Papers

New on arXiv

Thu 27 Nov 2025

327 papers

Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QARetrieval-augmented generation → Medical and biomedical RAG
PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual AgentsLLM agents and tool use → Software engineering coding agents
Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache CompressionLLM agents and tool use → Software engineering coding agents +1
Optimizing Algorithms for Mobile Health Interventions with Active Querying OptimizationDeep reinforcement learning methods → RL for clinical treatment and surgery
Advancing time series completion via RFAMoE and MDFFDiffusion models → Flow matching, time series and science +1
FlockVote: LLM-Empowered Agent-Based Modeling for Simulating U.S. Presidential ElectionsLLM agents and tool use → Social simulation and multi-agent debate
From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of ImagesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision AvoidanceDiffusion models → Diffusion and flow policies for robotics +1
MammoRGB: Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt TuningKnowledge distillation → Distillation for medical imaging
Solving Context Window Overflow in AI AgentsLLM agents and tool use → Medical and scientific domain agents
ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question AnsweringLLM reasoning → Multimodal reasoning +2
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion TransformerDiffusion models → Diffusion foundations and sampling
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot DemonstrationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Test-time scaling of diffusions with flow mapsDiffusion models → Diffusion foundations and sampling
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the ShieldDiffusion models → Diffusion foundations and sampling
VaMP: Variational Multi-Modal Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal ModelLLM reasoning → Multimodal reasoning
Geometrically-Constrained Agent for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +2
GeoZero: Incentivizing Reasoning from Scratch on Geospatial ScenesLLM reasoning → Spatial and embodied reasoning +1
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-TuningDiffusion models → Flow matching, time series and science
ReasonEdit: Towards Reasoning-Enhanced Image Editing ModelsLLM reasoning → Multimodal reasoning
Improving LLM-based Ontology Matching with fine-tuning on synthetic dataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
LLM-Cave: A benchmark and light environment for large language models reasoning and decision-making systemLLM reasoning → Reasoning benchmarks and evaluation
HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning GeneralizationLLM reasoning → Multimodal reasoning +1
High entropy leads to symmetry-equivariant policies in Dec-POMDPsDeep reinforcement learning methods → RL with diffusion and flow models
DeepSeekMath-V2: Towards Self-Verifiable Mathematical ReasoningLLM reasoning → Mathematical reasoning
Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time InterventionVision-language-action models → Failure recovery and robustness
Fast3Dcache: Training-free 3D Geometry Synthesis AccelerationDiffusion models → Diffusion foundations and sampling
CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQALLM reasoning → Multimodal reasoning
AI killed the video star. Audio-driven diffusion model for expressive talking head generationDiffusion models → Audio, speech and music
OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and LatencyEfficient LLM inference and serving → Serving systems and request scheduling
ITS3D: Inference-Time Scaling for Text-Guided 3D Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
DIPOLE: Fusing Vision and Geometry for Robust Visuomotor GeneralizationOffline RL and imitation learning from data → Robot manipulation imitation learning
GEO-Detective: Unveiling Location Privacy Risks in Images with LLM AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action RecognitionLLM agents and tool use → Multimodal and embodied agents
Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
NOMAD: A Multi-Agent LLM System for UML Class Diagram Generation from Natural Language RequirementsLLM agents and tool use → Software engineering coding agents
Improving Stochastic Action-Constrained Reinforcement Learning via Truncated DistributionsDeep reinforcement learning methods → RL theory and sample complexity
Asking like Socrates: Socrates helps VLMs understand remote sensing imagesLLM reasoning → Spatial and embodied reasoning
INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative ArtifactsLLM reasoning → Multimodal reasoning +1
Nonholonomic Narrow Dead-End Escape with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile KernelEfficient LLM inference and serving → KV cache optimization
RELiQ: Scalable Entanglement Routing via Reinforcement Learning in Quantum NetworksDeep reinforcement learning methods → Quantum reinforcement learning
Swarms of Large Language Model Agents for Protein Sequence Design with Experimental ValidationLLM agents and tool use → Medical and scientific domain agents
GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech SynthesisDiffusion models → Audio, speech and music
Investigating AI in Peer Support via Multi-Module System-Driven Embodied Conversational AgentsLLM agents and tool use → Medical and scientific domain agents
Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable CritiquesDeep reinforcement learning methods → RL training of language and agent models
UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive InterpretationMultimodal LLMs / vision-language models → Medical vision-language models
Co-Evolving Agents: Learning from Failures as Hard NegativesLLM agents and tool use → General LLM agent frameworks and benchmarks
Toward Diffusible High-Dimensional Latent Spaces: A Frequency PerspectiveDiffusion models → Diffusion foundations and sampling
Semantic Anchoring for Robust Personalization in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Rethinking Test Time Scaling for Flow-Matching Generative ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI AutomationLLM agents and tool use → GUI and mobile agents +1
From Compound Figures to Composite Understanding: Developing a Multi-Modal LLM from Biomedical Literature with Medical Multiple-Image Benchmarking and ValidationMultimodal LLMs / vision-language models → Medical vision-language models
BiCQL-ML: A Bi-Level Conservative Q-Learning Framework for Maximum Likelihood Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
Controllable 3D Object Generation with Single Image PromptDiffusion models → 3D, point cloud and scene generation
HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input InformationLLM reasoning → Prompting and chain-of-thought reasoning
A perceptual bias of AI Logical Argumentation Ability in WritingLLM reasoning → Reasoning benchmarks and evaluation
C2DLM: Causal Concept-Guided Diffusion Large Language ModelsDiffusion models → Discrete and text diffusion
Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive SamplesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge DevicesLLM agents and tool use → General LLM agent frameworks and benchmarks +1
DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and ActionLLM reasoning → Spatial and embodied reasoning +1
GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz OptimizationDiffusion models → Robustness, privacy and adversarial aspects
Representative Action Selection for Large Action Space: From Bandits to MDPsDeep reinforcement learning methods → RL theory and sample complexity
MoE3D: Mixture of Experts meets Multi-Modal 3D UnderstandingMixture-of-experts → Vision mixture-of-experts
Adaptive Dueling Double Deep Q-networks in Uniswap V3 Replication and Extension with MambaDeep reinforcement learning methods → Deep RL algorithms and representations
WorldWander: Bridging Egocentric and Exocentric Worlds in Video GenerationWorld models → Video-generation world models and simulators
Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Real-Time Procedural Learning From Experience for AI AgentsLLM agents and tool use → Agent memory systems
Convergence Dynamics of Over-Parameterized Score Matching for a Single GaussianDiffusion models → Diffusion foundations and sampling
OralGPT-Omni: A Versatile Dental Multimodal Large Language ModelMultimodal LLMs / vision-language models → Medical vision-language models
ICM-SR: Image-Conditioned Manifold Regularization for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial AttacksLLM safety and security → Safety alignment, refusal and guardrails
Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking RegressionLLM safety and security → Jailbreaking
SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World ModelWorld models → World models for autonomous driving
What AI Speaks for Your Community: Polling AI Agents for Public Opinion on Data Center ProjectsLLM agents and tool use → Social simulation and multi-agent debate
Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
MedEyes: Learning Dynamic Visual Focus for Medical Progressive DiagnosisLLM reasoning → Clinical and biomedical applications
StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow GenerationDiffusion models → Flow matching, time series and science
Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
A Safety and Security Framework for Real-World Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
On Meta-Evaluation
Cross-Platform Digital Discourse Analysis of the Israel-Hamas Conflict: Sentiment, Topics, and Event Dynamics
STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset
Byzantine Fault-Tolerant Multi-Agent System for Healthcare: A Gossip Protocol Approach to Secure Medical Message Propagation
The Ontological Dissonance Hypothesis: AI-Triggered Delusional Ideation as Folie a Deux Technologique
A Reproducible Workflow for Scraping, Structuring, and Segmenting Legacy Archaeological Artifact Images
AI Co-Artist: A LLM-Powered Framework for Interactive GLSL Shader Animation Evolution
Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming
Referenceless Proton Resonance Frequency Thermometry Using Deep Learning with Self-Attention
Semi-Supervised Contrastive Learning with Orthonormal Prototypes
Nonnegative Matrix Factorization through Cone Collapse
Graph Contrastive Learning via Spectral Graph Alignment

All 327