling limits of stochastic gradient descent
• SEDULity: A Proof-of-Learning Framework for Distributed and Secure Blockchains with Efficient Useful Work
• Adaptive Risk Mitigation in Demand Learning
• Vertical Semi-Federated Learning for Efficient Online Advertising
• Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation
• Dynamic Fraud Detection: Integrating Reinforcement Learning into Graph Neural Networks
• The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
• Defending Collaborative Filtering Recommenders via Adversarial Robustness Based Edge Reweighting
• Learning Dynamics in Memristor-Based Equilibrium Propagation
• Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction
• Optimized Architectures for Kolmogorov-Arnold Networks
• Sparse Concept Anchoring for Interpretable and Controllable Neural Representations
• GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction
• AI-Driven Early Warning Systems for Student Success: Discovering Static Feature Dominance in Temporal Prediction Models
• Policy Optimization for Dynamic Heart Transplant Allocation
• Empirical Mode Decomposition and Graph Transformation of the MSCI World Index: A Multiscale Topological Analysis for Graph Neural Network Modeling
• Effective Fine-Tuning with Eigenvector Centrality Based Pruning
• Optimal Mistake Bounds for Transductive Online Learning
• On the Accuracy of Newton Step and Influence Function Data Attributions
• Differentiable Energy-Based Regularization in GANs: A Simulator-Based Exploration of VQE-Inspired Auxiliary Losses
• Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics
• Causal inference and model explainability tools for retail
• Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain
• Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks
• On Approaches to Building Surrogate ODE Models for Diffusion Bridges
• Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
• Multi-Trajectory Physics-Informed Neural Networks for HJB Equations with Hard-Zero Terminal Inventory: Optimal Execution on Synthetic & SPY Data
• Solving a Machine Learning Regression Problem Based on the Theory of Random Functions
• SPARK: Igniting Communication-Efficient Decentralized Learning via Stage-wise Projected NTK and Accelerated Regularization
• Resting Neurons, Active Insights: Improving Input Sparsification for Large Language Models
• OLR-WAA: Adaptive and Drift-Resilient Online Regression with Dynamic Weighted Averaging
• Credit Risk Estimation with Non-Financial Features: Evidence from a Synthetic Istanbul Dataset
• TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
• Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift
• GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
• Improving Recursive Transformers with Mixture of LoRAs
• Unsupervised learning of multiscale switching dynamical system models from multimodal neural data
• Distillation of Discrete Diffusion by Exact Conditional Distribution Matching
• Wait, Wait, Wait... Why Do Reasoning Models Loop?
• Probability Estimation for Predicted-Occupancy Grids in Vehicle Safety Applications Based on Machine Learning
• Predicted-occupancy grids for vehicle safety applications based on autoencoders and the Random Forest algorithm
• Next-generation reservoir computing validated by classification task
• Machine Learning Architectures for the Estimation of Predicted Occupancy Grids in Road Traffic
• LLM-based Personalized Portfolio Recommender: Integrating Large Language Models and Reinforcement Learning for Intelligent Investment Strategy Optimization
• SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision
• Understanding When Graph Convolutional Networks Help: A Diagnostic Study on Label Scarcity and Structural Properties
• Application of Deep Learning in Biological Data Compression
• CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks
• Deep Learning-Driven Inversion Framework for Shear Modulus Estimation in Magnetic Resonance Elastography (DIME)
• Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization
• Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection
• Deep Q-Learning-Based Intelligent Scheduling for ETL Optimization in Heterogeneous Data Environments
• Multi-fidelity aerodynamic data fusion by autoencoder transfer learning
• LikeBench: Evaluating Subjective Likability in LLMs for Personalization
• Quanvolutional Neural Networks for Spectrum Peak-Finding
• Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency
• Noise-Resilient Quantum Aggregation on NISQ for Federated ADAS Learning
• Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting
• ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Data
• Learning to Retrieve with Weakened Labels: Robust Training under Label Noise
• B\'ezierFlow: B\'ezier Stochastic Interpolant Schedulers for Few-Step Generation
• KD-PINN: Knowledge-Distilled PINNs for ultra-low-latency real-time neural PDE solvers
• FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
• Link-Aware Energy-Frugal Continual Learning for Fault Detection in IoT Networks
• On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
• Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstruction
• Multiclass Graph-Based Large Margin Classifiers: Unified Approach for Support Vectors and Neural Networks
• XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
• DP-EMAR: A Differentially Private Framework for Autonomous Model Weight Repair in Federated IoT Systems
• Element-wise Modulation of Random Matrices for Efficient Neural Layers
• On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturing
• Learning under Distributional Drift: Reproducibility as an Intrinsic Statistical Resource
• Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
• Image Diffusion Preview with Consistency Solver
• Scalable Formal Verification via Autoencoder Latent Space Abstraction
• LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification
• StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion
• A Scientific Reasoning Model for Organic Synthesis Procedure Generation
• Directional Textual Inversion for Personalized Text-to-Image Generation
• Reinforcement Learning for Latent-Space Thinking in LLMs
• Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines
• Evolving Deep Learning Optimizers
• The Art of Storytelling in Authoritarian Regimes: Crafting State Narratives on Chinese Social Media
• mmWEAVER: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Description
• CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
• MPath: Multimodal Pathology Report Generation from Whole Slide Images
• Interval Fisher's Discriminant Analysis and Visualisation
• Policy Gradient Algorithms for Age-of-Information Cost Minimization
• Adversarial Attacks Against Deep Learning-Based Radio Frequency Fingerprint Identification
• Exploring Spatial-Temporal Representation via Star Graph for mmWave Radar-based Human Activity Recognition
• Human-computer interactions predict mental health
• On the Design of One-step Diffusion via Shortcutting Flow Paths
• Hybrid twinning using PBDW and DeepONet for the effective state estimation and prediction on partially known systems
• D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space
• Large Language Models as Generalist Policies for Network Optimization
• Amortized Causal Discovery with Prior-Fitted Networks
• Meta-Continual Mobility Forecasting for Proactive Handover Prediction
• Exploring Topological Bias in Heterogeneous Graph Neural Networks
• Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
• Phase transitions reveal hierarchical structure in deep neural networks
• Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors
• Learning to Extract Context for Context-Aware LLM Inference
• EnviroLLM: Resource Tracking and Optimization for Local AI
• DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
• Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
• Physics-informed neural networks to solve inverse problems in unbounded domains
• SigTime: Learning and Visually Explaining Time Series Signatures
• CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
• GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes
• Neural CDEs as Correctors for Learned Time Series Models
• High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees
• BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models
• On the Approximation Power of SiLU Networks: Exponential Rates and Depth Efficiency
• HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone
• MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching
• EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training
• Optimized Learned Count-Min Sketch
• Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model
• TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting
• Eventually LIL Regret: Almost Sure $\ln\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data
• Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
• Synthetic Swarm Mosquito Dataset for Acoustic Classification: A Proof of Concept
• The Data Efficiency Frontier of Financial Foundation Models: Scaling Laws from Continued Pretraining
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment
• DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
• Can Graphs Improve Tabular Foundation Models?
• UniVCD: A New Method for Unsupervised Change Detection in the Open-Vocabulary Era
• Sequence of Expert: Boosting Imitation Planners for Autonomous Driving through Temporal Alternation
• OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
• Harmonizing Generalization and Specialization: Uncertainty-Informed Collaborative Learning for Semi-supervised Medical Image Segmentation
• TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning
• Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
• Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
• From Overfitting to Reliability: Introducing the Hierarchical Approximate Bayesian Neural Network
• DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass
• Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis
• SACn: Soft Actor-Critic with n-step Returns
• Carrot, stick, or both? Price incentives for sustainable food choice in competitive environments
• PolySet: Restoring the Statistical Ensemble Nature of Polymers for Machine Learning
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models
• CORE: Contrastive Masked Feature Reconstruction on Graphs
• LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
• Intrinsic-Motivation Multi-Robot Social Formation Navigation with Coordinated Exploration
• MiniLingua: A Small Open-Source LLM for European Languages
• No One Left Behind: How to Exploit the Incomplete and Skewed Multi-Label Data for Conversion Rate Prediction
• ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
• Face Identity Unlearning for Retrieval via Embedding Dispersion
• Security and Detectability Analysis of Unicode Text Watermarking Methods Against Large Language Models
• FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models
• Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3)
• Detecting Emotion Drift in Mental Health Text Using Pre-Trained Transformers
• End2Reg: Learning Task-Specific Segmentation for Markerless Registration in Spine Surgery
• From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
• SSAS: Cross-subject EEG-based Emotion Recognition through Source Selection with Adversarial Strategy
