AI Research News Feeds for November 18th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• TR-Gaussians: High-fidelity Real-time Rendering of Planar Transmission and Reflection with 3D Gaussian Splatting
• MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements
• MM-Telco: Benchmarks and Multimodal Large Language Models for Telecom Applications
• PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
• DAP: A Discrete-token Autoregressive Planner for Autonomous Driving
• Trust in Vision-Language Models: Insights from a Participatory User Workshop
• HIBMatch: Hypergraph Information Bottleneck for Semi-supervised Alzheimer's Progression
• DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
• Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models
• 3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance
• BadVim: Unveiling Backdoor Threats in Visual State Space Model
• An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
• Revisiting Long-Tailed Learning: Insights from an Architectural Perspective
• Density-aware global-local attention network for point cloud segmentation
• Towards Collective Intelligence: Uncertainty-aware SAM Adaptation for Ambiguous Medical Image Segmentation
• Subjective and Objective Quality Evaluation of Super-Resolution Enhanced Broadcast Images on a Novel SR-IQA Dataset
• MeshCone: Second-Order Cone Programming for Geometrically-Constrained Mesh Enhancement
• FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentation
• RobustGait: Robustness Analysis for Appearance Based Gait Recognition
• Decoupling Scene Perception and Ego Status: A Multi-Context Fusion Approach for Enhanced Generalization in End-to-End Autonomous Driving
• MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images
• CapeNext: Rethinking and refining dynamic support information for category-agnostic pose estimation
• PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking
• Low-Level Dataset Distillation for Medical Image Enhancement
• DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
• Learning Implicit Neural Degradation Representation for Unpaired Image Dehazing
• Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining
• A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features
• CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model
• VEIL: Jailbreaking Text-to-Video Models via Visual Exploitation from Implicit Language
• Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
• MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation
• WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object Detection
• Automated Road Distress Detection Using Vision Transformersand Generative Adversarial Networks
• Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification
• SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical Registration
• THIR: Topological Histopathological Image Retrieval
• HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution
• GenTract: Generative Global Tractography
• Large Language Models Meet Extreme Multi-label Classification: Scaling and Multi-modal Framework
• Video Spatial Reasoning with Object-Centric 3D Rollout
• Birth of a Painting: Differentiable Brushstroke Reconstruction
• Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection
• Self-Supervised Ultrasound Screen Detection
• RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
• End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer
• 3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale
• Hybrid-Domain Adaptative Representation Learning for Gaze Estimation
• MRIQT: Physics-Aware Diffusion Model for Image Quality Transfer in Neonatal Ultra-Low-Field MRI
• MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
• Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention
• GeoX-Bench: Benchmarking Cross-View Geo-Localization and Pose Estimation Capabilities of Large Multimodal Models
• Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges
• SymGS : Leveraging Local Symmetries for 3D Gaussian Splatting Compression
• Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
• Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models
• SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting
• Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
• TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
• SkyReels-Text: Fine-grained Font-Controllable Text Editing for Poster Design
• CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving
• DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
• Computer Vision based group activity detection and action spotting
• YOLO Meets Mixture-of-Experts: Adaptive Expert Routing for Robust Object Detection
• Semi-Supervised Multi-Task Learning for Interpretable Quality As- sessment of Fundus Images
• Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model
• Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)
• TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing
• What Color Is It? A Text-Interference Multimodal Hallucination Benchmark
• Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source
• VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task
• FUSE: A Flow-based Mapping Between Shapes
• Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline
• InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE
• Language-Guided Invariance Probing of Vision-Language Models
• Mapping the Vanishing and Transformation of Urban Villages in China
• Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problems
• Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew
• Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks
• TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Images
• Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation
• Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification
• Adaptive Multi-Scale Integration Unlocks Robust Cell Annotation in Histopathology Images
• VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
• ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement
• Tissue Aware Nuclei Detection and Classification Model for Histopathology Images
• A Real-Time Driver Drowsiness Detection System Using MediaPipe and Eye Aspect Ratio
• Alpha Divergence Losses for Biometric Verification
• CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
• Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
• PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
• Distribution Matching Distillation Meets Reinforcement Learning
• TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
• Free-Form Scene Editor: Enabling Multi-Round Object Manipulation like in a 3D Engine
• Segment Anything Across Shots: A Method and Benchmark
• Back to Basics: Let Denoising Generative Models Denoise
• Image-based Morphological Characterization of Filamentous Biological Structures with Non-constant Curvature Shape Feature
• Slow - Motion Video Synthesis for Basketball Using Frame Interpolation
• Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks
• Understanding the Representation of Older Adults in Motion Capture Locomotion Datasets
• Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy: A Review
• End to End AI System for Surgical Gesture Sequence Recognition and Clinical Outcome Prediction
• TIMERIPPLE: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
• AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
• Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps
• AURA: Development and Validation of an Augmented Unplanned Removal Alert System using Synthetic ICU Videos
• Deep Unfolded BM3D: Unrolling Non-local Collaborative Filtering into a Trainable Neural Network
• Bregman geometry-aware split Gibbs sampling for Bayesian Poisson inverse problems
• Multimodal RGB-HSI Feature Fusion with Patient-Aware Incremental Heuristic Meta-Learning for Oral Lesion Classification
• RAA-MIL: A Novel Framework for Classification of Oral Cytology
• MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imaging
• DEMIST: \underline{DE}coupled \underline{M}ulti-stream latent d\underline{I}ffusion for Quantitative Myelin Map \underline{S}yn\underline{T}hesis
• Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
• Improving the Generalisation of Learned Reconstruction Frameworks
• BrainNormalizer: Anatomy-Informed Pseudo-Healthy Brain Reconstruction from Tumor MRI via Edge-Guided ControlNet
• Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration
• Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models
• Inertia-Informed Orientation Priors for Event-Based Optical Flow Estimation
• SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
• Scalable Vision-Guided Crop Yield Estimation
• ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks
• TM-UNet: Token-Memory Enhanced Sequential Modeling for Efficient Medical Image Segmentation
• One target to align them all: LiDAR, RGB and event cameras extrinsic calibration for Autonomous Driving
• Rethinking Bias in Generative Data Augmentation for Medical AI: a Frequency Recalibration Method
• LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors
• SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models
• Explainable AI-Generated Image Detection RewardBench
• Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Reinforcement Learning
• Fast Reasoning Segmentation for Images and Videos
• Changes in Real Time: Online Scene Change Detection with Multi-View Fusion
• Reasoning Text-to-Video Retrieval via Digital Twin Video Representations and Large Language Models
• Leveraging Quantum-Based Architectures for Robust Diagnostics
• Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation
• MSLoRA: Multi-Scale Low-Rank Adaptation via Attention Reweighting
• VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving
• Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
• Towards Rotation-only Imaging Geometry: Rotation Estimation
• Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance
• MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation
• RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
• Text-Guided Channel Perturbation and Pretrained Knowledge Integration for Unified Multi-Modality Image Fusion
• CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training
• MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
• Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion
• Visible Structure Retrieval for Lightweight Image-Based Relocalisation
• MdaIF: Robust One-Stop Multi-Degradation-Aware Image Fusion with Language-Driven Semantics
• D$^{2}$-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation
• ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding
• HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models
• EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis
• SEMC: Structure-Enhanced Mixture-of-Experts Contrastive Learning for Ultrasound Standard Plane Recognition
• Through-Foliage Surface-Temperature Reconstruction for early Wildfire Detection
• Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
• TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
• Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
• Fine-Grained Representation for Lane Topology Reasoning
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• LoRA-Enhanced Vision Transformer for Single Image based Morphing Attack Detection via Knowledge Distillation from EfficientNet
• Pixels or Positions? Benchmarking Modalities in Group Activity Recognition
• Open-World Test-Time Adaptation with Hierarchical Feature Aggregation and Attention Affine
• C3Net: Context-Contrast Network for Camouflaged Object Detection
• Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation
• Denoising Vision Transformer Autoencoder with Spectral Self-Regularization
• Medical Knowledge Intervention Prompt Tuning for Medical Image Classification
• DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry
• Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis
• Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
• DensePercept-NCSSD: Vision Mamba towards Real-time Dense Visual Perception with Non-Causal State Space Duality
• Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis
• BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections
• R$^{2}$Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
• HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models
• Counting Through Occlusion: Framework for Open World Amodal Counting
• FSDAM: Few-Shot Driving Attention Modeling via Vision-Language Coupling
• Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning
• Direct Visual Grounding by Directing Attention of Visual Tokens
• Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests
• SAGE: Saliency-Guided Contrastive Embeddings
• Which Way from B to A: The role of embedding geometry in image interpolation for Stable Diffusion
• Lightweight Optimal-Transport Harmonization on Edge Devices
• Enhancing Neuro-Oncology Through Self-Assessing Deep Learning Models for Brain Tumor Unified Model for MRI Segmentation
• MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
• SAGA: Source Attribution of Generative AI Videos
• Video Finetuning Improves Reasoning Between Frames
• View-aware Cross-modal Distillation for Multi-view Action Recognition
• Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views
• Simple Lines, Big Ideas: Towards Interpretable Assessment of Human Creativity from Drawings
• ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
• Reconstructing 3D Scenes in Native High Dynamic Range
• FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI
• DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning
• CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection
• Explore How to Inject Beneficial Noise in MLLMs
• CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation
• Generative Photographic Control for Scene-Consistent Video Cinematic Editing
• Text2Traffic: A Text-to-Image Generation and Editing Method for Traffic Scenes
• PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos
• ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarios
• Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking
• Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
• T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving
• EndoSight AI: Deep Learning-Driven Real-Time Gastrointestinal Polyp Detection and Segmentation for Enhanced Endoscopic Diagnostics
• CalibrateMix: Guided-Mixup Calibration of Image Semi-Supervised Models
• GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
• HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology
• ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
• Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach
• UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
• Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection
• PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
• Medal S: Spatio-Textual Prompt Model for Medical Segmentation
• Infinite-Story: A Training-Free Consistent Text-to-Image Generation
• SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
• Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis
• You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection
• Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues
• SpectralAdapt: Semi-Supervised Domain Adaptation with Spectral Priors for Human-Centered Hyperspectral Image Reconstruction
• REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
• Towards 3D Object-Centric Feature Learning for Semantic Scene Completion
• Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts
• uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data
• MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization
• DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation
• ViSS-R1: Self-Supervised Reinforcement Video Reasoning
