Papers

New on arXiv

Thu 12 Jun 2025

378 papers

Novel RL approach for efficient Elevator Group Control SystemsDeep reinforcement learning methods → RL for energy, networks and operations
DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual ReasoningLLM reasoning → Multimodal reasoning
Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVARetrieval-augmented generation → RAG pipeline design and evaluation
Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants IntegretionRetrieval-augmented generation → Privacy and security of RAG
A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for DebiasingLLM agents and tool use → Social simulation and multi-agent debate
Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
UCD: Unlearning in LLMs via Contrastive DecodingLLM safety and security → Machine unlearning
DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative DecodingEfficient LLM inference and serving → Speculative decoding
TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for AutonomyWorld models → World models for autonomous driving
Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy PatientsDiffusion models → Medical imaging and segmentation
Constrained Diffusion Models for Synthesizing Representative Power Flow DatasetsDiffusion models → Flow matching, time series and science
Learning a Continue-Thinking Token for Enhanced Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool CallingLLM agents and tool use → Tool learning and function calling
Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human DemonstrationsOffline RL and imitation learning from data → Robot learning from demonstration
Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation ModelsLLM safety and security → Machine unlearning
No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
DiffPR: Diffusion-Based Phase Reconstruction via Frequency-Decoupled LearningDiffusion models → Inverse problems and image restoration
Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in ManufacturingLLM agents and tool use → Tool learning and function calling
Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenesKnowledge distillation → Detection and dense prediction distillation
Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?LLM reasoning → Test-time compute and efficient thinking
Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow ModelsDiffusion models → Diffusion foundations and sampling
AutoMind: Adaptive Knowledgeable Agent for Automated Data ScienceLLM agents and tool use → Web, search, and research agents
What Exactly Does Guidance Do in Masked Discrete Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image ReasoningLLM reasoning → Multimodal reasoning
SpectralAR: Spectral Autoregressive Visual GenerationDiffusion models → Image generation, text-to-image and editing
ChineseHarm-Bench: A Chinese Harmful Content Detection BenchmarkLLM safety and security → Safety alignment, refusal and guardrails
ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse ProblemsDiffusion models → Inverse problems and image restoration
Build the web for agents, not agents for the webLLM agents and tool use → Web, search, and research agents
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential MonitorsLLM safety and security → Prompt injection and agent security
Spurious Rewards: Rethinking Training Signals in RLVRLLM reasoning → Reinforcement learning for reasoning
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language ModelsLLM safety and security → Machine unlearning
Dynamic Epistemic Friction in DialogueLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed IntelligenceLLM agents and tool use → Agentic AI for wireless networks
Constructing Interpretable Features from Compositional Neuron GroupsMechanistic interpretability → SAE features and their applications
Sequential-Parallel Duality in Prefix Scannable ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
M4V: Multimodal Mamba for Efficient Text-to-Video GenerationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
MagistralLLM reasoning → Reinforcement learning for reasoning
Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical ReasoningLLM reasoning → Mathematical reasoning
The Diffusion DualityDiffusion models → Discrete and text diffusion
Generalization or Hallucination? Understanding Out-of-Context Reasoning in TransformersLLM reasoning → Reasoning benchmarks and evaluation
Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy RegularizationDeep reinforcement learning methods → RL theory and sample complexity
VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative VideosLLM reasoning → Multimodal reasoning
A Study on Individual Spatiotemporal Activity Generation Method Using MCP-Enhanced Chain-of-Thought Large Language ModelsLLM reasoning → Spatial and embodied reasoning
CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-TrainingRetrieval-augmented generation → Agentic RAG, agents and memory
RationalVLA: A Rational Vision-Language-Action Model with Dual SystemVision-language-action models → 3D and spatial-aware VLA
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference OptimizationLLM reasoning → Test-time compute and efficient thinking +1
Constructing and Evaluating Declarative RAG Pipelines in PyTerrierRetrieval-augmented generation → RAG pipeline design and evaluation
Human-Robot Navigation using Event-based Cameras and Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
SlotPi: Physics-informed Object-centric Reasoning ModelsLLM reasoning → Spatial and embodied reasoning
ME: Trigger Element Combination Backdoor Attack on Copyright InfringementDiffusion models → Robustness, privacy and adversarial aspects
Mind the Gap: Benchmarking LLM Uncertainty and Calibration with Specialty-Aware Clinical QA and Reasoning-Based Behavioural FeaturesLLM reasoning → Clinical and biomedical applications
OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization ProblemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question AnsweringLLM reasoning → Causal reasoning in LLMs
Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question AnsweringLLM agents and tool use → Medical and scientific domain agents
IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical DomainMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced ClaimsRetrieval-augmented generation → Medical and biomedical RAG
PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large ModelsLLM reasoning → Mathematical reasoning
Data Shifts Hurt CoT: A Theoretical StudyLLM reasoning → Prompting and chain-of-thought reasoning
GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-TuningDiffusion models → Video generation
Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative ModelsDiffusion models → Flow matching, time series and science
Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
Hessian Geometry of Latent Space in Generative ModelsDiffusion models → Diffusion foundations and sampling
Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMsLLM reasoning → Time series reasoning
Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI TutorsRetrieval-augmented generation → Agentic RAG, agents and memory
SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
TexTailor: Customized Text-aligned Texturing via Effective ResamplingDiffusion models → 3D, point cloud and scene generation
High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion modelDiffusion models → Diffusion for compression and wireless
SoK: Evaluating Jailbreak Guardrails for Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Primender Sequence: A Novel Mathematical Construct for Testing Symbolic Inference and AI ReasoningLLM reasoning → Mathematical reasoning
Rethinking Random Masking in Self-Distillation on ViTKnowledge distillation → General knowledge distillation methods
Harmonizing Geometry and Uncertainty: Diffusion with HyperspheresDiffusion models → Diffusion foundations and sampling
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion TransformersDiffusion models → Video generation
Equivariant Neural Diffusion for Molecule GenerationDiffusion models → Flow matching, time series and science
LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT LengthLLM reasoning → Reasoning for agents, planning and code
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and ReasoningLLM reasoning → Multimodal reasoning
Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
Edit360: 2D Image Edits to 3D Assets from Any AngleDiffusion models → 3D, point cloud and scene generation
A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring WatermarksDiffusion models → Robustness, privacy and adversarial aspects
BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug SynthesisLLM agents and tool use → Software engineering coding agents
OIBench: Benchmarking Strong Reasoning Models with Olympiad in InformaticsLLM reasoning → Test-time compute and efficient thinking
Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity ApplicationsLLM reasoning → Reasoning for agents, planning and code +1
MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language ModelsLLM reasoning → Clinical and biomedical applications +1
Towards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution ShiftsKnowledge distillation → Multimodal distillation
Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length PenaltyLLM reasoning → Test-time compute and efficient thinking
MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile DevicesEfficient LLM inference and serving → Serving systems and request scheduling
Measuring Semantic Information Production in Generative Diffusion ModelsDiffusion models → Diffusion foundations and sampling
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference AttacksLLM safety and security → Membership inference attacks
Can Sound Replace Vision in LLaVA With Token Substitution?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?LLM reasoning → Multimodal reasoning +1
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry ChallengesLLM reasoning → Knowledge- and tool-augmented reasoning +2
ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided DiffusionDiffusion models → Flow matching, time series and science
DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation ModelsState-space sequence models (S4, Mamba) → Vision Mamba backbones

All 378