Papers

New on arXiv

Sat 6 Dec 2025

144 papers

Delete and Retain: Efficient Unlearning for Document ClassificationLLM safety and security → Machine unlearning
WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous DrivingVision-language-action models → VLA for autonomous driving +3
Metaphor-based Jailbreak Attacks on Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
Verifier Threshold: An Efficient Test-Time Scaling Approach for Image GenerationLLM reasoning → Diffusion reasoning and test-time scaling
RAG-HAR: Retrieval Augmented Generation-based Human Activity RecognitionRetrieval-augmented generation → RAG pipeline design and evaluation
Towards Efficient Hypergraph and Multi-LLM Agent Recommender SystemsLLM agents and tool use → Agentic recommender systems
OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense EvaluationLLM safety and security → Jailbreaking
MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video UnderstandingLLM reasoning → Clinical and biomedical applications +2
The Effect of Belief Boxes and Open-mindedness on PersuasionLLM agents and tool use → Social simulation and multi-agent debate
SUGAR: A Sweeter Spot for Generative Unlearning of Many IdentitiesLLM safety and security → Vision-language and text-to-image safety
Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level ManipulationLLM agents and tool use → Agent threats, guardrails and governance +1
Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
ProSocialAlign: Preference Conditioned Test Time Alignment in Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Entropy-Controlled Intrinsic Motivation Reinforcement Learning for Quadruped Robot Locomotion in Complex TerrainsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual ControlDeep reinforcement learning methods → Deep RL algorithms and representations
Enhancing Medical Cross-Modal Hashing Retrieval using Dropout-Voting Mixture-of-Experts FusionMixture-of-experts → Medical and biomedical MoE
HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation ProtocolsLLM agents and tool use → Medical and scientific domain agents
AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in CybersecurityLLM agents and tool use → Agent threats, guardrails and governance
RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUsLLM reasoning → Reinforcement learning for reasoning
Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied IntelligenceLLM safety and security → Prompt injection and agent security
Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation FrameworkEnd-to-end autonomous driving → VLMs for autonomous driving
VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement LearningLLM reasoning → Multimodal reasoning +1
TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision SearchDiffusion models → Diffusion foundations and sampling
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
S2WMamba: A Wavelet-Assisted Mamba-Based Dual-Branch Network For PansharpeningState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
A Hybrid Physics-Based and Reinforcement Learning Framework for Electric Vehicle Charging Time PredictionDeep reinforcement learning methods → RL for energy, networks and operations
Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression ComprehensionLLM reasoning → Multimodal reasoning
Networked Restless Multi-Arm Bandits with Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMsLLM reasoning → Multimodal reasoning +1
Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic SetupLLM agents and tool use → General LLM agent frameworks and benchmarks
Learning Without Time-Based Embodiment Resets in Soft-Actor CriticDeep reinforcement learning methods → Deep RL algorithms and representations
Learning When to Switch: Adaptive Policy Selection via Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
DUET: Agentic Design Understanding via Experimentation and TestingLLM agents and tool use → Software engineering coding agents
Auto-exploration for online reinforcement learningDeep reinforcement learning methods → Deep RL algorithms and representations
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
Bayesian Modeling for Uncertainty Management in Financial Risk Forecasting and Compliance
Hybrid Quantum-Classical Ensemble Learning for S&P 500 Directional Prediction
Anubuddhi: A Multi-Agent AI System for Designing and Simulating Quantum Optics Experiments
The Graph-Embedded Hazard Model (GEHM): Stochastic Network Survival Dynamics on Economic Graphs
Prediction of Respiratory Syncytial Virus-Associated Hospitalizations Using Machine Learning Models Based on Environmental Data
Predictive Modeling of Flood-Prone Areas Using SAR and Environmental Variables
Smart Surveillance: Identifying IoT Device Behaviours using ML-Powered Traffic Analysis
Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States
Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops
Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation
3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
Explainable Fundus Image Curation and Lesion Detection in Diabetic Retinopathy
From Remote Sensing to Multiple Time Horizons Forecasts: Transformers Model for CyanoHAB Intensity in Lake Champlain
ChargingBoul: A Competitive Negotiating Agent with Novel Opponent Modeling
On fine-tuning Boltz-2 for protein-protein affinity prediction
Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability
Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract
Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Classifiers
Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules
GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation
Deep Manifold Part 2: Neural Network Mathematics
Bridging spatial awareness and global context in medical image segmentation
BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models
A Latent Variable Framework for Scaling Laws in Large Language Models
A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation
Approximate Multiplier Induced Error Propagation in Deep Neural Networks
Novel Deep Learning Architectures for Classification and Segmentation of Brain Tumors from MRI Images
On The Role of K-Space Acquisition in MRI Reconstruction Domain-Generalization
Hierarchical Clustering With Confidence
ShadowWolf -- Automatic Labelling, Evaluation and Model Training Optimised for Camera Trap Wildlife Images
Hierarchical geometric deep learning enables scalable analysis of molecular dynamics
Simultaneous Heterogeneity and Reduced-rank Learning for Multivariate Response Regression
Diagnosis-based mortality prediction for intensive care unit patients via transfer learning
AI as "Co-founder": GenAI for Entrepreneurship
Method of UAV Inspection of Photovoltaic Modules Using Thermal and RGB Data Fusion
PRIMRose: Insights into the Per-Residue Energy Metrics of Proteins with Double InDel Mutations using Deep Learning
Optimizing LLMs Using Quantization for Mobile Execution
Sanvaad: A Multimodal Accessibility Framework for ISL Recognition and Voice-Based Interaction
Classifying German Language Proficiency Levels Using Large Language Models
Knowing What's Missing: Assessing Information Sufficiency in Question Answering
Modeling Contextual Passage Utility for Multihop Question Answering
Instance Dependent Testing of Samplers using Interval Conditioning
BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination
Towards Stable Cross-Domain Depression Recognition under Missing Modalities
Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
Neural expressiveness for beyond importance model compression
AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars
Canonical Tail Dependence for Soft Extremal Clustering of Multichannel Brain Signals
Automated Deep Learning Estimation of Anthropometric Measurements for Preparticipation Cardiovascular Screening
Smart Spatial Planning in Egypt: An Algorithm-Driven Approach to Public Service Evaluation in Qena City
A new initialisation to Control Gradients in Sinusoidal Neural network
When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition
DragMesh: Interactive 3D Generation Made Easy
A Perception CNN for Facial Expression Recognition
Rethinking Training Dynamics in Scale-wise Autoregressive Generation
Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator
UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems
Perceptual Region-Driven Infrared-Visible Co-Fusion for Extreme Scene Enhancement
Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
Web Technologies Security in the AI Era: A Survey of CDN-Enhanced Defenses
Protecting Bystander Privacy via Selective Hearing in Audio LLMs

All 144