• Monocular 3D Lane Detection via Structure Uncertainty-Aware Network with Curve-Point Queries
• LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
• Psychological stress during Examination and its estimation by handwriting in answer script
• Real-time pothole detection with onboard sensors and camera on vehicles
• A Method for Identifying Farmland System Habitat Types Based on the Dynamic-Weighted Feature Fusion Network Model
• AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation
• EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance
• Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
• LE-CapsNet: A Light and Enhanced Capsule Network
• Target-Balanced Score Distillation
• CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition
• AdaptFly: Prompt-Guided Adaptation of Foundation Models for Low-Altitude UAV Networks
• Do Blind Spots Matter for Word-Referent Mapping? A Computational Study with Infant Egocentric Video
• GROVER: Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion
• Exposing DeepFakes via Hyperspectral Domain Mapping
• Toward bilipshiz geometric models
• Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
• Batch Transformer Architecture: Case of Synthetic Image Generation for Emotion Expression Facial Recognition
• Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing
• SOTFormer: A Minimal Transformer for Unified Object Tracking and Trajectory Prediction
• Defending Unauthorized Model Merging via Dual-Stage Weight Protection
• FocusSDF: Boundary-Aware Learning for Medical Image Segmentation via Signed Distance Supervision
• Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)
• Advancing Annotat3D with Harpia: A CUDA-Accelerated Library For Large-Scale Volumetric Data Segmentation
• Prompt Triage: Structured Optimization Enhances Vision-Language Model Performance on Medical Imaging Benchmarks
• PI-NAIM: Path-Integrated Neural Adaptive Imputation Model
• Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models
• From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing
• Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs
• From Classification to Cross-Modal Understanding: Leveraging Vision-Language Models for Fine-Grained Renal Pathology
• BeyondFacial: Identity-Preserving Personalized Generation Beyond Facial Close-ups
• LithoSeg: A Coarse-to-Fine Framework for High-Precision Lithography Segmentation
• LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension
• Null-Space Diffusion Distillation for Efficient Photorealistic Lensless Imaging
• Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark
• GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
• VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation
• Improved Masked Image Generation with Knowledge-Augmented Token Representations
• SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images
• FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
• DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging
• DeiTFake: Deepfake Detection Model using DeiT Multi-Stage Training
• UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localization
• PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling
• MovSemCL: Movement-Semantics Contrastive Learning for Trajectory Similarity
• DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
• Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound
• Point Cloud Quantization through Multimodal Prompting for 3D Understanding
• Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning
• SemanticStitch: Enhancing Image Coherence through Foreground-Aware Seam Carving
• Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning
• Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillatio
• Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks
• DINOv3-Guided Cross Fusion Framework for Semantic-aware CT generation from MRI and CBCT
• Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
• BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation
• Fine-Grained DINO Tuning with Dual Supervision for Face Forgery Detection
• MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
• RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving
• OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description
• Compression and Inference of Spiking Neural Networks on Resource-Constrained Hardware
• MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering
• Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain
• FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective
• MMRINet: Efficient Mamba-Based Segmentation with Dual-Path Refinement for Low-Resource MRI Analysis
• Cross-View Cross-Modal Unsupervised Domain Adaptation for Driver Monitoring System
• Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation
• OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
• LSS3D: Learnable Spatial Shifting for Consistent and High-Quality 3D Generation from Single-Image
• GeoMVD: Geometry-Enhanced Multi-View Generation Model Based on Geometric Information Extraction
• A Novel AI-Driven System for Real-Time Detection of Mirror Absence, Helmet Non-Compliance, and License Plates Using YOLOv8 and OCR
• Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
• FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention
• Model Inversion Attack Against Deep Hashing
• Fusionista2.0: Efficiency Retrieval System for Large-Scale Datasets
• Prompt-Conditioned FiLM and Multi-Scale Fusion on MedSigLIP for Low-Dose CT Quality Assessment
• A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation
• CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
• Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations
• CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs
• Exploring Parameter-Efficient Fine-Tuning and Backtranslation for the WMT 25 General Translation Task
• LLMLagBench: Identifying Temporal Training Boundaries in Large Language Models
• PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection
• AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing
• Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
• CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
• MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
• ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
• AugAbEx : Way Forward for Extractive Case Summarization
• Do LLMs and Humans Find the Same Questions Difficult? A Case Study on Japanese Quiz Answering
• Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load
• From Phonemes to Meaning: Evaluating Large Language Models on Tamil
• Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
• Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing
• SGuard-v1: Safety Guardrail for Large Language Models
• QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs
• TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
• Mitigating Length Bias in RLHF through a Causal Lens
• MMWOZ: Building Multimodal Agent for Task-oriented Dialogue
• Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
• Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing
• Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
• Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
• Adaptive Focus Memory for Language Models
• On the Brittleness of LLMs: A Journey around Set Membership
• Evidence of Phase Transitions in Small Transformer-Based Language Models
• LLM Reinforcement in Context
• Evaluating Autoformalization Robustness via Semantically Similar Paraphrasing
• BioMedJImpact: A Comprehensive Dataset and LLM Pipeline for AI Engagement and Scientific Impact Analysis of Biomedical Journals
• From Passive to Persuasive: Steering Emotional Nuance in Human-AI Negotiation
• Quantifying consistency and accuracy of Latent Dirichlet Allocation
• NeuroLex: A Lightweight Domain Language Model for EEG Report Understanding and Generation
• From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
