AI Research News Feeds for September 19th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• The Why and How of Convex Clustering
• Variational Gaussian Approximation in Replica Analysis of Parametric Models
• Rate doubly robust estimation for weighted average treatment effects
• Semiparametric Learning from Open-Set Label Shift Data
• Consistent causal discovery with equal error variances: a least-squares perspective
• Gap-Dependent Bounds for Federated $Q$-learning
• Sharp Matrix Empirical Bernstein Inequalities
• Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
• Efficient Dual-domain Image Dehazing with Haze Prior Perception
• Skeleton-based sign language recognition using a dual-stream spatio-temporal dynamic graph convolutional network
• MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields
• GCDance: Genre-Controlled 3D Full Body Dance Generation Driven By Music
• HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement
• GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation
• On the Role of Individual Differences in Current Approaches to Computational Image Aesthetics
• BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports
• Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalities
• PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution
• Erased or Dormant? Rethinking Concept Erasure Through Reversibility
• Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation
• OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
• Fovea Stacking: Imaging with Dynamic Localized Aberration Correction
• Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
• Multi-label Scene Classification for Autonomous Vehicles: Acquiring and Accumulating Knowledge from Diverse Datasets
• Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
• Domain Generalization for In-Orbit 6D Pose Estimation
• Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models
• Standardizing Generative Face Video Compression using Supplemental Enhancement Information
• Gradient Distance Function
• Morph: A Motion-free Physics Optimization Framework for Human Motion Generation
• Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration
• A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation
• Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction
• Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
• ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
• Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation
• Lost in Translation? Vocabulary Alignment for Source-Free Domain Adaptation in Open-Vocabulary Semantic Segmentation
• Calibration-Aware Prompt Learning for Medical Vision-Language Models
• RLBind: Adversarial-Invariant Cross-Modal Alignment for Unified Robust Embeddings
• QuizRank: Picking Images by Quizzing VLMs
• Doppler Radiance Field-Guided Antenna Selection for Improved Generalization in Multi-Antenna Wi-Fi-based Human Activity Recognition
• From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
• Two Web Toolkits for Multimodal Piano Performance Dataset Acquisition and Fingering Annotation
• Interactive Face Video Coding: A Generative Compression Framework
• Image Super-Resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features
• AutoEdit: Automatic Hyperparameter Tuning for Image Editing
• Transplant-Ready? Evaluating AI Lung Segmentation Models in Candidates with Severe Lung Disease
• OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
• RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
• MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation
• A Race Bias Free Face Aging Model for Reliable Kinship Verification
• Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
• Maize Seedling Detection Dataset (MSDD): A Curated High-Resolution RGB Dataset for Seedling Maize Detection and Benchmarking with YOLOv9, YOLO11, YOLOv12 and Faster-RCNN
• Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
• Geometric Image Synchronization with Deep Watermarking
• RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
• Pseudo-Label Enhanced Cascaded Framework: 2nd Technical Report for LSVOS 2025 VOS Track
• Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications
• GenKOL: Modular Generative AI Framework For Scalable Virtual KOL Generation
• DF-LLaVA: Unlocking MLLM's potential for Synthetic Image Detection via Prompt-Guided Knowledge Injection
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification
• Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
• Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoders
• EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
• SPATIALGEN: Layout-guided 3D Indoor Scene Generation
• PRISM: Product Retrieval In Shopping Carts using Hybrid Matching
• UCorr: Wire Detection and Depth Estimation for Autonomous Drones
• No Modality Left Behind: Adapting to Missing Modalities via Knowledge Distillation for Brain Tumor Segmentation
• DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Images
• FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction
• Chain-of-Thought Re-ranking for Image Retrieval Tasks
• Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks
• A Real-Time Multi-Model Parametric Representation of Point Clouds
• Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models
• Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model
• Fracture interactive geodesic active contours for bone segmentation
• MapAnything: Mapping Urban Assets using Single Street-View Images
• Controllable Localized Face Anonymization Via Diffusion Inpainting
• Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer
• NeRF-based Visualization of 3D Cues Supporting Data-Driven Spacecraft Pose Estimation
• Attention Lattice Adapter: Visual Explanation Generation for Visual Foundation Model
• MemEvo: Memory-Evolving Incremental Multi-view Clustering
• Edge-Aware Normalized Attention for Efficient and Detail-Preserving Single Image Super-Resolution
• Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
• DiffVL: Diffusion-Based Visual Localization on 2D Maps via BEV-Conditioned GPS Denoising
• DICE: Diffusion Consensus Equilibrium for Sparse-view CT Reconstruction
• Domain Adaptation for Ulcerative Colitis Severity Estimation Using Patient-Level Diagnoses
• Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression
• HybridMamba: A Dual-domain Mamba for 3D Medical Image Segmentation
• Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections
• MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
• Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signals
• FunAudio-ASR Technical Report
• Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications
• Synaptic Theory of Chunking in Working Memory
• Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
• GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search
