AI Research News Feeds for September 12th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs
• Symmetry-Guided Multi-Agent Inverse Reinforcement Learning
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty
• UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
• SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification
• Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks
• ABS-Mamba: SAM2-Driven Bidirectional Spiral Mamba Network for Medical Image Translation
• Spec2VolCAMU-Net: A Spectrogram-to-Volume Model for EEG-to-fMRI Reconstruction based on Multi-directional Time-Frequency Convolutional Attention Encoder and Vision-Mamba U-Net
• C3VDv2 -- Colonoscopy 3D video dataset with enhanced realism
• SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model
• Dynamic Structural Recovery Parameters Enhance Prediction of Visual Outcomes After Macular Hole Surgery
• In-Loop Filtering Using Learned Look-Up Tables for Video Coding
• Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration
• Total Disentanglement of Font Images into Style and Character Class Features
• Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods
• Attention-Guided Multi-scale Interaction Network for Face Super-Resolution
• The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods
• ForestSplats: Deformable transient field for Gaussian Splatting in the Wild
• GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
• AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systems
• TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization
• An Improved U-Net Model for Offline handwriting signature denoising
• JAX-IK: Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters
• GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving
• A Fully Automatic Framework for Intracranial Pressure Grading: Integrating Keyframe Identification, ONSD Measurement and Clinical Data
• Unsupervised Integrated-Circuit Defect Segmentation via Image-Intrinsic Normality
• Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift
• FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution
• FlexiD-Fuse: Flexible number of inputs multi-modal medical image fusion based on diffusion model
• Improving Human Motion Plausibility with Body Momentum
• Region-Wise Correspondence Prediction between Manga Line Art Images
• Generative Diffusion Contrastive Network for Multi-View Clustering
• DualTrack: Sensorless 3D Ultrasound needs Local and Global Context
• InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation
• PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
• Visual Grounding from Event Cameras
• Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
• Measuring Epistemic Humility in Multimodal Large Language Models
• Can Understanding and Generation Truly Benefit Together -- or Just Coexist?
• Geometric Neural Distance Fields for Learning Human Motion Priors
• Locality in Image Diffusion Models Emerges from Data Statistics
• SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
• DeepTV: A neural network approach for total variation minimization
• CameraVDP: Perceptual Display Assessment with Uncertainty Estimation via Camera and Visual Difference Prediction
• Ultrafast Deep Learning-Based Scatter Estimation in Cone-Beam Computed Tomography
• Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention
• Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
• ALL-PET: A Low-resource and Low-shot PET Foundation Model in the Projection Domain
• Noise-Robust Topology Estimation of 2D Image Data via Neural Networks and Persistent Homology
• RT-DETR++ for UAV Object Detection
• CWSSNet: Hyperspectral Image Classification Enhanced by Wavelet Domain Convolution
• Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios
• VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
• MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network
• Medverse: A Universal Model for Full-Resolution 3D Medical Image Segmentation, Transformation and Enhancement
• Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis
• DATE: Dynamic Absolute Time Enhancement for Long Video Understanding
• Unified Start, Personalized End: Progressive Pruning for Efficient 3D Medical Image Segmentation
• Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
• Learning Object-Centric Representations in SAR Images with Multi-Level Feature Fusion
• You Share Beliefs, I Adapt: Progressive Heterogeneous Collaborative Perception
• Image Recognition with Vision and Language Embeddings of VLMs
• Fine-Grained Customized Fashion Design with Image-into-Prompt benchmark and dataset from LMM
• Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
• Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection
• Diffusion-Based Action Recognition Generalizes to Untrained Domains
• SFD-Mamba2Net: Strcture-Guided Frequency-Enhanced Dual-Stream Mamba2 Network for Coronary Artery Segmentation
• Live(r) Die: Predicting Survival in Colorectal Liver Metastasis
• Discovering Divergent Representations between Text-to-Image Models
• An U-Net-Based Deep Neural Network for Cloud Shadow and Sun-Glint Correction of Unmanned Aerial System (UAS) Imagery
• CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
• iMatcher: Improve matching in point cloud registration via local-to-global geometric consistency learning
• UltrON: Ultrasound Occupancy Networks
• E-MLNet: Enhanced Mutual Learning for Universal Domain Adaptation with Sample-Specific Weighting
• VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI
• Integrating Anatomical Priors into a Causal Diffusion Model
• Enhancing 3D Medical Image Understanding with Pretraining Aided by 2D Multimodal Large Language Models