• Auditing Google's AI Overviews and Featured Snippets: A Case Study on Baby Care and Pregnancy
• Visual Room 2.0: Seeing is Not Understanding for MLLMs
• Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
• AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models
• How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm
• Spark-Prover-X1: Formal Theorem Proving Through Diverse Data Training
• BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models
• Evaluating the Ability of Large Language Models to Identify Adherence to CONSORT Reporting Guidelines in Randomized Controlled Trials: A Methodological Evaluation Study
• Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction
• A Comparative Analysis of Recurrent and Attention Architectures for Isolated Sign Language Recognition
• Zero-Shot Grammar Competency Estimation Using Large Language Model Generated Pseudo Labels
• Distinguishing Repetition Disfluency from Morphological Reduplication in Bangla ASR Transcripts: A Novel Corpus and Benchmarking Analysis
• TCM-5CEval: Extended Deep Evaluation Benchmark for LLM's Comprehensive Clinical Research Competence in Traditional Chinese Medicine
• Translation Entropy: A Statistical Framework for Evaluating Translation Systems
• Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
• Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms
• Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
• RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
• AHaSIS: Shared Task on Sentiment Analysis for Arabic Dialects
• Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
• Can Large Language Models Function as Qualified Pediatricians? A Systematic Evaluation in Real-World Clinical Contexts
• Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
• Non-Linear Scoring Model for Translation Quality Evaluation
• Aspect-Level Obfuscated Sentiment in Thai Financial Disclosures and Its Impact on Abnormal Returns
• Applying Large Language Models to Characterize Public Narratives
• Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
• Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation
• Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
• Crossing Borders: A Multimodal Challenge for Indian Poetry Translation and Image Generation
• LLM-Generated Negative News Headlines Dataset: Creation and Benchmarking Against Real Journalism
• CLINB: A Climate Intelligence Benchmark for Foundational Models
• SynBullying: A Multi LLM Synthetic Conversational Dataset for Cyberbullying Detectio
• EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation
• Automatic generation of DRI Statements
• Generative AI as a Linguistic Equalizer in Global Science
• Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy
• Leveraging Large Language Models for Career Mobility Analysis: A Study of Gender, Race, and Job Change Using U.S. Online Resume Profiles
• How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-resource Transfer
• VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing
• DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions
• Co-Layout: LLM-driven Co-optimization for Interior Layout
• Evolving Prompts for Toxicity Search in Large Language Models
• Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing
• A Content-Preserving Secure Linguistic Steganography
• WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance
• PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics
• Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
• Attention Grounded Enhancement for Visual Document Retrieval
• ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
• Historical/temporal necessities/possibilities, and a logical theory of them in branching time
• Simultaneous Machine Translation with Large Language Models
• Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language
• Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models
• ProFuser: Progressive Fusion of Large Language Models
• Contextual Breach: Assessing the Robustness of Transformer-based QA Models
• Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model
• Uncovering Factor Level Preferences to Improve Human-Model Alignment
• Is Our Chatbot Telling Lies? Assessing Correctness of an LLM-based Dutch Support Chatbot
• DeepMIDE: A Multi-Output Spatio-Temporal Method for Ultra-Scale Offshore Wind Energy Forecasting
• EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models
• Fair In-Context Learning via Latent Concept Variables
• Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)
• Toward Explainable Offline RL: Analyzing Representations in Intrinsically Motivated Decision Transformers
• Neutron Reflectometry by Gradient Descent
• A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data
• Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
• Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation
• FinGPT: Open-Source Financial Large Language Models
• Foundations of Structural Causal Models with Latent Selection
• A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
• Architectures and random properties of symplectic quantum circuits
• Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces
• Emulation with uncertainty quantification of regional sea-level change caused by the Antarctic Ice Sheet
• MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents
• On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
• Identify As A Human Does: A Pathfinder of Next-Generation Anti-Cheat Framework for First-Person Shooter Games
• A Framework for Real-Time Volcano-Seismic Event Recognition Based on Multi-Station Seismograms and Semantic Segmentation Models
• Time-Series-Informed Closed-loop Learning for Sequential Decision Making and Control
• NoLBERT: A No Lookahead(back) Foundational Language Model
• Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
• qc-kmeans: A Quantum Compressive K-Means Algorithm for NISQ Devices
• TimeStampEval: A Simple LLM Eval and a Little Fuzzy Matching Trick to Improve Search Accuracy
• MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
• On the Notion that Language Models Reason
• Scaling Open-Weight Large Language Models for Hydropower Regulatory Information Extraction: A Systematic Analysis
• Towards Autoformalization of LLM-generated Outputs for Requirement Verification
• Three Stage Narrative Analysis; Plot-Sentiment Breakdown, Structure Learning and Concept Detection
• Identifying Imaging Follow-Up in Radiology Reports: A Comparative Analysis of Traditional ML and LLM Approaches
• MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers
• Context-Emotion Aware Therapeutic Dialogue Generation: A Multi-component Reinforcement Learning Approach to Language Models for Mental Health Support
• A Reasoning Paradigm for Named Entity Recognition
• Ground Plane Projection for Improved Traffic Analytics at Intersections
• CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification
• More Than Irrational: Modeling Belief-Biased Agents
• AGGRNet: Selective Feature Extraction and Aggregation for Enhanced Medical Image Classification
• Multi-Domain EEG Representation Learning with Orthogonal Mapping and Attention-based Fusion for Cognitive Load Classification
• Stochastic Predictive Analytics for Stocks in the Newsvendor Problem
• From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm
• GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
• Real-Time Drivers' Drowsiness Detection and Analysis through Deep Learning
• MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
• A Multicollinearity-Aware Signal-Processing Framework for Cross-$\beta$ Identification via X-ray Scattering of Alzheimer's Tissue
• Discovering autonomous quantum error correction via deep reinforcement learning
• Iris: First-Class Multi-GPU Programming Experience in Triton
• DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
• FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration
• DLMMPR:Deep Learning-based Measurement Matrix for Phase Retrieval
• Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
• OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding
• LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• Adaptive Dual-Layer Web Application Firewall (ADL-WAF) Leveraging Machine Learning for Enhanced Anomaly and Threat Detection
• Scalable Hierarchical AI-Blockchain Framework for Real-Time Anomaly Detection in Large-Scale Autonomous Vehicle Networks
• AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework
• Accelerated Distributional Temporal Difference Learning with Linear Function Approximation
• Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data
• X-VMamba: Explainable Vision Mamba
• An Evaluation Framework for Network IDS/IPS Datasets: Leveraging MITRE ATT&CK and Industry Relevance Metrics
• TSB-HB: A Hierarchical Bayesian Extension of the TSB Model for Intermittent Demand Forecasting
• Adaptively Coordinating with Novel Partners via Learned Latent Strategies
• Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL
• RoCoISLR: A Romanian Corpus for Isolated Sign Language Recognition
• Event-CausNet: Unlocking Causal Knowledge from Text with Large Language Models for Reliable Spatio-Temporal Forecasting
• Function-on-Function Bayesian Optimization
• Neuro-Logic Lifelong Learning
• Practical Causal Evaluation Metrics for Biological Networks
• Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter
• Efficient Adversarial Malware Defense via Trust-Based Raw Override and Confidence-Adaptive Bit-Depth Reduction
• DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
• Benign Overfitting in Linear Classifiers with a Bias Term
• Scalable learning of macroscopic stochastic dynamics
• Mapping fNIRS Signals to Agent Performance: Toward Reinforcement Learning from Neural Feedback
• Structured Imitation Learning of Interactive Policies through Inverse Games
• Bootstrapping LLMs via Preference-Based Policy Optimization
• Classification of Hope in Textual Data using Transformer-Based Models
• Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation
• MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning
• Revealing the dynamic responses of Pb under shock loading based on DFT-accuracy machine learning potential
• GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs
• MeanFlow Transformers with Representation Autoencoders
• Reconstruction of Manifold Distances from Noisy Observations
• Orientation-Free Neural Network-Based Bias Estimation for Low-Cost Stationary Accelerometers
• Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
• STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
• NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes
• Region-Point Joint Representation for Effective Trajectory Similarity Learning
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks
• Likelihood-guided Regularization in Attention Based Models
• Case study of a differentiable heterogeneous multiphysics solver for a nuclear fusion application
• Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection
• EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation
• AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research
• Moving Pictures of Thought: Extracting Visual Knowledge in Charles S. Peirce's Manuscripts with Vision-Language Models
• Uncovering Causal Drivers of Energy Efficiency for Industrial Process in Foundry via Time-Series Causal Inference
• Taming Barren Plateaus in Arbitrary Parameterized Quantum Circuits Without Sacrificing Expressibility
• Exploring Multi-Table Retrieval Through Iterative Search
• Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling
• Systematic evaluation of time-frequency features for binaural sound source localization
• The Shape of Data: Topology Meets Analytics. A Practical Introduction to Topological Analytics and the Stability Index (TSI) in Business
• AI Fairness Beyond Complete Demographics: Current Achievements and Future Directions
• BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
• Power Homotopy for Zeroth-Order Non-Convex Optimizations
• A Gentle Introduction to Conformal Time Series Forecasting
• AtlasMorph: Learning conditional deformable templates for brain MRI
• Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
• OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
• Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues
• Cost-Driven Synthesis of Sound Abstract Interpreters
• T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization
• QUILL: An Algorithm-Architecture Co-Design for Cache-Local Deformable Attention
• Training-Free Multi-View Extension of IC-Light for Textual Position-Aware Scene Relighting
• Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
• From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands
• UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
• Scaling Spatial Intelligence with Multimodal Foundation Models
• Loss Patterns of Neural Networks
• Achieving Fairness with a Simple Ridge Penalty
• State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length
• Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
• CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
• GLANCE: Global Actions in a Nutshell for Counterfactual Explainability
• Uncertainty Quantification for Deep Learning
• Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problems
• Deep deterministic policy gradient with symmetric data augmentation for lateral attitude tracking control of a fixed-wing aircraft
• Temporal Test-Time Adaptation with State-Space Models
• Efficiently Computing Compact Formal Explanations
• Exploiting Missing Data Remediation Strategies using Adversarial Missingness Attacks
• Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularization
• Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
• Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning
• Finding Kissing Numbers with Game-theoretic Reinforcement Learning
• Fast and Robust Simulation-Based Inference With Optimization Monte Carlo
• PAST: A Primary-Auxiliary Spatio-Temporal Network for Traffic Time Series Imputation
• MMWSTM-ADRAN+: A Novel Hybrid Deep Learning Architecture for Enhanced Climate Time Series Forecasting and Extreme Event Prediction
• Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression
• Discovering Operational Patterns Using Image-Based Convolutional Clustering and Composite Evaluation: A Case Study in Foundry Melting Processes
• Hardware optimization on Android for inference of AI models
• Artificial Intelligence-Enabled Spirometry for Early Detection of Right Heart Failure
• Multi-task GINN-LP for Multi-target Symbolic Regression
• AdamX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate
• GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction
• Quantum Machine Learning via Contrastive Training
• Naga: Vedic Encoding for Deep State Space Models
• A Quantum Tensor Network-Based Viewpoint for Modeling and Analysis of Time Series Data
• Mitigating Spurious Correlations in Patch-wise Tumor Classification on High-Resolution Multimodal Images
• Fairness-Aware Graph Representation Learning with Limited Demographic Information
• Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries
• RAC-DMVC: Reliability-Aware Contrastive Deep Multi-View Clustering under Multi-Source Noise
• P1: Mastering Physics Olympiads with Reinforcement Learning
• Batch Acquisition Function Evaluations and Decouple Optimizer Updates for Faster Bayesian Optimization
• Towards Multimodal Representation Learning in Paediatric Kidney Disease
• Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures
• FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
• Weight-sparse transformers have interpretable circuits
• Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
• Scientific Data Compression and Super-Resolution Sampling