• Dense Video Understanding with Gated Residual Tokenization
• Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
• MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation
• Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge
• MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs
• WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
• Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
• mdok of KInIT: Robustly Fine-tuned LLM for Binary and Multiclass AI-Generated Text Detection
• ImpRAG: Retrieval-Augmented Generation with Implicit Queries
• SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction
• FCPE: A Fast Context-based Pitch Estimation Model
• AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt
• An Evaluation-Centric Paradigm for Scientific Visualization Agents
• The Art of Storytelling: Multi-Agent Generative AI for Dynamic Multimodal Narratives
• FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning
• RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs
• Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE
• Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs
• Single- vs. Dual-Prompt Dialogue Generation with LLMs for Job Interviews in Human Resources
• Unsupervised Concept Vector Extraction for Bias Control in LLMs
• CARE: Multilingual Human Preference Learning for Cultural Awareness
• Extracting memorized pieces of (copyrighted) books from open-weight language models
• LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models
• Large Language Model probabilities cannot distinguish between possible and impossible language
• A1: Asynchronous Test-Time Scaling via Conformal Prediction
• Fair-GPTQ: Bias-Aware Quantization for Large Language Models
• What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques
• Assessing Historical Structural Oppression Worldwide via Rule-Guided Prompting of Large Language Models
• LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models
• A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
• Frame Sampling Strategies Matter: A Benchmark for small vision language models
• SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding
• SINAI at eRisk@CLEF 2023: Approaching Early Detection of Gambling with Natural Language Processing
• SINAI at eRisk@CLEF 2022: Approaching Early Detection of Gambling and Eating Disorders with Natural Language Processing
• ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance
• LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring
• V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
• Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens
• FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
• A Comparative Evaluation of Large Language Models for Persian Sentiment Analysis and Emotion Detection in Social Media Texts
• Explicit vs. Implicit Biographies: Evaluating and Adapting LLM Information Extraction on Wikidata-Derived Texts
• Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
• Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
• Can maiBERT Speak for Maithili?
• Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models
• Leveraging IndoBERT and DistilBERT for Indonesian Emotion Classification in E-Commerce Reviews
• SWE-QA: Can Language Models Answer Repository-level Code Questions?
• UMA-Split: unimodal aggregation for both English and Mandarin non-autoregressive speech recognition
• HARNESS: Lightweight Distilled Arabic Speech Foundation Models
• From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse
• Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM
• UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
• Evaluating Large Language Models for Cross-Lingual Retrieval
• KAIO: A Collection of More Challenging Korean Questions
• Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration
• Persuasive or Neutral? A Field Experiment on Generative AI in Online Travel Planning
• Refining Syntactic Distinctions Using Decision Trees: A Paper on Postnominal 'That' in Complement vs. Relative Clauses
• Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing
• Predicting Antibiotic Resistance Patterns Using Sentence-BERT: A Machine Learning Approach
• Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models
• Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings
• Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
• Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss
• Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation
• Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification
• From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models
• Controlling Language Difficulty in Dialogues with Linguistic Features
• Tokenization Strategies for Low-Resource Agglutinative Languages in Word2Vec: Case Study on Turkish and Finnish
• The meaning of prompts and the prompts of meaning: Semiotic reflections and modelling
• Cloud-Edge Collaborative Data Anomaly Detection in Industrial Sensor Networks
• Mixture of Multicenter Experts in Multimodal AI for Debiased Radiotherapy Target Delineation
• Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning
• General Geospatial Inference with a Population Dynamics Foundation Model
• Robust Reinforcement Learning under Diffusion Models for Data with Jumps
• Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning
• Deep Learning Agents Trained For Avoidance Behave Like Hawks And Doves
• An Empirical Study of Federated Prompt Learning for Vision Language Model
• Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidance
• BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings
• Synthetic-to-Real Object Detection using YOLOv11 and Domain Randomization Strategies
• Real-Time Streaming Mel Vocoding with Generative Flow Matching
• Shedding Light on Dark Matter at the LHC with Machine Learning
• Asymptotic Study of In-context Learning with Random Transformers through Equivalent Models
• AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Use
• Class-invariant Test-Time Augmentation for Domain Generalization
• Indoor Airflow Imaging Using Physics-Informed Background-Oriented Schlieren Tomography
• Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
• Data coarse graining can improve model performance
• Radiolunadiff: Estimation of wireless network signal strength in lunar terrain
• LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning
• Designing Latent Safety Filters using Pre-Trained Vision Models
• Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution
• Beyond Spherical geometry: Unraveling complex features of objects orbiting around stars from its transit light curve using deep learning
• CARGO: A Framework for Confidence-Aware Routing of Large Language Models
• Inspired by machine learning optimization: can gradient-based optimizers solve cycle skipping in full waveform inversion given sufficient iterations?
• MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration
• Explaining deep learning for ECG using time-localized clusters
• CausalPre: Scalable and Effective Data Pre-processing for Causal Fairness
• Artificial Intelligence-derived Cardiotocography Age as a Digital Biomarker for Predicting Future Adverse Pregnancy Outcomes
• Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches
• Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
• A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
• Monitoring Machine Learning Systems: A Multivocal Literature Review
• SpeechOp: Inference-Time Task Composition for Generative Speech Processing
• Diffusion-Based Unsupervised Audio-Visual Speech Separation in Noisy Environments with Noise Prior
• Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models
• Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
• Emergent Alignment via Competition
• The Energy-Efficient Hierarchical Neural Network with Fast FPGA-Based Incremental Learning
• Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
• Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges
• TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference
• Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
• Self-Improving Embodied Foundation Models
• Precision Neural Networks: Joint Graph And Relational Learning
• Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization
• Leveraging Reinforcement Learning, Genetic Algorithms and Transformers for background determination in particle physics
• Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation
• A Comparative Analysis of Transformer Models in Social Bot Detection
• Data-Driven Prediction of Maternal Nutritional Status in Ethiopia Using Ensemble Machine Learning Models
• Stochastic Bilevel Optimization with Heavy-Tailed Noise
• FAWN: A MultiEncoder Fusion-Attention Wave Network for Integrated Sensing and Communication Indoor Scene Inference
• Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
• Evidential Physics-Informed Neural Networks for Scientific Discovery
• Online reinforcement learning via sparse Gaussian mixture model Q-functions
• DyWPE: Signal-Aware Dynamic Wavelet Positional Encoding for Time Series Transformers
• Towards Pre-trained Graph Condensation via Optimal Transport
• Transcoder-based Circuit Analysis for Interpretable Single-Cell Foundation Models
• Pre-training under infinite compute
• STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction models
• A Neural Network for the Identical Kuramoto Equation: Architectural Considerations and Performance Evaluation
• Hashing-Baseline: Rethinking Hashing in the Age of Pretrained Models
• FedAVOT: Exact Distribution Alignment in Federated Learning via Masked Optimal Transport
• H-Alpha Anomalyzer: An Explainable Anomaly Detector for Solar H-Alpha Observations
• An Explainable AI Framework for Dynamic Resource Management in Vehicular Network Slicing
• Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
• "What's Up, Doc?": Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets
• FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation
• VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion
• Fine-tuning Vision Language Models with Graph-based Knowledge for Explainable Medical Image Analysis
• Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping
• Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step Reading
• Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models
• Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents
• PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
• Binarized Neural Networks Converge Toward Algorithmic Simplicity: Empirical Support for the Learning-as-Compression Hypothesis
• Semantic Exploration and Dense Mapping of Complex Environments using Ground Robot with Panoramic LiDAR-Camera Fusion
• DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
• Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
• Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
• 3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection
• Reconstruction of Differentially Private Text Sanitization via Large Language Models
• Advanced Physics-Informed Neural Network with Residuals for Solving Complex Integral Equations
• SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation
• Examining False Positives under Inference Scaling for Mathematical Reasoning
• SNaRe: Domain-aware Data Generation for Low-Resource Event Detection
• Semi-Supervised 3D Medical Segmentation from 2D Natural Images Pretrained Model
• Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting
• SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
• Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
• FlowRL: Matching Reward Distributions for LLM Reasoning
• Automatic Mapping of AutomationML Files to Ontologies for Graph Queries and Validation
• Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning
• Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
• Blockchain-Enabled Explainable AI for Trusted Healthcare Systems
• Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering
• CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models
• Reinforcement Learning Agent for a 2D Shooter Game
• Listening, Imagining \& Refining: A Heuristic Optimized ASR Correction Framework with LLMs
• TextMine: LLM-Powered Knowledge Extraction for Humanitarian Mine Action
• Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
• WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
• Exploring How Audio Effects Alter Emotion with Foundation Models
• Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
• Diffusion-Based Scenario Tree Generation for Multivariate Time Series Prediction and Multistage Stochastic Optimization
• [Re] Improving Interpretation Faithfulness for Vision Transformers
• Empathy-R1: A Chain-of-Empathy and Reinforcement Learning Framework for Long-Form Mental Health Support
• MeanFlowSE: one-step generative speech enhancement via conditional mean flow
• AI-Driven Multi-Agent Vehicular Planning for Battery Efficiency and QoS in 6G Smart Cities
• A Multi-To-One Interview Paradigm for Efficient MLLM Evaluation
• Patent Language Model Pretraining with ModernBERT
• Cross-Modal Knowledge Distillation for Speech Large Language Models
• M4Diffuser: Multi-View Diffusion Policy with Manipulability-Aware Control for Robust Mobile Manipulation
• ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
• Enterprise AI Must Enforce Participant-Aware Access Control
• Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
• Reveal and Release: Iterative LLM Unlearning with Self-generated Data
• Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech
• DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training
• MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
• Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery
• OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning
• ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classification
• When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine
• Simulating a Bias Mitigation Scenario in Large Language Models
• Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs
• Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents
• BEACON: Behavioral Malware Classification with Large Language Model Embeddings and Deep Learning
• Delta Knowledge Distillation for Large Language Models
• Leveraging Artificial Intelligence as a Strategic Growth Catalyst for Small and Medium-sized Enterprises
• ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference
• Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
• LLM Jailbreak Detection for (Almost) Free!
• Can I Trust This Chatbot? Assessing User Privacy in AI-Healthcare Chatbot Applications
• FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
• Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
• Beyond Data Privacy: New Privacy Risks for Large Language Models
• Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
• Beyond Classification: Evaluating LLMs for Fine-Grained Automatic Malware Behavior Auditing
• Near-Real-Time Resource Slicing for QoS Optimization in 5G O-RAN using Deep Reinforcement Learning
• DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
• eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations
• Q-ROAR: Outlier-Aware Rescaling for RoPE Position Interpolation in Quantized Long-Context LLMs
• A Taxonomy of Prompt Defects in LLM Systems
• LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
• CrossPT: Exploring Cross-Task Transferability through Multi-Task Prompt Tuning
• Hallucination Detection with the Internal Layers of LLMs
• Opening the Black Box: Interpretable LLMs via Semantic Resonance Architecture
• JU-NLP at Touch\'e: Covert Advertisement in Conversational AI-Generation and Detection Strategies
• From Correction to Mastery: Reinforced Distillation of Large Language Model Agents
• Shutdown Resistance in Large Language Models
• Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
• Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models
• SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models
• SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models
• Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
• RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
• The NazoNazo Benchmark: A Cost-Effective and Extensible Test of Insight-Based Reasoning in LLMs
• OpenLens AI: Fully Autonomous Research Agent for Health Infomatics
• Explainable AI for Infection Prevention and Control: Modeling CPE Acquisition and Patient Outcomes in an Irish Hospital with Transformers
• Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
• A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making
• Calibrated Generative AI as Meta-Reviewer: A Systemic Functional Linguistics Discourse Analysis of Reviews of Peer Reviews
• From Sea to System: Exploring User-Centered Explainable AI for Maritime Decision Support
• Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment
• Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion
• Rationality Check! Benchmarking the Rationality of Large Language Models
• From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing
• Detecting Pipeline Failures through Fine-Grained Analysis of Web Agents
• VCBench: Benchmarking LLMs in Venture Capital