Papers

New on arXiv

Sun 7 Dec 2025

189 papers

Enhancing Admission Inquiry Responses with Fine-Tuned Models and Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
Permission Manifests for Web AgentsLLM agents and tool use → Web, search, and research agents
Ideal Attribution and Faithful Watermarks for Language ModelsLLM safety and security → Watermarking generated content and models
Reformulate, Retrieve, Localize: Agents for Repository-Level Bug LocalizationLLM agents and tool use → Software engineering coding agents
Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought LengthLLM reasoning → Reasoning benchmarks and evaluation
FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic HallucinationsRetrieval-augmented generation → Hallucination detection in RAG
Toward Reliable Machine Unlearning: Theory, Algorithms, and EvaluationLLM safety and security → Machine unlearning
On Memory: A comparison of memory mechanisms in world modelsWorld models → Video-generation world models and simulators
Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific ImagingDiffusion models → Medical imaging and segmentation
Statistical analysis of Inverse Entropy-regularized Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR ChallengeVision-language-action models → Failure recovery and robustness +1
Adaptive Normalization Mamba with Multi Scale Trend Decomposition and Patch MoE EncodingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy IdentificationMultimodal LLMs / vision-language models → Medical vision-language models
Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory AnalysisDeep reinforcement learning methods → Interpretable and logic-guided RL
SoK: Trust-Authorization Mismatch in LLM Agent InteractionsLLM agents and tool use → Agent threats, guardrails and governance
Khalasi: Energy-Efficient Navigation for Surface Vehicles in Vortical Flow FieldsDeep reinforcement learning methods → RL for robot navigation and UAV control
BabelCoder: Agentic Code Translation with Specification AlignmentLLM agents and tool use → Software engineering coding agents
Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language ModelsLLM safety and security → Backdoor and data poisoning attacks
Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal RecommendationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?LLM reasoning → Reasoning benchmarks and evaluation
Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe PriorEfficient LLM inference and serving → Visual token pruning in multimodal models
Spatial Retrieval Augmented Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language ReasoningLLM reasoning → Multimodal reasoning +2
RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement LearningMultimodal LLMs / vision-language models → Video understanding with MLLMs
Stable-MoE: Lyapunov-based Token Routing for Distributed Mixture-of-Experts Training over Edge NetworksMixture-of-experts → Expert routing strategies
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMsDiffusion models → Discrete and text diffusion
Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language PriorsLLM reasoning → Multimodal reasoning +1
UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and EnhancementMultimodal LLMs / vision-language models → Image editing and quality assessment
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model AlignmentMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language ModelsEfficient LLM inference and serving → KV cache optimization
The Role of Entropy in Visual Grounding: Analysis and OptimizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the WildLLM agents and tool use → Multimodal and embodied agents
SIEVE: Selective Integrity Verification and Escalation for Defending LLM Agents against Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass CorrelationLLM agents and tool use → General LLM agent frameworks and benchmarks
Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic ModelDiffusion models → Diffusion foundations and sampling
State Diversity Matters in Offline Behavior DistillationOffline RL and imitation learning from data → Offline RL algorithms
Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form GenerationLLM reasoning → Reinforcement learning for reasoning
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic MemoryLLM agents and tool use → Agent memory systems
Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment AnalysisMechanistic interpretability → Circuits and mechanistic analysis
RunawayEvil: Jailbreaking the Image-to-Video Generative ModelsLLM safety and security → Vision-language and text-to-image safety
Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language TasksLLM reasoning → Multimodal reasoning +1
The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous PipelinesLLM agents and tool use → Agent threats, guardrails and governance
TextMamba: Scene Text Detector with MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
Graph-Regularized Sparse Autoencoders for LLM Safety SteeringLLM safety and security → Safety alignment, refusal and guardrails +1
LightSearcher: Efficient DeepSearch via Experiential MemoryLLM reasoning → Knowledge- and tool-augmented reasoning
An Index-based Approach for Efficient and Effective Web Content ExtractionRetrieval-augmented generation → Agentic RAG, agents and memory +1
Learning to Hedge SwaptionsDeep reinforcement learning methods → Adversarial robustness and RL in finance
PG-Flow: Deterministic implicit policy gradients for geometric product-form queueing networksDeep reinforcement learning methods → RL for energy, networks and operations
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical AlignmentWorld models → Embodied and robot world models
Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured DistributionsDiffusion models → Diffusion foundations and sampling
A New Trajectory-Oriented Approach to Enhancing Comprehensive Crowd Navigation PerformanceDeep reinforcement learning methods → RL for robot navigation and UAV control
Uniqueness ratio as a predictor of a privacy leakage
TeachMaster: Generative Teaching via Code
Evaluating Anomaly Detectors for Simulated Highly Imbalanced Industrial Classification Problems
BIONIX: A Wireless, Low-Cost Prosthetic Arm with Dual-Signal EEG and EMG Control
The Principle of Proportional Duty: A Knowledge-Duty Framework for Ethical Equilibrium in Human and Artificial Systems
LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms
It's About Time: The Temporal and Modal Dynamics of Copilot Usage
The Art of Storytelling in Authoritarian Regimes: Crafting State Narratives on Chinese Social Media
Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training
Mathematics of natural intelligence
ELANA: A Simple Energy and Latency Analyzer for LLMs
RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting
DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation
Transformation of Biological Networks into Images via Semantic Cartography for Visual Interpretation and Scalable Deep Analysis
Evaluating and Preserving High-level Fidelity in Super-Resolution
Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues
A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data
Transferring Clinical Knowledge into ECGs Representation
Block Sparse Flash Attention
Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks
Optimizing video analytics inference pipelines: a case study
Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition
Benchmarking Deep Neural Networks for Modern Recommendation Systems
Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model
Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models
Utilizing Multi-Agent Reinforcement Learning with Encoder-Decoder Architecture Agents to Identify Optimal Resection Location in Glioblastoma Multiforme Patients
Flash Multi-Head Feed-Forward Network
OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction
LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding
Selective Masking based Self-Supervised Learning for Image Semantic Segmentation
Feasibility-aware Learning of Robust Temporal Logic Controllers using BarrierNet
Prediction with Expert Advice under Local Differential Privacy
Comparing BFGS and OGR for Second-Order Optimization
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
Learning Conditional Independence Differential Graphs From Time-Dependent Data
PARIS: Pruning Algorithm via the Representer theorem for Imbalanced Scenarios
Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology
Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets
A Unifying Human-Centered AI Fairness Framework
Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

All 189