• Cross-Learning from Scarce Data via Multi-Task Constrained Optimization
• Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers
• Efficient Calibration for Decision Making
• Learning stochasticity: a nonparametric framework for intrinsic noise estimation
• ST-ProC: A Graph-Prototypical Framework for Robust Semi-Supervised Travel Mode Identification
• Rare Genomic Subtype Discovery from RNA-seq via Autoencoder Embeddings and Stability-Aware Clustering
• From Black Box to Insight: Explainable AI for Extreme Event Preparedness
• Limitations of Quantum Advantage in Unsupervised Machine Learning
• LLM Architecture, Scaling Laws, and Economics: A Quick Summary
• Social and Physical Attributes-Defined Trust Evaluation for Effective Collaborator Selection in Human-Device Coexistence Systems
• Mind the Gap: Revealing Inconsistencies Across Heterogeneous AI Accelerators
• Quantifying Skill and Chance: A Unified Framework for the Geometry of Games
• Physics-Informed Neural Network-based Reliability Analysis of Buried Pipelines
• Lightweight Hopfield Neural Networks for Bioacoustic Detection and Call Monitoring of Captive Primates
• Hierarchical Federated Graph Attention Networks for Scalable and Resilient UAV Collision Avoidance
• Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges
• Omics-scale polymer computational database transferable to real-world artificial intelligence applications
• Tactile Data Recording System for Clothing with Motion-Controlled Robotic Sliding
• Exploring Parallelism in FPGA-Based Accelerators for Machine Learning Applications
• The Environmental Impact of Ensemble Techniques in Recommender Systems
• GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning
• A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systems
• Generalized Inequality-based Approach for Probabilistic WCET Estimation
• Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation
• Harli: Harvest Underutilized Resources in LLM Serving with Finetuning Tasks
• Noise-Aware Optimization in Nominally Identical Manufacturing and Measuring Systems for High-Throughput Parallel Workflows
• Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules
• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction
• On the Measure of a Model: From Intelligence to Generality
• Towards Mitigating Systematics in Large-Scale Surveys via Few-Shot Optimal Transport-Based Feature Alignment
• FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition
• A Computational Method for Solving the Stochastic Joint Replenishment Problem in High Dimensions
• TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models
• MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning
• Modeling X-ray photon pile-up with a normalizing flow
• ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts
• Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
• Additive Large Language Models for Semi-Structured Text
• PCA recovery thresholds in low-rank matrix inference with sparse noise
• Enhancing XR Auditory Realism via Multimodal Scene-Aware Acoustic Rendering
• InData: Towards Secure Multi-Step, Tool-Based Data Analysis
• A Deep Learning Framework for Thyroid Nodule Segmentation and Malignancy Classification from Ultrasound Images
• Improving Neutrino Oscillation Measurements through Event Classification
• Augmenting The Weather: A Hybrid Counterfactual-SMOTE Algorithm for Improving Crop Growth Prediction When Climate Changes
• Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization
• Temporal Micro-Doppler Spectrogram-based ViT Multiclass Target Classification
• On the Entropy Calibration of Language Models
• Bayesian--AI Fusion for Epidemiological Decision Making: Calibrated Risk, Honest Uncertainty, and Hyperparameter Intelligence
• Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams
• Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
• Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy
• Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models
• Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis
• Calibrated Multimodal Representation Learning with Missing Modalities
• Preference Learning from Physics-Based Feedback: Tuning Language Models to Design BCC/B2 Superalloys
• BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
• Aggregating Conformal Prediction Sets via {\alpha}-Allocation
• Informed Bootstrap Augmentation Improves EEG Decoding
• From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction
• Explainable Transformer-Based Email Phishing Classification with Adversarial Robustness
• Decoupled Action Head: Confining Task Knowledge to Conditioning Layers
• TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery
• Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function
• Rapid Machine Learning-Driven Detection of Pesticides and Dyes Using Raman Spectroscopy
• MixAR: Mixture Autoregressive Image Generation
• Chemistry-Enhanced Diffusion-Based Framework for Small-to-Large Molecular Conformation Generation
• Suppressing VLM Hallucinations with Spectral Representation Filtering
• Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts
• Reinforcement Learning for Chemical Ordering in Alloy Nanoparticles
• PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
• D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
• Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor
• Learning Time in Static Classifiers
• Linear time small coresets for k-mean clustering of segments with applications
• Enhancing Machine Learning Model Efficiency through Quantization and Bit Depth Optimization: A Performance Analysis on Healthcare Data
• LMM-IR: Large-Scale Netlist-Aware Multimodal Framework for Static IR-Drop Prediction
• Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
• PID-controlled Langevin Dynamics for Faster Sampling of Generative Models
• FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
• NFQ2.0: The CartPole Benchmark Revisited
• Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back
• FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
• Attention-Enhanced Convolutional Autoencoder and Structured Delay Embeddings for Weather Prediction
• A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning
• Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
• Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations
• Oxytrees: Model Trees for Bipartite Learning
• On Robustness of Linear Classifiers to Targeted Data Poisoning
• LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
• Convolutional Model Trees
• Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering
• DIVIDE: A Framework for Learning from Independent Multi-Mechanism Data Using Deep Encoders and Gaussian Processes
• Are LLMs The Way Forward? A Case Study on LLM-Guided Reinforcement Learning for Decentralized Autonomous Driving
• Conformal Online Learning of Deep Koopman Linear Embeddings
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers
• MolEdit: Knowledge Editing for Multimodal Molecule Language Models
• Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
• Physics-Constrained Adaptive Neural Networks Enable Real-Time Semiconductor Manufacturing Optimization with Minimal Training Data
• Optimal Look-back Horizon for Time Series Forecasting in Federated Learning
• Genomic Next-Token Predictors are In-Context Learners
• The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation
• Expressive Temporal Specifications for Reward Monitoring
• Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
• Catastrophic Forgetting in Kolmogorov-Arnold Networks
• An Evaluation of Representation Learning Methods in Particle Physics Foundation Models
• Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency
• RoS-Guard: Robust and Scalable Online Change Detection with Delay-Optimal Guarantees
• From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
• An approach of deep reinforcement learning for maximizing the net present value of stochastic projects