• Improvement of Human-Object Interaction Action Recognition Using Scene Information and Multi-Task Learning Approach
• IRDFusion: Iterative Relation-Map Difference guided Feature Fusion for Multispectral Object Detection
• S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localization
• FPI-Det: a face--phone Interaction Dataset for phone-use detection and understanding
• Prompting the Market? A Large-Scale Meta-Analysis of GenAI in Finance NLP (2022-2025)
• LAVA: Language Model Assisted Verbal Autopsy for Cause-of-Death Determination
• Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
• All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens
• Generative Engine Optimization: How to Dominate AI Search
• COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation
• DiFlow-TTS: Discrete Flow Matching with Factorized Speech Tokens for Low-Latency Zero-Shot Text-To-Speech
• FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
• ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts
• Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving
• CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering
• Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability
• Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese
• Uncertainty Quantification in Retrieval Augmented Question Answering
• CritiQ: Mining Data Quality Criteria from Human Preferences
• AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models
• A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions
• The NTNU System at the S&I Challenge 2025 SLA Open Track
• ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding
• Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC
• Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach
• Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings
• BRoverbs -- Measuring how much LLMs understand Portuguese proverbs
• MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction
• TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla
• Compass-v3: Scaling Domain-Specific LLMs for Multilingual E-Commerce in Southeast Asia
• LITcoder: A General-Purpose Library for Building and Comparing Encoding Models
• GmSLM : Generative Marmoset Spoken Language Modeling
• CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling
• Reading Between the Lines: Classifying Resume Seniority with Large Language Models
• Agentic LLMs for Question Answering over Tabular Data
• From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models
• MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems
• Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Research
• Hierarchical Bracketing Encodings Work for Dependency Graphs
• GrACE: A Generative Approach to Better Confidence Elicitation in Large Language Models
• Mitigating Language Barriers in Education: Developing Multilingual Digital Learning Materials with Machine Translation
• SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models
• Scalable Evaluation of Online Facilitation Strategies via Synthetic Simulation of Discussions
• Harmonia: A Multi-Agent Reinforcement Learning Approach to Data Placement and Migration in Hybrid Storage Systems
• Quantum-Assisted Machine Learning Models for Enhanced Weather Prediction
• ACE: A Security Architecture for LLM-Integrated App Systems
• Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models
• Self-Optimizing Machine Learning Potential Assisted Automated Workflow for Highly Efficient Complex Systems Material Design
• Inferring entropy production in many-body systems using nonequilibrium MaxEnt
• Modular Jump Gaussian Processes
• Efficient Optimization Accelerator Framework for Multistate Ising Problems
• A User-Centric, Privacy-Preserving, and Verifiable Ecosystem for Personal Data Management and Utilization
• Bridging Simplicity and Sophistication using GLinear: A Novel Architecture for Enhanced Time Series Prediction
• Investigating Energy Efficiency and Performance Trade-offs in LLM Inference Across Tasks and DVFS Settings
• Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
• Revisiting Non-Acyclic GFlowNets in Discrete Environments
• Adaptive kernel predictors from feature-learning infinite limits of neural networks
• MOLLM: Multi-Objective Large Language Model for Molecular Design -- Optimizing with Experts
• A Vector-Quantized Foundation Model for Patient Behavior Monitoring
• Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations
• Convergence Analysis of Asynchronous Federated Learning with Gradient Compression for Non-Convex Optimization
• Temporal Query Network for Efficient Multivariate Time Series Forecasting
• Towards Robust Influence Functions with Flat Validation Minima
• Development and Comparative Evaluation of Three Artificial Intelligence Models (NLP, LLM, JEPA) for Predicting Triage in Emergency Departments: A 7-Month Retrospective Proof-of-Concept
• DivMerge: A divergence-based model merging method for multi-tasking
• Iterative Methods for Full-Scale Gaussian Process Approximations for Large Spatial Data
• Sigma Flows for Image and Data Labeling and Learning Structured Prediction
• Examining Different Research Communities: Authorship Network
• Average Causal Effect Estimation in DAGs with Hidden Variables: Beyond Back-Door and Front-Door Criteria
• Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions
• Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
• Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination
• Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception
• Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
• Low-degree lower bounds via almost orthonormal bases
• Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
• Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