• Non-Resolution Reasoning: A Framework for Preserving Semantic Ambiguity in Language Models
• SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping
• Behavior-Aware and Generalizable Defense Against Black-Box Adversarial Attacks for ML-Based IDS
• Verifying Rumors via Stance-Aware Structural Modeling
• Memory in the Age of AI Agents
• Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
• DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
• ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
• DA-SSL: self-supervised domain adaptor to leverage foundational models in turbt histopathology slides
• Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
• From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves
• World Models Can Leverage Human Videos for Dexterous Manipulation
• Large-Language Memorization During the Classification of United States Supreme Court Cases
• Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance
• Feedforward 3D Editing via Text-Steerable Image-to-3D
• DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders
• AI Copilots for Reproducibility in Science: A Case Study
• Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
• Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach
• PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Fast Wrong-way Cycling Detection in CCTV Videos: Sparse Sampling is All You Need
• Efficient Neural Common Neighbor for Temporal Graph Link Prediction
• Dy-mer: An Explainable DNA Sequence Representation Scheme using Dictionary Learning
• Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations
• No Screening is More Efficient with Multiple Objects
• Layer-aware TDNN: Speaker Recognition Using Multi-Layer Features from Pre-Trained Models
• MAISI: Medical AI for Synthetic Imaging
• KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
• Training Versatile Coding Agents in Synthetic Environments
• Comparison of different segmentation algorithms on brain volume and fractal dimension in infant brain MRIs
• Semantic Distance Measurement based on Multi-Kernel Gaussian Processes
• Adversarially Probing Cross-Family Sound Symbolism in 27 Languages
• Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting
• Accurate de novo sequencing of the modified proteome with OmniNovo
• GRC-Net: Gram Residual Co-attention Net for epilepsy prediction
• V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval
• Fractional Differential Equation Physics-Informed Neural Network and Its Application in Battery State Estimation
• UniMark: Artificial Intelligence Generated Content Identification Toolkit
• Dynamic Homophily with Imperfect Recall: Modeling Resilience in Adversarial Networks
• SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema
• A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams
• Rough Sets for Explainability of Spectral Graph Clustering
• Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling
• Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
• Exploring the Design Space of Transition Matching
• AI-Driven Real-Time Kick Classification in Olympic Taekwondo Using Sensor Fusion
• Mage: Cracking Elliptic Curve Cryptography with Cross-Axis Transformers
• Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The Public
• Explainable Artificial Intelligence for Economic Time Series: A Comprehensive Review and a Systematic Taxonomy of Methods and Concepts
• Can You Keep a Secret? Exploring AI for Care Coordination in Cognitive Decline
• Noise-robust Contrastive Learning for Critical Transition Detection in Dynamical Systems
• Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?
• Skillful Subseasonal-to-Seasonal Forecasting of Extreme Events with a Multi-Sphere Coupled Probabilistic Model
• StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
• Coupled Variational Reinforcement Learning for Language Model General Reasoning
• Detecting Prompt Injection Attacks Against Application Using Classifiers
• Content-Aware Ad Banner Layout Generation with Two-Stage Chain-of-Thought in Vision Language Models
• Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery
• Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives
• ORIBA: Exploring LLM-Driven Role-Play Chatbot as a Creativity Support Tool for Original Character Artists
• DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model
• Anatomy-Guided Representation Learning Using a Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images
• PerNodeDrop: A Method Balancing Specialized Subnets and Regularization in Deep Neural Networks
• DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
• Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
• Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
• Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis
• Theoretical Foundations of Prompt Engineering: From Heuristics to Expressivity
• Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits
• Robust Motion Generation using Part-level Reliable Data from Videos
• Intelligent Scientific Literature Explorer using Machine Learning (ISLE)
• Federated Learning with Feedback Alignment
• CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
• Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models (ASTA)
• Designing The Drive: Enhancing User Experience through Adaptive Interfaces in Autonomous Vehicles
• State over Tokens: Characterizing the Role of Reasoning Tokens
• OLC-WA: Drift Aware Tuning-Free Online Classification with Weighted Average
• Unveiling Statistical Significance of Online Regression over Multiple Datasets
• Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems
• Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks
• A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness
• From Small to Large: Generalization Bounds for Transformers on Variable-Size Inputs
• OPAL: Operator-Programmed Algorithms for Landscape-Aware Black-Box Optimization
• Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, LLaMA
• Decoding Human and AI Persuasion in National College Debate: Analyzing Prepared Arguments Through Aristotle's Rhetorical Principles
• Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
• On the continuity of flows
• Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding
• Adapting Multimodal Foundation Models for Few-Shot Learning: A Comprehensive Study on Contrastive Captioners
• Network Level Evaluation of Hangup Susceptibility of HRGCs using Deep Learning and Sensing Techniques: A Goal Towards Safer Future
• PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
• SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding
• Selective Conformal Risk Control
• Information-Consistent Language Model Recommendations through Group Relative Policy Optimization
• Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM
• Optimal Labeler Assignment and Sampling for Active Learning in the Presence of Imperfect Labels
• SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition
• Meta-GPT: Decoding the Metasurface Genome with Generative Artificial Intelligence
• CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
• Cisco Integrated AI Security and Safety Framework Report
• MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation
• Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
• Unified Interactive Multimodal Moment Retrieval via Cascaded Embedding-Reranking and Temporal-Aware Score Fusion
• Content Adaptive based Motion Alignment Framework for Learned Video Compression
• Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping
• Tackling Snow-Induced Challenges: Safe Autonomous Lane-Keeping with Robust Reinforcement Learning
• Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• Scaling Bidirectional Spans and Span Violations in Attention Mechanism
• GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
• LLM Rationalis? Measuring Bargaining Capabilities of AI Negotiators
• A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval
• Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection
• MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data
• Error-Driven Prompt Optimization for Arithmetic Reasoning
• Behavior and Representation in Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection
• Differentiable Evolutionary Reinforcement Learning
• neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings
• Defending the Hierarchical Result Models of Precedential Constraint
• MedCEG: Reinforcing Verifiable Medical Reasoning with Critical Evidence Graph
• A Multitask VAE for Time Series Preprocessing and Prediction of Blood Glucose Level
• Enhancing Urban Visual Place Recognition for Crowdsourced Flood Imagery via LLM-Guided Attention
• Totalitarian Technics: The Hidden Cost of AI Scribes in Healthcare
• The Ontological Dissonance Hypothesis: AI-Triggered Delusional Ideation as Folie a Deux Technologique
• Assessing Greenspace Attractiveness with ChatGPT, Claude, and Gemini: Do AI Models Reflect Human Perceptions?
• Active Inference with Reusable State-Dependent Value Profiles
• CR3G: Causal Reasoning for Patient-Centric Explanations in Radiology Report Generation
• Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representation
• Soft Decision Tree classifier: explainable and extendable PyTorch implementation
• Semantic Nutrition Estimation: Predicting Food Healthfulness from Text Descriptions
• Vision Foundry: A System for Training Foundational Vision AI Models
• Spiking Manifesto
• Airport Passenger Flow Forecasting via Deformable Temporal-Spectral Transformer Approach
• KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document
• KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
• Explainable AI for Smart Greenhouse Control: Interpretability of Temporal Fusion Transformer in the Internet of Robotic Things
• Rep Smarter, Not Harder: AI Hypertrophy Coaching with Wearable Sensors and Edge Neural Networks
• Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
• GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
• TopicProphet: Prophesies on Temporal Topic Trends and Stocks
• Adaptive Path Integral Diffusion: AdaPID
• Generative Stochastic Optimal Transport: Guided Harmonic Path-Integral Diffusion
• An Operator-Consistent Graph Neural Network for Learning Diffusion Dynamics on Irregular Meshes
• Hierarchical Task Offloading and Trajectory Optimization in Low-Altitude Intelligent Networks Via Auction and Diffusion-based MARL
• Expert Assessment: The Systemic Environmental Risks of Artficial Intelligence
• Explainable Adversarial-Robust Vision-Language-Action Model for Robotic Manipulation
• On the Dangers of Bootstrapping Generation for Continual Learning and Beyond
• Industrial AI Robustness Card: Evaluating and Monitoring Time Series Models
• Using Socio-economic Indicators, Smart Transit Systems, and Urban Simulator to Accelerate ZEV Adoption and Reduce VMT
• Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops
• WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
• It's About Time: The Temporal and Modal Dynamics of Copilot Usage
• Understanding Structural Representation in Foundation Models for Polymers
• An Experience Report on a Pedagogically Controlled, Curriculum-Constrained AI Tutor for SE Education
• Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"
• Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directions
• Should AI Become an Intergenerational Civil Right?