• On the Fundamental Limits of LLMs at Scale
• On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples
• Method of Manufactured Learning for Solver-free Training of Neural Operators
• Functional Mean Flow in Hilbert Space
• Contrastive Entropy Bounds for Density and Conditional Density Decomposition
• LinkedIn Profile Characteristics and Professional Success Indicators
• AIF: Asynchronous Inference Framework for Cost-Effective Pre-Ranking
• APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift
• A FEDformer-Based Hybrid Framework for Anomaly Detection and Risk Forecasting in Financial Time Series
• Global Cross-Time Attention Fusion for Enhanced Solar Flare Prediction from Multivariate Time Series
• RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems
• Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
• Learning Branching Policies for MILPs with Proximal Policy Optimization
• Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
• The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training
• The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference
• Learning Time-Scale Invariant Population-Level Neural Representations
• SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment
• One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
• Bi-View Embedding Fusion: A Hybrid Learning Approach for Knowledge Graph's Nodes Classification Addressing Problems with Limited Data
• Generalization Bounds for Semi-supervised Matrix Completion with Distributional Side Information
• Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting
• Self-Organization of Attractor Landscapes in High-Capacity Kernel Logistic Regression Hopfield Networks
• Latency and Ordering Effects in Online Decisions
• MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity
• Self-Adaptive Graph Mixture of Models
• A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning
• Real-time prediction of breast cancer sites using deformation-aware graph neural network
• Transformer-Based Scalable Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions
• Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning
• Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schr\"odinger Bridges
• Soft Conflict-Resolution Decision Transformer for Offline Multi-Task Reinforcement Learning
• Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching
• OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs
• Warm-starting active-set solvers using graph neural networks
• Real-time distortion prediction in metallic additive manufacturing via a physics-informed neural operator approach
• Uncertainty-aware Physics-informed Neural Networks for Robust CARS-to-Raman Signal Reconstruction
• DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Play
• ParaDySe: A Parallel-Strategy Switching Framework for Dynamic Sequence Lengths in Transformer
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
• Laplace Learning in Wasserstein Space
• MorphBoost: Self-Organizing Universal Gradient Boosting with Adaptive Tree Morphing
• Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification
• Computational Measurement of Political Positions: A Review of Text-Based Ideal Point Estimation Algorithms
• Incoherent Beliefs & Inconsistent Actions in Large Language Models
• Uncovering and Mitigating Transient Blindness in Multimodal Model Editing
• Seek and You Shall Fold
• Edge-aware baselines for ogbn-proteins in PyTorch Geometric: species-wise normalization, post-hoc calibration, and cost-accuracy trade-offs
• KForge: Program Synthesis for Diverse AI Hardware Accelerators
• Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning
• Tab-PET: Graph-Based Positional Encodings for Tabular Transformers
• Statistically Accurate and Robust Generative Prediction of Rock Discontinuities with A Tabular Foundation Model
• Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning
• A Novel Hierarchical Integration Method for Efficient Model Merging in Medical LLMs
• Federated Learning for Pediatric Pneumonia Detection: Enabling Collaborative Diagnosis Without Sharing Patient Data
• Multiscale Grassmann Manifolds for Single-Cell Data Analysis
• Fast 3D Surrogate Modeling for Data Center Thermal Management
• Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
• Physics-Informed Neural ODEs with Scale-Aware Residuals for Learning Stiff Biophysical Dynamics
• KAN/H: Kolmogorov-Arnold Network using Haar-like bases
• DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks
• Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts
• Diffusion Models: A Mathematical Introduction
• IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
• Improving a Hybrid Graphsage Deep Network for Automatic Multi-objective Logistics Management in Supply Chain
• Sumudu Neural Operator for ODEs and PDEs
• Learning Fair Representations with Kolmogorov-Arnold Networks
• CATCHFed: Efficient Unlabeled Data Utilization for Semi-Supervised Federated Learning in Limited Labels Environments
• Coordinate Descent for Network Linearization
• Simplicial covering dimension of extremal concept classes
• Conformal Constrained Policy Optimization for Cost-Effective LLM Agents
• Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers
• On the Trade-Off Between Transparency and Security in Adversarial Machine Learning
• Leveraging Exogenous Signals for Hydrology Time Series Forecasting
• Transformers vs. Recurrent Models for Estimating Forest Gross Primary Production
• Better LLM Reasoning via Dual-Play
• FLEX: Feature Importance from Layered Counterfactual Explanations
• Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
• Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm
• A Systematic Study of Model Extraction Attacks on Graph Foundation Models
• Batch Matrix-form Equations and Implementation of Multilayer Perceptrons
• Beyond the Laplacian: Interpolated Spectral Augmentation for Graph Neural Networks
• A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
• SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis
• Learning the relative composition of EEG signals using pairwise relative shift pretraining
• Computation-aware Energy-harvesting Federated Learning: Cyclic Scheduling with Selective Participation
• Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression
• ReCast: Reliability-aware Codebook Assisted Lightweight Time Series Forecasting
• Selecting Fine-Tuning Examples by Quizzing VLMs
• EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
• Mesh-based Super-resolution of Detonation Flows with Multiscale Graph Transformers
• Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread
• Treatment Stitching with Schr\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies
• SenseRay-3D: Generalizable and Physics-Informed Framework for End-to-End Indoor Propagation Modeling
• To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance
• Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networks
• HCPO: Hierarchical Conductor-Based Policy Optimization in Multi-Agent Reinforcement Learning
• FairGSE: Fairness-Aware Graph Neural Network without High False Positive Rates
• Fusion-ResNet: A Lightweight multi-label NILM Model Using PCA-ICA Feature Fusion
• Variation-Bounded Loss for Noise-Tolerant Learning
• Finding Time Series Anomalies using Granular-ball Vector Data Description
• Open Banking Foundational Model: Learning Language Representations from Few Financial Transactions
• Rethinking Deep Alignment Through The Lens Of Incomplete Learning
• Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis
• FGM optimization in complex domains using Gaussian process regression based profile generation algorithm
• TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective
• Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering
• Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?