• Semantic Concentration for Self-Supervised Dense Representations Learning
• Database Views as Explanations for Relational Deep Learning
• DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
• Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates
• What Does Normal Even Mean? Evaluating Benign Traffic in Intrusion Detection Datasets
• Personality-Enhanced Social Recommendations in SAMI: Exploring the Role of Personality Detection in Matchmaking
• Steering MoE LLMs via Expert (De)Activation
• On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Networks
• Geometry and Stability of Supervised Learning Problems
• Attribution Regularization for Multimodal Paradigms
• AdaWaveNet: Adaptive Wavelet Network for Time Series Analysis
• Unveiling Multiple Descents in Unsupervised Autoencoders
• Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices
• Tensor-Based Foundations of Ordinary Least Squares and Neural Network Regression Models
• Communication Compression for Distributed Learning without Control Variates
• AquaCast: Urban Water Dynamics Forecasting with Precipitation-Informed Multi-Input Transformer
• AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings
• CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
• Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
• PIPES: A Meta-dataset of Machine Learning Pipelines
• Cough Classification using Few-Shot Learning
• ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning
• Conditioning on PDE Parameters to Generalise Deep Learning Emulation of Stochastic and Chaotic Dynamics
• ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
• Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
• A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals
• Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation
• WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
• Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities
• Convexity of Optimization Curves: Local Sharp Thresholds, Robustness Impossibility, and New Counterexamples
• Physics-informed waveform inversion using pretrained wavefield neural operators
• Generative quantum advantage for classical and quantum problems
• The Role of Community Detection Methods in Performance Variations of Graph Mining Tasks
• Scalable extensions to given-data Sobol' index estimators
• CryptGNN: Enabling Secure Inference for Graph Neural Networks
• Global Optimization of Stochastic Black-Box Functions with Arbitrary Noise Distributions using Wilson Score Kernel Density Estimation
• Value bounds and Convergence Analysis for Averages of LRP attributions
• Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
• Active Learning and Explainable AI for Multi-Objective Optimization of Spin Coated Polymers
• Fast attention mechanisms: a tale of parallelism
• Deep Context-Conditioned Anomaly Detection for Tabular Data
• "A 6 or a 9?": Ensemble Learning Through the Multiplicity of Performant Models and Explanations
• An entropy formula for the Deep Linear Network
• Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models
• Learning What Matters: Causal Time Series Modeling for Arctic Sea Ice Prediction
• Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
• Peering Partner Recommendation for ISPs using Machine Learning
• Quantum Machine Learning, Quantitative Trading, Reinforcement Learning, Deep Learning
• Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL
• Breaking the Statistical Similarity Trap in Extreme Convection Detection
• Identifying Key Features for Establishing Sustainable Agro-Tourism Centre: A Data Driven Approach
• Constructing a Question-Answering Simulator through the Distillation of LLMs
• Unsupervised Multi-Attention Meta Transformer for Rotating Machinery Fault Diagnosis
• Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
• Data Driven Discovery of Emergent Dynamics in Reaction Diffusion Systems from Sparse and Noisy Observations
• Kriging prior Regression: A Case for Kriging-Based Spatial Features with TabPFN in Soil Mapping
• Fused Lasso Improves Accuracy of Co-occurrence Network Inference in Grouped Samples
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
• LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applications
• TinyDef-DETR: A DETR-based Framework for Defect Detection in Transmission Lines from UAV Imagery
• On Synthesis of Timed Regular Expressions
• Beyond the Pre-Service Horizon: Infusing In-Service Behavior for Improved Financial Risk Forecasting
• Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
• Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards
• Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
• Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty
• FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis
• Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation
• Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review
• Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization
• Combating Falsification of Speech Videos with Live Optical Signatures (Extended Version)
• MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
• Diffusion Graph Neural Networks for Robustness in Olfaction Sensors and Datasets
• Crack Path Prediction with Operator Learning using Discrete Particle System data Generation
• Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict
• Persistent Homology of Topic Networks for the Prediction of Reader Curiosity
• Uncertainty Estimation by Human Perception versus Neural Models
• Uncertainty-aware Diffusion and Reinforcement Learning for Joint Plane Localization and Anomaly Diagnosis in 3D Ultrasound
• Can Large Language Models Understand As Well As Apply Patent Regulations to Pass a Hands-On Patent Attorney Test?