• Beyond Automation: Rethinking Work, Creativity, and Governance in the Age of Generative AI
• A fine-grained look at causal effects in causal spaces
• Towards Accessible Physical AI: LoRA-Based Fine-Tuning of VLA Models for Real-World Robot Control
• Vibe Coding in Practice: Flow, Technical Debt, and Guidelines for Sustainable Use
• FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applications
• Gene regulatory network inference algorithm based on spectral signed directed graph convolution
• MONET -- Virtual Cell Painting of Brightfield Images and Time Lapses Using Reference Consistent Diffusion
• Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction
• Mapping AI Risk Mitigations: Evidence Scan and Preliminary AI Risk Mitigation Taxonomy
• The Agentic Regulator: Risks for AI in Finance and a Proposed Agent-based Framework for Governance
• Unveiling User Perceptions in the Generative AI Era: A Sentiment-Driven Evaluation of AI Educational Apps' Role in Digital Transformation of e-Teaching
• DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition
• How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism
• A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach
• Data-Driven Global Sensitivity Analysis for Engineering Design Based on Individual Conditional Expectations
• Designing The Internet of Agents: A Framework for Trustworthy, Transparent, and Collaborative Human-Agent Interaction (HAX)
• Semantic search for 100M+ galaxy images using AI-generated captions
• Evidence-Driven Decision Support for AI Model Selection in Research Software Engineering
• V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
• Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
• Semantic-Drive: Democratizing Long-Tail Data Curation via Open-Vocabulary Grounding and Neuro-Symbolic VLM Consensus
• AI as a Teaching Partner: Early Lessons from Classroom Codesign with Secondary Teachers
• Instruction-Tuning Open-Weight Language Models for BPMN Model Generation
• The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior
• Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
• Congestion Reduction in EV Charger Placement Using Traffic Equilibrium Models
• A neuro-symbolic framework for accountability in public-sector AI
• MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models
• A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
• BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
• MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater
• Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
• Diffusion Language Model Inference with Monte Carlo Tree Search
• Thermal RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms
• Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation
• ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB
• Not All Transparency Is Equal: Source Presentation Effects on Attention, Interaction, and Persuasion in Conversational Search
• Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving
• A Monad-Based Clause Architecture for Artificial Age Score (AAS) in Large Language Models
• Solving Parallel Machine Scheduling With Precedences and Cumulative Resource Constraints With Calendars
• Mirror Mode in Fire Emblem: Beating Players at their own Game with Imitation and Reinforcement Learning
• Structured Personalization: Modeling Constraints as Matroids for Data-Minimal LLM Agents
• Causal Strengths and Leaky Beliefs: Interpreting LLM Reasoning via Noisy-OR Causal Bayes Nets
• Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis
• CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
• AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org
• Hypergame Rationalisability: Solving Agent Misalignment In Strategic Play
• Log Anomaly Detection with Large Language Models via Knowledge-Enriched Fusion
• Context-Aware Agentic Power Resources Optimisation in EV using Smart2ChargeApp
• The Forecast Critic: Leveraging Large Language Models for Poor Forecast Identification
• Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
• Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective
• Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation
• TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion
• A Geometric Theory of Cognition
• A Multi-Axial Mindset for Ontology Design Lessons from Wikidata's Polyhierarchical Structure
• Quantum-Aware Generative AI for Materials Discovery: A Framework for Robust Exploration Beyond DFT Biases
• Entropy Collapse: A Universal Failure Mode of Intelligent Systems
• Feeling the Strength but Not the Source: Partial Introspection in LLMs
• Understanding Critical Thinking in Generative Artificial Intelligence Use: Development, Validation, and Correlates of the Critical Thinking in AI Use Scale
• AI Transparency Atlas: Framework, Scoring, and Real-Time Model Card Evaluation Pipeline
• MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs
• SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation
• KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs
• World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents
• Large Language Newsvendor: Decision Biases and Cognitive Mechanisms
• AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation
• Modular and Multi-Path-Aware Offline Benchmarking for Mobile GUI Agents
• Value-Aware Multiagent Systems
• Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
• WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment
• Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning
• Personalized QoE Prediction: A Demographic-Augmented Machine Learning Framework for 5G Video Streaming Networks
• Causal Counterfactuals Reconsidered
• Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution
• Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents
• Satisfiability Modulo Theory Meets Inductive Logic Programming
• Towards Open Standards for Systemic Complexity in Digital Forensics
• M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
• Socratic Students: Teaching Language Models to Learn by Asking Questions
• Towards Unified Co-Speech Gesture Generation via Hierarchical Implicit Periodicity Learning
• Can AI Understand What We Cannot Say? Measuring Multilevel Alignment Through Abortion Stigma Across Cognitive, Interpersonal, and Structural Levels
• MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
• SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
• Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows