Papers

New on arXiv

Sat 29 Nov 2025

191 papers

InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Password-Activated Shutdown Protocols for Misaligned Frontier AgentsLLM safety and security → Prompt injection and agent security
When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTIMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series ForecastingMixture-of-experts → MoE for time series and graphs
MambaScope: Coarse-to-Fine Scoping for Efficient Vision MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones +1
Privacy Preserving Diffusion Models for Mixed-Type Tabular Data GenerationDiffusion models → Robustness, privacy and adversarial aspects
ART: Adaptive Response Tuning Framework -- A Multi-Agent Tournament-Based Approach to LLM Response OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
Hierarchical Decentralized Multi-Agent Coordination with Privacy-Preserving Knowledge Sharing: Extending AgentNet for Scalable Autonomous SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
AgentODRL: A Large Language Model-based Multi-agent System for ODRL GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy OptimizationLLM reasoning → Clinical and biomedical applications
Scaling Down to Scale Up: Towards Operationally-Efficient and Deployable Clinical Models via Cross-Modal Low-Rank Adaptation for Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamicsDiffusion models → Diffusion foundations and sampling
GCMCG: A Clustering-Aware Graph Attention and Expert Fusion Network for Multi-Paradigm, Multi-task, and Cross-Subject EEG DecodingMixture-of-experts → Medical and biomedical MoE
List Replicable Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical FidelityLLM reasoning → Mathematical reasoning
DQ4FairIM: Fairness-aware Influence Maximization using Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
Algorithmic Guarantees for Distilling Supervised and Offline RL DatasetsOffline RL and imitation learning from data → Offline RL algorithms
Toward a Safe Internet of AgentsLLM agents and tool use → Agent threats, guardrails and governance
Truthful and Trustworthy IoT AI Agents via Immediate-Penalty Enforcement under Approximate VCG MechanismsDeep reinforcement learning methods → RL for energy, networks and operations
G-KV: Decoding-Time KV Cache Eviction with Global AttentionLLM reasoning → Test-time compute and efficient thinking +1
ESPO: Entropy Importance Sampling Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical ReasoningLLM reasoning → Clinical and biomedical applications
LAP: Fast LAtent Diffusion Planner for Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time ScalingLLM reasoning → Test-time compute and efficient thinking
Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to TransparencyLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal PredictionOffline RL and imitation learning from data → Imitation learning methods
FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward SignalLLM reasoning → Diffusion reasoning and test-time scaling +1
Hardware-Software Collaborative Computing of Photonic Spiking Reinforcement Learning for Robotic Continuous ControlDeep reinforcement learning methods → Spiking and neuromorphic RL
What about gravity in video generation? Post-Training Newton's Laws with Verifiable RewardsDiffusion models → Video generation
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in CryptocurrencyLLM agents and tool use → Financial trading and forecasting agents
Red Teaming Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask PredictionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL SubroutinesOffline RL and imitation learning from data → Offline RL algorithms
Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case StudySynthetic data and self-improvement for LLMs → Code and instruction data synthesis
POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion ModelsDiffusion models → Inverse problems and image restoration
Breaking It Down: Domain-Aware Semantic Segmentation for Retrieval Augmented GenerationRetrieval-augmented generation → Multimodal RAG
S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal ForecastingKnowledge distillation → General knowledge distillation methods
MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality AdaptersState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Learning Causal States Under Partial Observability and PerturbationDiffusion models → Diffusion and flow policies for robotics +1
SMamDiff: Spatial Mamba for Stochastic Human Motion PredictionDiffusion models → Video generation +1
Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
MedCondDiff: Lightweight, Robust, Semantically Guided Diffusion for Medical Image SegmentationDiffusion models → Medical imaging and segmentation
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling AgentsLLM agents and tool use → Agent threats, guardrails and governance
CogEvo-Edu: Cognitive Evolution Educational Multi-Agent Collaborative SystemRetrieval-augmented generation → Agentic RAG, agents and memory +1
Evidence-Guided Schema Normalization for Temporal Tabular ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
VCWorld: A Biological World Model for Virtual Cell SimulationWorld models → Medical and surgical world models
ChartPoint: Guiding MLLMs with Grounding Reflection for Chart ReasoningLLM reasoning → Multimodal reasoning +1
Gradient Inversion in Federated Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Words into World: A Task-Adaptive Agent for Language-Guided Spatial Retrieval in ARMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
WARP: Weight Teleportation for Attack-Resilient Unlearning ProtocolsLLM safety and security → Machine unlearning
UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse AnnotationsDiffusion models → Inverse problems and image restoration
PharmaShip: An Entity-Centric, Reading-Order-Supervised Benchmark for Chinese Pharmaceutical Shipping Documents
Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
Harnessing Data Spaces to Build Intelligent Smart City Infrastructures Across the Cloud-Edge Continuum
Optimizing Text Search: A Novel Pattern Matching Algorithm Based on Ukkonen's Approach
RMSup: Physics-Informed Radio Map Super-Resolution for Compute-Enhanced Integrated Sensing and Communications
QSTAformer: A Quantum-Enhanced Transformer for Robust Short-Term Voltage Stability Assessment against Adversarial Attacks
Exploring Health Misinformation Detection with Multi-Agent Debate
Fine-tuning an ECG Foundation Model to Predict Coronary CT Angiography Outcomes
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
Large Language Model based Smart Contract Auditing with LLMBugScanner
Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification
Quantum Machine Learning for Secondary Frequency Control
Superpixel Attack: Enhancing Black-box Adversarial Attack with Image-driven Division Areas
A Comparison of Human and ChatGPT Classification Performance on Complex Social Media Data
ML-Tool-Bench: Tool-Augmented Planning for ML Tasks
EDIT: Early Diffusion Inference Termination for dLLMs Based on Dynamics of Training Gradients
Restricted Block Permutation for Two-Sample Testing
Active Learning of Fractional-Order Viscoelastic Model Parameters for Realistic Haptic Rendering
Self-sufficient Independent Component Analysis for Demixing Flows
Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs
Fast, Robust, Permutation-and-Sign Invariant SO(3) Pattern Alignment
Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
Large Language Models for Software Engineering: A Reproducibility Crisis
Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition
Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation
Financial Text Classification Based On rLoRA Finetuning On Qwen3-8B model
XAI-Driven Skin Disease Classification: Leveraging GANs to Augment ResNet-50 Performance
Automatic Pith Detection in Tree Cross-Section Images Using Deep Learning
Melody or Machine: Detecting Synthetic Music with Dual-Stream Contrastive Learning
Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
Stable Voting and the Splitting of Cycles
Generalized Graph Transformer Variational Autoencoder
Prism: A Minimal Compositional Metalanguage for Specifying Agent Behavior
Statistical-computational gap in multiple Gaussian graph alignment
On the Holographic Geometry of Deterministic Computation
Efficient Matroid Bandit Linear Optimization Leveraging Unimodality
Developing Fairness-Aware Task Decomposition to Improve Equity in Post-Spinal Fusion Complication Prediction
DLRREC: Denoising Latent Representations via Multi-Modal Knowledge Fusion in Deep Recommender Systems
IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
Statistical NLP for Optimization of Clinical Trial Success Prediction in Pharmaceutical R&D
SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension
Slovak Conceptual Dictionary
Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models
Enhancing Analogy-Based Software Effort Estimation with Firefly Algorithm Optimization
Describe Anything Anywhere At Any Moment
Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers

All 191