AI Research News Feeds for October 15th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
• Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
• ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
• Hardware-aware Coding Function Design for Compressive Single-Photon 3D Cameras
• MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites
• FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
• Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
• DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation
• State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
• UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
• BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
• Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos
• The Impact of Synthetic Data on Object Detection Model Performance: A Comparative Analysis with Real-World Data
• DIANet: A Phase-Aware Dual-Stream Network for Micro-Expression Recognition via Dynamic Images
• HoneyBee: Data Recipes for Vision-Language Reasoners
• BIGFix: Bidirectional Image Generation with Token Fixing
• Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection
• Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding
• Multiplicative Loss for Enhancing Semantic Segmentation in Medical and Cellular Images
• Local Background Features Matter in Out-of-Distribution Detection
• AngularFuse: A Closer Look at Angle-based Perception for Spatial-Sensitive Multi-Modality Image Fusion
• SpineBench: Benchmarking Multimodal LLMs for Spinal Pathology Analysis
• PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval
• Hybrid Gaussian Splatting for Novel Urban View Synthesis
• CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
• Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling
• Scene Coordinate Reconstruction Priors
• Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agenda
• VideoLucy: Deep Memory Backtracking for Long Video Understanding
• A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation
• MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
• BSGS: Bi-stage 3D Gaussian Splatting for Camera Motion Deblurring
• Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points
• CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
• MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking
• Learning Human Motion with Temporally Conditional Mamba
• Unlocking Zero-Shot Plant Segmentation with Pl@ntNet Intelligence
• LayerSync: Self-aligning Intermediate Layers
• Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
• WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation
• Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency
• On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
• TerraCodec: Compressing Earth Observations
• MCOP: Multi-UAV Collaborative Occupancy Prediction
• EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
• Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
• FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
• SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
• E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
• PET Head Motion Estimation Using Supervised Deep Learning with Attention
• AnyUp: Universal Feature Upsampling
• Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
• What If : Understanding Motion Through Sparse Interactions
• Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
• ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
• Detect Anything via Next Point Prediction
• DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
• GS-Verse: Mesh-based Gaussian Splatting for Physics-aware Interaction in Virtual Reality
• MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
• Gaussian Semantic Field for One-shot LiDAR Global Localization
• MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations
• Tensor Completion via Monotone Inclusion: Generalized Low-Rank Priors Meet Deep Denoisers
• Fast Visuomotor Policy for Robotic Manipulation
• SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
• Enhancing Representations through Heterogeneous Self-Supervised Learning
• Constructing a Real-World Benchmark for Early Wildfire Detection with the New PYRONEAR-2025 Dataset
• Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability
• Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
• Exploring Facial Biomarkers for Depression through Temporal Analysis of Action Units
• CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving
• TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusion
• DarkIR: Robust Low-Light Image Restoration
• Generate, Transduct, Adapt: Iterative Transduction with VLMs
• Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective
• UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
• OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
• Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications
• DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding
• SAIP-Net: Enhancing Remote Sensing Image Segmentation via Spectral Adaptive Information Propagation
• Visual Affordance Prediction: Survey and Reproducibility
• Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
• VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
• Image Quality Assessment for Embodied AI
• Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space
• Normalize Filters! Classical Wisdom for Deep Vision
• CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy
• OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
• GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
• Logarithmic Mathematical Morphology: theory and applications
• BAAF: A benchmark attention adaptive framework for medical ultrasound image segmentation tasks
• OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation
• Robust Real-Time Endoscopic Stereo Matching under Fuzzy Tissue Boundaries
• GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling
• How to Train Your Metamorphic Deep Neural Network
• R-WoM: Retrieval-augmented World Model For Computer-use Agents
• LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance
• LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
• GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences
• Evaluating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries
• Scaling Long-Horizon LLM Agent via Context-Folding
• SAGE: A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn AGent Evaluation
• Generate Logical Equivalence Questions
• Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM
• On the Interplay between Human Label Variation and Model Fairness
• Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
• Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
• Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
• A Survey on Parallel Reasoning
• Towards Inference-time Scaling for Continuous Space Reasoning
• Not in Sync: Unveiling Temporal Bias in Audio Chat Models
• DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation
• DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
• A large-scale, unsupervised pipeline for automatic corpus annotation using LLMs: variation and change in the English consider construction
• Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation
• Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
• MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts
• PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
• Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
• Resource-sensitive but language-blind: Community size and not grammatical complexity better predicts the accuracy of Large Language Models in a novel Wug Test
• SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
• VISaGE: Understanding Visual Generics and Exceptions
• Teaching Language Models to Faithfully Express their Uncertainty
• ACADATA: Parallel Dataset of Academic Data for Machine Translation
• COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
• Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
• Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages
• Language Models Model Language
• Cost Analysis of Human-corrected Transcription for Predominately Oral Languages
• Evolution of wartime discourse on Telegram: A comparative study of Ukrainian and Russian policymakers' communication before and after Russia's full-scale invasion of Ukraine
• Task-Aware Reduction for Scalable LLM-Database Systems
• Don't Walk the Line: Boundary Guidance for Filtered Generation
• Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities
• Deep Research Brings Deeper Harm
• UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
• HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
• DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
• Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
• The Role of Parametric Injection-A Systematic Study of Parametric Retrieval-Augmented Generation
• Content Anonymization for Privacy in Long-form Audio
• SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
• MLRIP: Pre-training a military language representation model with informative factual knowledge and professional knowledge base
• GRDD: A Dataset for Greek Dialectal NLP
• Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning
• Cross-Modal Safety Alignment: Is textual unlearning all you need?
• The Open Source Advantage in Large Language Models (LLMs)
• AFRIDOC-MT: Document-level MT Corpus for African Languages
• From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
• A Survey of Multilingual Reasoning in Language Models
• Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking
• Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions
• The Distribution of Dependency Distance and Hierarchical Distance in Contemporary Written Japanese and Its Influencing Factors
• MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation
• The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models
• Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
• Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment
• Lost at the Beginning of Reasoning
• Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
• LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
• Revela: Dense Retriever Learning via Language Modeling
• Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
• Enhancing the Quality of 3D Lunar Maps Using JAXA's Kaguya Imagery
• Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis
• Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning
• Evaluating the Explainability of Vision Transformers in Medical Imaging
• APGNet: Adaptive Prior-Guided for Underwater Camouflaged Object Detection
• VIDMP3: Video Editing by Representing Motion with Pose and Position Priors
• Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback
• IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation
• An Adaptive Edge-Guided Dual-Network Framework for Fast QR Code Motion Deblurring
• LOOPerSet: A Large-Scale Dataset for Data-Driven Polyhedral Compiler Optimization
• Kernel Treatment Effects with Adaptively Collected Data
• ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
• Neural variational inference for cutting feedback during uncertainty propagation
• Grounded AI for Code Review: Resource-Efficient Large-Model Serving in Enterprise Pipelines
• On some practical challenges of conformal prediction
• Learning Operators through Coefficient Mappings in Fixed Basis Spaces
• Learning to Throw-Flip
• Generative Modeling of Aerosol State Representations
• FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes
• Does Weighting Improve Matrix Factorization for Recommender Systems?
• The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution
• Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading
• DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism
• Interactive Atmospheric Composition Emulation for Next-Generation Earth System Models
• Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
• Mean-square and linear convergence of a stochastic proximal point algorithm in metric spaces of nonpositive curvature
• Learning-Augmented Streaming Algorithms for Correlation Clustering
• Deep Signature and Neural RDE Methods for Path-Dependent Portfolio Optimization
• Controllable Generative Trajectory Prediction via Weak Preference Alignment
• How Patterns Dictate Learnability in Sequential Data
• Fast and the Furious: Hot Starts in Pursuit-Evasion Games
• Quantifying Dataset Similarity to Guide Transfer Learning
• Transfer Learning with Distance Covariance for Random Forest: Error Bounds and an EHR Application
• In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
• Adversarial Robustness in One-Stage Learning-to-Defer
• GrASP: A Generalizable Address-based Semantic Prefetcher for Scalable Transactional and Analytical Workloads
• Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
• torchsom: The Reference PyTorch Library for Self-Organizing Maps
• Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentials
• PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
• Machine Learning-Integrated Hybrid Fluid-Kinetic Framework for Quantum Electrodynamic Laser Plasma Simulations
• Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs
• Analyzing Data Quality and Decay in Mega-Constellations: A Physics-Informed Machine Learning Approach
• DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation
• SeFEF: A Seizure Forecasting Evaluation Framework
• Network-Optimised Spiking Neural Network (NOS) Scheduling for 6G O-RAN: Spectral Margin and Delay-Tail Control
• Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications
• Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
• Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
• Lecture Notes on Verifying Graph Neural Networks
• Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling
• Privacy-aware Gaussian Process Regression
• Expert-Aided Causal Discovery of Ancestral Graphs
• Neural Surveillance: Live-Update Visualization of Latent Training Dynamics
• Output-Constrained Decision Trees
• LDPKiT: Superimposing Remote Queries for Privacy-Preserving Local Model Training
• Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs
• LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM Inference
• InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
• Methods to improve run time of hydrologic models: opportunities and challenges in the machine learning era
• Graph Neural Network Surrogates to leverage Mechanistic Expert Knowledge towards Reliable and Immediate Pandemic Response
• Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations
• Sim-to-real supervised domain adaptation for radioisotope identification
• Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing
• Stochastic Process Learning via Operator Flow Matching
• $k$-SVD with Gradient Descent
• Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees
• On Different Notions of Redundancy in Conditional-Independence-Based Discovery of Graphical Models
• Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT
• Clustering by Nonparametric Smoothing
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
• Rethinking Graph Structure Learning in the Era of LLMs
• OrbitZoo: Multi-Agent Reinforcement Learning Environment for Orbital Dynamics
• Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
• An Effective Gram Matrix Characterizes Generalization in Deep Networks
• A Representation Learning Approach to Feature Drift Detection in Wireless Networks
• Efficient Attention via Pre-Scoring: Prioritizing Informative Keys in Transformers
• Approximation theory for 1-Lipschitz ResNets
• Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
• LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
• Evolving Machine Learning: A Survey
• LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
• Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
• MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation
• Understanding the Impact of Sampling Quality in Direct Preference Optimization
• Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning
• Load Balancing Mixture of Experts with Similarity Preserving Routers
• Online Selective Generation with Adversarial Bandit Feedback
• Multi-model Online Conformal Prediction with Graph-Structured Feedback
• Understanding and Improving Length Generalization in Recurrent Models
• On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning
• Robust Causal Discovery in Real-World Time Series with Power-Laws
• Sparse Robust Classification via the Kernel Mean
• Speech Enhancement and Dereverberation with Diffusion-based Generative Models
• When Vision Fails: Text Attacks Against ViT and OCR
• Deep conditional distribution learning via conditional F\"ollmer flow
• Online Auction Design Using Distribution-Free Uncertainty Quantification with Applications to E-Commerce
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
• An Asymptotically Optimal Coordinate Descent Algorithm for Learning Bayesian Networks from Gaussian Models
• Reinforcement learning-based statistical search strategy for an axion model from flavor
• Data-light Uncertainty Set Merging with Admissibility
• Mixing Times and Privacy Analysis for the Projected Langevin Algorithm under a Modulus of Continuity
• Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
• Near-Optimal Real-Time Personalization with Simple Transformers
• Joint Source-Environment Adaptation of Data-Driven Underwater Acoustic Source Ranging Based on Model Uncertainty
• Query Complexity of Classical and Quantum Channel Discrimination
• Provably faster randomized and quantum algorithms for $k$-means clustering via uniform sampling
• One-Stage Top-$k$ Learning-to-Defer: Score-Based Surrogates with Theoretical Guarantees
• Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners
• MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
• When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking Recovery
• Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping
• ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworks
• Re-uploading quantum data: A universal function approximator for quantum inputs
• Dual Perspectives on Non-Contrastive Self-Supervised Learning
• LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
• Knowledge Fusion via Bidirectional Information Aggregation
• StegOT: Trade-offs in Steganography via Optimal Transport
• Heterogeneous Point Set Transformers for Segmentation of Multiple View Particle Detectors
• Assessment of different loss functions for fitting equivalent circuit models to electrochemical impedance spectroscopy data
• LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
• Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning
• Population synthesis with geographic coordinates
• A physics-aware deep learning model for shear band formation around collapsing pores in shocked reactive materials
• Using LLMs to Directly Guess Conditional Expectations Can Improve Efficiency in Causal Estimation
• Neural PDE Solvers with Physics Constraints: A Comparative Study of PINNs, DRM, and WANs
• Operator Learning for Power Systems Simulation
• A Multi-Component Reward Function with Policy Gradient for Automated Feature Selection with Dynamic Regularization and Bias Mitigation
• Federated k-Means via Generalized Total Variation Minimization
• Leveraging Shared Prototypes for a Multimodal Pulse Motion Foundation Model
• HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network
• A Generic Machine Learning Framework for Radio Frequency Fingerprinting
• Combined Representation and Generation with Diffusive State Predictive Information Bottleneck
• Principled Operator Learning in Ocean Dynamics: The Role of Temporal Structure
• A Unified Framework for Lifted Training and Inversion Approaches
• An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
• TAWRMAC: A Novel Dynamic Graph Representation Learning Method
• Understanding Robust Machine Learning for Nonparametric Regression with Heavy-Tailed Noise
• Advancing Intoxication Detection: A Smartwatch-Based Approach
• AutoGD: Automatic Learning Rate Selection for Gradient Descent
• Clustering Result Re-guided Incomplete Multi-view Spectral Clustering
• Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
• An Unsupervised Time Series Anomaly Detection Approach for Efficient Online Process Monitoring of Additive Manufacturing
• Learning Joint Embeddings of Function and Process Call Graphs for Malware Detection
• Tight Robustness Certificates and Wasserstein Distributional Attacks for Deep Neural Networks
• Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification
• Experience-Efficient Model-Free Deep Reinforcement Learning Using Pre-Training
• One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem
• ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
• Rademacher Meets Colors: More Expressivity, but at What Cost ?
• PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
• Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation
• Preference-driven Knowledge Distillation for Few-shot Node Classification
• Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
• Robust Learning of Diffusion Models with Extremely Noisy Conditions
• Hierarchical Bayesian Flow Networks for Molecular Graph Generation
• Progressive Scale Convolutional Network for Spatio-Temporal Downscaling of Soil Moisture: A Case Study Over the Tibetan Plateau
• Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning
• Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs
• Multi-View Graph Learning with Graph-Tuple
• Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker
• Exploration-free Algorithms for Multi-group Mean Estimation
• Applying non-negative matrix factorization with covariates to label matrix for classification
• Softmax $\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent
• Anchor-based Maximum Discrepancy for Relative Similarity Testing
• Gradient Enhanced Self-Training Physics-Informed Neural Network (gST-PINN) for Solving Nonlinear Partial Differential Equations
• A Hybrid Machine Learning Approach for Synthetic Data Generation with Post Hoc Calibration for Clinical Tabular Datasets
• Reinforced Domain Selection for Continuous Domain Adaptation
• Multi-scale Frequency-Aware Adversarial Network for Parkinson's Disease Assessment Using Wearable Sensors
• Multitask Learning with Learned Task Relationships
• Understanding Self-supervised Contrastive Learning through Supervised Objectives
• FusionGen: Feature Fusion-Based Few-Shot EEG Data Generation
• Budget Allocation for Unknown Value Functions in a Lipschitz Space
• Encoder Decoder Generative Adversarial Network Model for Stock Market Prediction
• SDG-L: A Semiparametric Deep Gaussian Process based Framework for Battery Capacity Prediction
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
• Digital Twin-enabled Multi-generation Control Co-Design with Deep Reinforcement Learning
• Stock Prediction via a Dual Relation Fusion Network incorporating Static and Dynamic Relations
• Designing ReLU Generative Networks to Enumerate Trees with a Given Tree Edit Distance
• Structure Over Signal: A Globalized Approach to Multi-relational GNNs for Stock Prediction
• Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
• Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage
• Crisis-Aware Regime-Conditioned Diffusion with CVaR Allocation
• Aegis: A Correlation-Based Data Masking Advisor for Data Sharing Ecosystems
• Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion
• A Joint Learning Approach to Hardware Caching and Prefetching
• Quantifying Information Disclosure During Gradient Descent Using Gradient Uniqueness
• Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
• Interpretable Machine Learning for Cognitive Aging: Handling Missing Data and Uncovering Social Determinant
• Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models
• Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors
• Instruction-aware User Embedding via Synergistic Language and Representation Modeling
• Conformal Inference for Time Series over Graphs
• Robust Photoplethysmography Signal Denoising via Mamba Networks
• Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs
• Efficient Edge Test-Time Adaptation via Latent Feature Coordinate Correction
• Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
• Test-Time Adaptation by Causal Trimming
• DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing
• A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB)
• Emergence of hybrid computational dynamics through reinforcement learning
• Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness
• Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models
• Cross-Scale Reservoir Computing for large spatio-temporal forecasting and modeling
• Enforcing convex constraints in Graph Neural Networks
• Neural Weight Compression for Language Models
• Learning the Structure of Connection Graphs
• FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization
• MIEO: encoding clinical data to enhance cardiovascular event prediction
• FedLoRA-Optimizer: Federated LoRA Fine-Tuning with Global and Local Optimization in Heterogeneous Data Scenarios
• Vision-LLMs for Spatiotemporal Traffic Forecasting
• Gym-TORAX: Open-source software for integrating RL with plasma control simulators
• DiffStyleTS: Diffusion Model for Style Transfer in Time Series
• FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management
• Leveraging LLMs for Semi-Automatic Corpus Filtration in Systematic Literature Reviews
• Differentiable Fast Top-K Selection for Large-Scale Recommendation
• Rescaling-Aware Training for Efficient Deployment of Deep Learning Models on Full-Integer Hardware
• How Reinforcement Learning After Next-Token Prediction Facilitates Learning
• Context-Aware Model-Based Reinforcement Learning for Autonomous Racing
• Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
• Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest
• Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
• Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization
• An Eulerian Perspective on Straight-Line Sampling
• Chronologically Consistent Generative AI
• Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
• Reinforced sequential Monte Carlo for amortised sampling
• Risk-Calibrated Bayesian Streaming Intrusion Detection with SRE-Aligned Decisions
• Performance of Machine Learning Methods for Gravity Inversion: Successes and Challenges
• AdaptAuth: Multi-Layered Behavioral and Credential Analysis for a Secure and Adaptive Authentication Framework for Password Security
• Distributed clustering in partially overlapping feature spaces
• Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation
• Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective
• Egocentric Visual Navigation through Hippocampal Sequences
• Calibrating Generative Models
• Improving Speech Emotion Recognition with Mutual Information Regularized Generative Model
• The Hybrid Multimodal Graph Index (HMGI): A Comprehensive Framework for Integrated Relational and Vector Search
• BrainForm: a Serious Game for BCI Training and Data Collection
• Enhancing Neural Code Representation with Additional Context
• An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations
• Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models
• Chimera: State Space Models Beyond Sequences
• Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
• SafeMT: Multi-turn Safety for Multimodal Language Models
• Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
• Budget-constrained Active Learning to Effectively De-censor Survival Data
• From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
• CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
• Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
• DE3S: Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classification
• HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment
• Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
• MoRA: On-the-fly Molecule-aware Low-Rank Adaptation Framework for LLM-based Multi-Modal Molecular Assistant
• PromptLocate: Localizing Prompt Injection Attacks
• Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development
• Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
• Human-in-the-Loop Bandwidth Estimation for Quality of Experience Optimization in Real-Time Video Communication
• HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
• TFGA-Net: Temporal-Frequency Graph Attention Network for Brain-Controlled Speaker Extraction
• Quantum Annealing for Staff Scheduling in Educational Environments
• Chinese ModernBERT with Whole-Word Masking
• Deep SPI: Safe Policy Improvement via World Models
• Causal Inspired Multi Modal Recommendation
• Simple Projection Variants Improve ColBERT Performance
• Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
• (R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm
• LLM-REVal: Can We Trust LLM Reviewers Yet?
• Deep Attention-guided Adaptive Subsampling
• LiteVPNet: A Lightweight Network for Video Encoding Control in Quality-Critical Applications
• Phenome-Wide Multi-Omics Integration Uncovers Distinct Archetypes of Human Aging
• Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
• Low-Field Magnetic Resonance Image Quality Enhancement using a Conditional Flow Matching Model
• A Function Centric Perspective On Flat and Sharp Minima
• When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
• A Text-Image Fusion Method with Data Augmentation Capabilities for Referring Medical Image Segmentation
• PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
• The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
• BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)
• Unconditional Human Motion and Shape Generation via Balanced Score-Based Diffusion
• Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
• Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
• SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
• StyleDecipher: Robust and Explainable Detection of LLM-Generated Texts with Stylistic Analysis
• Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
• Learning-To-Measure: In-context Active Feature Acquisition
• Designing Tools with Control Confidence
• Laminar: A Scalable Asynchronous RL Post-Training Framework
• Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis
• Reasoning Pattern Matters: Learning to Reason without Human Rationales
• SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
• Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
• From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
• DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
• Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition
• Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
• Topological Signatures of ReLU Neural Network Activation Patterns
• Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?
• Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
• Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
• Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies
• Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems
• HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictions
• Hey, wait a minute: on at-issue sensitivity in Language Models
• VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage
• Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective
• Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction
• Dr.LLM: Dynamic Layer Routing in LLMs
• MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
• UniFusion: Vision-Language Model as Unified Encoder in Image Generation
• CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• Causal Agent based on Large Language Model
• Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance
• Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design
• Constrained Identifiability of Causal Effects
• The Philosophical Foundations of Growing AI Like A Child
• Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
• Open and Sustainable AI: challenges, opportunities and the road ahead in the life sciences (October 2025 -- Version 2)
• EgoBrain: Synergizing Minds and Eyes For Human Action Understanding
• Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning
• MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration
• Similarity Field Theory: A Mathematical Framework for Intelligence
• Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption
• Can ChatGPT support software verification?
• Offline Fictitious Self-Play for Competitive Games
• ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
• Assessing Latency in ASR Systems: A Methodological Perspective for Real-Time Use
• Generative AI for Requirements Engineering: A Systematic Literature Review
• COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
• Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds
• Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation
• CiteBART: Learning to Generate Citations for Local Citation Recommendation
• Polynomial-Time Algorithms for Fair Orientations of Chores
• GraphRAG under Fire
• AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
• Query Brand Entity Linking in E-Commerce Search
• ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
• FOCUS on Contamination: A Geospatial Deep Learning Framework with a Noise-Aware Loss for Surface Water PFAS Prediction
• Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances
• A Customized SAT-based Solver for Graph Coloring
• MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation
• Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
• Fixed Point Explainability
• Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
• AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
• Steering Large Language Models for Machine Translation Personalization
• Protein Design with Dynamic Protein Vocabulary
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
• Can LLMs Reason Structurally? An Evaluation via the Lens of Data Structures
• EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
• Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
• BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
• Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series
• SPADE: Spatial Transcriptomics and Pathology Alignment Using a Mixture of Data Experts for an Expressive Latent Space
• Inverse Design in Nanophotonics via Representation Learning
• SAFER: Probing Safety in Reward Models with Sparse Autoencoder
• AI Agents for the Dhumbal Card Game: A Comparative Study
• Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
• CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research
• Asking Clarifying Questions for Preference Elicitation With Large Language Models
• CausalTrace: A Neurosymbolic Causal Analysis Agent for Smart Manufacturing
• Do Large Language Models Respect Contracts? Evaluating and Enforcing Contract-Adherence in Code Generation
• Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response
• ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
• AI Agents as Universal Task Solvers
• HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory
• EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
• BeSTAD: Behavior-Aware Spatio-Temporal Anomaly Detection for Human Mobility Data
• Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models
• One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
• ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations
• Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
• MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
• Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
• ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
• On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy
• GOAT: A Training Framework for Goal-Oriented Agent with Tools
• MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
• PromptFlow: Training Prompts Like Neural Networks
• $\mathbf{T^3}$: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
• Tensor Logic: The Language of AI
• RAG-Anything: All-in-One RAG Framework
• O-Forge: An LLM + Computer Algebra Framework for Asymptotic Analysis
• A Survey of Vibe Coding with Large Language Models
• PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
• MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamics
• Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized Intersections
• Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
• Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews
• Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation
• ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
• Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings
• HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
• Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
• ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
• Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
• CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
• Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
• Clutch Control: An Attention-based Combinatorial Bandit for Efficient Mutation in JavaScript Engine Fuzzing
• CTRL-Rec: Controlling Recommender Systems With Natural Language
• Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
• Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring
• Modeling Hypergraph Using Large Language Models
• Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
• Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
• SeeingSounds: Learning Audio-to-Visual Alignment via Text
• Celebrity Profiling on Short Urdu Text using Twitter Followers' Feed
• Fast and Interpretable Protein Substructure Alignment via Optimal Transport
• Zero-Shot Large Language Model Agents for Fully Automated Radiotherapy Treatment Planning
• Artificial Intelligence for Optimal Learning: A Comparative Approach towards AI-Enhanced Learning Environments
• The Adoption Paradox: A Comparative Analysis of Veterinary AI Adoption in China and the North America
• AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
• Audio-Guided Visual Perception for Audio-Visual Navigation
• GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
• PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
• BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
• Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detection
• Data or Language Supervision: What Makes CLIP Better than DINO?
• Countermind: A Multi-Layered Security Architecture for Large Language Models
• MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
• Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks
• Indoor Localization using Compact, Telemetry-Agnostic, Transfer-Learning Enabled Decoder-Only Transformer
• Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering
• TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition
• Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
• Y-shaped Generative Flows
• Direct Multi-Token Decoding
• CTIArena: Benchmarking LLM Knowledge and Reasoning Across Heterogeneous Cyber Threat Intelligence
• Learning Dynamics of VLM Finetuning
• Conjecturing: An Overlooked Step in Formal Mathematical Reasoning
• PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation
• CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
• Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models
• Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models
• Generative AI and Firm Productivity: Field Experiments in Online Retail
• APCE: Adaptive Progressive Context Expansion for Long Context Processing
• Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
• MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging
• A Review on Domain Adaption and Generative Adversarial Networks(GANs)