• Evaluation of Multi- and Single-objective Learning Algorithms for Imbalanced Data
• MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization
• AlignTree: Efficient Defense Against LLM Jailbreak Attacks
• Chicken Swarm Kernel Particle Filter: A Structured Rejuvenation Approach with KLD-Efficient Sampling
• SCI: An Equilibrium for Signal Intelligence
• Cross-view Joint Learning for Mixed-Missing Multi-view Unsupervised Feature Selection
• Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks
• MMSense: Adapting Vision-based Foundation Model for Multi-task Multi-modal Wireless Sensing
• Optimal Self-Consistency for Efficient Reasoning with Large Language Models
• Active Learning of Symbolic Automata Over Rational Numbers
• BlinDNO: A Distributional Neural Operator for Dynamical System Reconstruction from Time-Label-Free data
• LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment
• Dynamic Reward Scaling for Multivariate Time Series Anomaly Detection: A VAE-Enhanced Reinforcement Learning Approach
• BitSnap: Checkpoint Sparsification and Quantization in LLM Training
• CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection
• On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
• Interpretable Fine-Gray Deep Survival Model for Competing Risks: Predicting Post-Discharge Foot Complications for Diabetic Patients in Ontario
• The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
• Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood Glucose Regulation
• Tailored Primitive Initialization is the Secret Key to Reinforcement Learning
• VISAGNN: Versatile Staleness-Aware Efficient Training on Large-Scale Graphs
• Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction
• Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection
• Redundancy-optimized Multi-head Attention Networks for Multi-View Multi-Label Feature Selection
• Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction
• Diffusion Model Based Signal Recovery Under 1-Bit Quantization
• SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• Towards Better IncomLDL: We Are Unaware of Hidden Labels in Advance
• BSO: Binary Spiking Online Optimization Algorithm
• Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
• Spectral Bias Mitigation via xLSTM-PINN: Memory-Gated Representation Refinement for Physics-Informed Learning
• Regret Guarantees for Linear Contextual Stochastic Shortest Path
• Center-Outward q-Dominance: A Sample-Computable Proxy for Strong Stochastic Dominance in Multi-Objective Optimisation
• CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
• Training Instabilities Induce Flatness Bias in Gradient Descent
• Softmax as a Lagrangian-Legendrian Seam
• LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora
• Detecting Statistically Significant Fairness Violations in Recidivism Forecasting Algorithms
• DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs
• Decoupling Positional and Symbolic Attention Behavior in Transformers
• The Anatomy of a Triton Attention Kernel
• Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations
• Output Supervision Can Obfuscate the Chain of Thought
• Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
• WildfireGenome: Interpretable Machine Learning Reveals Local Drivers of Wildfire Risk and Their Cross-County Variation
• Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
• Sound Logical Explanations for Mean Aggregation Graph Neural Networks
• Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach
• Aspiration-based Perturbed Learning Automata in Games with Noisy Utility Measurements. Part A: Stochastic Stability in Non-zero-Sum Games
• Enhancing failure prediction in nuclear industry: Hybridization of knowledge- and data-driven techniques
• Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
• Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
• Early GVHD Prediction in Liver Transplantation via Multi-Modal Deep Learning on Imbalanced EHR Data
• MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
• SA-EMO: Structure-Aligned Encoder Mixture of Operators for Generalizable Full-waveform Inversion
• Global Feature Enhancing and Fusion Framework for Strain Gauge Time Series Classification
• Predicting Grain Growth in Polycrystalline Materials Using Deep Learning Time Series Models
• Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
• An Explainable and Fair AI Tool for PCOS Risk Assessment: Calibration, Subgroup Equity, and Interactive Clinical Deployment
• Enhancing PINN Accuracy for the RLW Equation: Adaptive and Conservative Approaches
• EcoSpa: Efficient Transformer Training with Coupled Sparsity
• A Deep Learning Model to Predicting Changes in Consumer Attributes for New Line-extended Products
• Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection
• Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning
• Enhanced Water Leak Detection with Convolutional Neural Networks and One-Class Support Vector Machine
• Incomplete Depression Feature Selection with Missing EEG Channels
• How many stations are sufficient? Exploring the effect of urban weather station density reduction on imputation accuracy of air temperature and humidity
• Convergence of Multiagent Learning Systems for Traffic control
• On the Probabilistic Learnability of Compact Neural Network Preimage Bounds
• SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
• Clifford Algebraic Rotor Embeddings : Maybe embeddings should start to CARE
• Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks
• Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion
• Do traveling waves make good positional encodings?
• H-Model: Dynamic Neural Architectures for Adaptive Processing
• Evaluation of LLM-based Explanations for a Learning Analytics Dashboard
• Synergistic Feature Fusion for Latent Lyrical Classification: A Gated Deep Learning Architecture
• Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
• Learning with Preserving for Continual Multitask Learning
• Homotopy-Guided Self-Supervised Learning of Parametric Solutions for AC Optimal Power Flow
• A neural optimization framework for free-boundary diffeomorphic mapping problems and its applications
• Probabilistic Wildfire Susceptibility from Remote Sensing Using Random Forests and SHAP
• MPCM-Net: Multi-scale network integrates partial attention convolution with Mamba for ground-based cloud image segmentation
• Stratified Knowledge-Density Super-Network for Scalable Vision Transformers
• A Bayesian Model for Multi-stage Censoring
• R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models
• Regularized Schr\"odinger: Alleviating Distortion and Exposure Bias in Solving Inverse Problems
• Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling
• Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
• Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues
• AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation
• Toward Dignity-Aware AI: Next-Generation Elderly Monitoring from Fall Detection to ADL
• Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantification
• Moirai 2.0: When Less Is More for Time Series Forecasting
• Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification
• Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting
• Enhancing Reinforcement Learning in 3D Environments through Semantic Segmentation: A Case Study in ViZDoom
• Simple Vision-Language Math Reasoning via Rendered Text
• Multimodal ML: Quantifying the Improvement of Calorie Estimation Through Image-Text Pairs
• Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental modelling
• FSC-Net: Fast-Slow Consolidation Networks for Continual Learning
• Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control
• Reasoning: From Reflection to Solution