• TreeGPT: Pure TreeFFN Encoder-Decoder Architecture for Structured Reasoning Without Attention Mechanisms
• CogGuide: Human-Like Guidance for Zero-Shot Omni-Modal Reasoning
• Inconsistency Handling in Prioritized Databases with Universal Constraints: Complexity Analysis and Links with Active Integrity Constraints
• Deep Reinforcement Learning for Inventory Networks: Toward Reliable Policy Optimization
• A minimal coalition logic
• Algorithmic Collusion by Large Language Models
• Semantic Augmentation in Images using Language
• Discovering physical laws with parallel symbolic enumeration
• Rethinking Disentanglement under Dependent Factors of Variation
• DeepVoting: Learning and Fine-Tuning Voting Rules with Canonical Embeddings
• RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
• MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond
• Knowledge-Guided Biomarker Identification for Label-Free Single-Cell RNA-Seq Data: A Reinforcement Learning Perspective
• EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds
• V-HOP: Visuo-Haptic 6D Object Pose Tracking
• MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue
• VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification
• Byzantine-Robust Federated Learning Using Generative Adversarial Networks
• SWI: Speaking with Intent in Large Language Models
• Entropy-Gated Branching for Efficient Test-Time Reasoning
• KROMA: Ontology Matching with Knowledge Retrieval and Large Language Models
• Robix: A Unified Model for Robot Interaction, Reasoning and Planning
• Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
• An improved educational competition optimizer with multi-covariance learning operators for global optimization problems
• Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification
• Fluent but Unfeeling: The Emotional Blind Spots of Language Models
• ObjectReact: Learning Object-Relative Control for Visual Navigation
• Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
• Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth
• LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering
• Explaining Concept Drift through the Evolution of Group Counterfactuals
• Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations
• Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
• ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
• Enhancing Few-Shot Transfer Learning with Optimized Multi-Task Prompt Tuning through Modular Prompt Composition
• Simulating Human-like Daily Activities with Desire-driven Autonomy
• LLMs for sensory-motor control: Combining in-context and iterative learning
• Optimizing Length Compression in Large Reasoning Models
• Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
• Virtual staining for 3D X-ray histology of bone implants
• CoAtNeXt:An Attention-Enhanced ConvNeXtV2-Transformer Hybrid Model for Gastric Tissue Classification
• Adaptive Knowledge Distillation using a Device-Aware Teacher for Low-Complexity Acoustic Scene Classification
• Modality-Agnostic Input Channels Enable Segmentation of Brain lesions in Multimodal MRI with Sequences Unavailable During Training
• Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization
• OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning
• MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts
• Classification of Driver Behaviour Using External Observation Techniques for Autonomous Vehicles
• Robust Non-Linear Correlations via Polynomial Regression
• MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
• LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
• We're Still Doing It (All) Wrong: Recommender Systems, Fifteen Years Later
• ENSI: Efficient Non-Interactive Secure Inference for Large Language Models
• Resource-Efficient Glioma Segmentation on Sub-Saharan MRI
• Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
• OpenFake: An Open Dataset and Platform Toward Large-Scale Deepfake Detection
• Incorporating AI Incident Reporting into Telecommunications Law and Policy: Insights from India
• Explainable AI for Accelerated Microstructure Imaging: A SHAP-Guided Protocol on the Connectome 2.0 scanner
• Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs
• A modified RIME algorithm with covariance learning and diversity enhancement for numerical optimization
• KoopMotion: Learning Almost Divergence Free Koopman Flow Fields for Motion Planning
• SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
• Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
• DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models
• Character-Level Perturbations Disrupt LLM Watermarks
• Automated Classification of Tutors' Dialogue Acts Using Generative AI: A Case Study Using the CIMA Corpus
• ViRanker: A BGE-M3 & Blockwise Parallel Transformer Cross-Encoder for Vietnamese Reranking
• Objectness Similarity: Capturing Object-Level Fidelity in 3D Scene Evaluation
• Video Understanding by Design: How Datasets Shape Architectures and Insights
• OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge
• HISPASpoof: A New Dataset For Spanish Speech Forensics
• A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering
• Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing
• Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication
• EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
• Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
• Probing Pre-trained Language Models on Code Changes: Insights from ReDef, a High-Confidence Just-in-Time Defect Prediction Dataset
• On Integrating Large Language Models and Scenario-Based Programming for Improving Software Reliability
• Efficient Trie-based Biasing using K-step Prediction for Rare Word Recognition
• Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function
• Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems
• Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
• Deep opacity and AI: A threat to XAI and to privacy protection mechanisms
• Uncertainty Estimation using Variance-Gated Distributions
• Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned
• A vibe coding learning design to enhance EFL students' talking to, through, and about AI
• Multi Robot Coordination in Highly Dynamic Environments: Tackling Asymmetric Obstacles and Limited Communication
• Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses
• Benchmarking Energy Efficiency of Large Language Models Using vLLM
• Recurrence Meets Transformers for Universal Multimodal Retrieval
• PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability
• Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications
• Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
• Implicit Neural Representations of Intramyocardial Motion and Strain
• Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison
• Can Vision-Language Models Solve Visual Math Equations?
• Personalized Sleep Prediction via Deep Adaptive Spatiotemporal Modeling and Sparse Data
• Envy-Free but Still Unfair: Envy-Freeness Up To One Item (EF-1) in Personalized Recommendation
• Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation
• MoWE : A Mixture of Weather Experts
• A Scoping Review of Machine Learning Applications in Power System Protection and Disturbance Management
• Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M
• STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
• Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
• Understanding Economic Tradeoffs Between Human and AI Agents in Bargaining Games
• Anti-Money Laundering Machine Learning Pipelines; A Technical Analysis on Identifying High-risk Bank Clients with Supervised Learning
• Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
• ProgD: Progressive Multi-scale Decoding with Dynamic Graphs for Joint Multi-agent Motion Forecasting
• Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions
• Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
• Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
• Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
• LightAgent: Production-level Open-source Agentic AI Framework
• Explaining Tournament Solutions with Minimal Supports
• Measuring Implicit Spatial Coordination in Teams: Effects on Collective Intelligence and Performance
• Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization
• Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
• TORSO: Template-Oriented Reasoning Towards General Tasks
• Inteligencia Artificial jur\'idica y el desaf\'io de la veracidad: an\'alisis de alucinaciones, optimizaci\'on de RAG y principios para una integraci\'on responsable
• SEDM: Scalable Self-Evolving Distributed Memory for Agents
• Compositional Concept Generalization with Variational Quantum Circuits
• Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution
• The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
• PerFairX: Is There a Balance Between Fairness and Personality in Large Language Model Recommendations?
• An Interval Type-2 Version of Bayes Theorem Derived from Interval Probability Range Estimates Provided by Subject Matter Experts
• Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs
• Global Constraint LLM Agents for Text-to-Model Translation
• ForTIFAI: Fending Off Recursive Training Induced Failure for AI Models
• Uncertainty Awareness and Trust in Explainable AI- On Trust Calibration using Local and Global Explanations