Papers

New on arXiv

Thu 3 Jul 2025

306 papers

Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial AutomationLLM reasoning → Spatial and embodied reasoning +1
CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis TasksLLM reasoning → Reasoning for agents, planning and code
SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
Neural Inhibition Improves Dynamic Routing and Mixture of ExpertsMixture-of-experts → Expert routing strategies
Where Do Reasoning Models Refuse?LLM reasoning → Prompting and chain-of-thought reasoning +1
ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language ModelsLLM reasoning → Mathematical reasoning
Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing ObservationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic AgentsLLM reasoning → Audio-language model reasoning +2
ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Mitigating Goal Misgeneralization via Minimax RegretDeep reinforcement learning methods → Deep RL algorithms and representations
LATTE: Latent Trajectory Embedding for Diffusion-Generated Image DetectionDiffusion models → Diffusion foundations and sampling
Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy OptimizationLLM reasoning → Reasoning for agents, planning and code
Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual TuningLLM reasoning → LLM reasoning for recommendation
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive CachingDiffusion models → Video generation
Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model AdaptationLLM reasoning → Multimodal reasoning +2
AnyI2V: Animating Any Conditional Image with Motion ControlDiffusion models → Video generation
MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMsLLM reasoning → Reinforcement learning for reasoning
LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All UsersLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context InjectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to ReasonLLM reasoning → Reinforcement learning for reasoning +1
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
USAD: End-to-End Human Activity Recognition via Diffusion Model with Spatiotemporal AttentionDiffusion models → Video generation
Establishing Best Practices for Building Rigorous Agentic BenchmarksLLM agents and tool use → General LLM agent frameworks and benchmarks
SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language ModelLLM reasoning → Test-time compute and efficient thinking
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video DiffusionDiffusion models → 3D, point cloud and scene generation
Multimodal Mathematical Reasoning with Diverse Solving PerspectiveLLM reasoning → Multimodal reasoning
Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Moral Responsibility or Obedience: What Do We Want from AI?LLM agents and tool use → General LLM agent frameworks and benchmarks
Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMsLLM reasoning → Clinical and biomedical applications
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal AlignmentSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
DexVLG: Dexterous Vision-Language-Grasp Model at ScaleVision-language-action models → Human-video and latent-action pretraining
Meta SecAlign: A Secure Foundation LLM Against Prompt Injection AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem ProvingSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image GenerationDiffusion models → Image generation, text-to-image and editing
A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous ControlDeep reinforcement learning methods → Deep RL algorithms and representations
Your Mailbox Is Mine: Prompt Injection Attacks Against Real-World LLM Email AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
RLHGNN: Reinforcement Learning-driven Heterogeneous Graph Neural Network for Next Activity Prediction in Business ProcessesDeep reinforcement learning methods → RL for energy, networks and operations
APT: Adaptive Personalized Training for Diffusion Models with Limited DataDiffusion models → Image generation, text-to-image and editing
Learning few-step posterior samplers by unfolding and distillation of diffusion modelsDiffusion models → Inverse problems and image restoration
TUC-PPO: Team Utility-Constrained Proximal Policy Optimization for Spatial Public Goods GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
Hey AI, Generate Me a Hardware Code! Agentic AI-based Hardware Design & VerificationLLM agents and tool use → Software engineering coding agents
OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative DecodingEfficient LLM inference and serving → Speculative decoding
HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep SearchRetrieval-augmented generation → Agentic RAG, agents and memory
On Efficient Bayesian Exploration in Model-Based Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM InferenceEfficient LLM inference and serving → Speculative decoding
DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-MakingLLM agents and tool use → Medical and scientific domain agents
Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics EmulationDiffusion models → Flow matching, time series and science
AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion ModelsDiffusion models → Diffusion foundations and sampling
WebSailor: Navigating Super-human Reasoning for Web AgentLLM reasoning → Reasoning for agents, planning and code +1
Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic InterpretabilityMechanistic interpretability → Knowledge and representations inside LLMs
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchLLM agents and tool use → Web, search, and research agents
Clarifying Before Reasoning: A Coq Prover with Structural ContextLLM reasoning → Reasoning benchmarks and evaluation
CyberRAG: An Agentic RAG cyber attack classification and reporting toolRetrieval-augmented generation → Privacy and security of RAG +1
AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head AvatarsDiffusion models → 3D, point cloud and scene generation
Improving Consistency in Vehicle Trajectory Prediction Through Preference OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
PosDiffAE: Position-aware Diffusion Auto-encoder For High-Resolution Brain Tissue Classification Incorporating Artifact RestorationDiffusion models → Medical imaging and segmentation
Posterior Transition Modeling for Unsupervised Diffusion-Based Speech EnhancementDiffusion models → Audio, speech and music
Coling-UniA at SciVQA 2025: Few-Shot Example Retrieval and Confidence-Informed Ensembling for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Offline Reinforcement Learning with Penalized Action Noise InjectionDiffusion models → Diffusion and flow policies for robotics +1
OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM AgentLLM agents and tool use → Web, search, and research agents
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information LeakageLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features FeedbackDiffusion models → Image generation, text-to-image and editing
DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content GenerationDiffusion models → 3D, point cloud and scene generation
LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillationKnowledge distillation → Speech and audio distillation
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory AgentLLM reasoning → Reasoning for agents, planning and code
Uncertainty-aware Reward Design ProcessLLM reasoning → Reinforcement learning for reasoning
Listwise Preference Alignment Optimization for Tail Item RecommendationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
Scaling LLM Planning: NL2FLOW for Parametric Problem Generation and Rigorous EvaluationLLM reasoning → Reasoning for agents, planning and code
FMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
A comparative study of some wavelet and sampling operators on various features of an image
Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
Self-DANA: A Resource-Efficient Channel-Adaptive Self-Supervised Approach for ECG Foundation Models
Collective Communication Profiling of Modern-day Machine Learning Workloads
Analysing semantic data storage in Distributed Ledger Technologies for Data Spaces
A Fuzzy Supervisor Agent Design for Clinical Reasoning Assistance in a Multi-Agent Educational Clinical Scenario Simulation
LLMs and Fuzzing in Tandem: A New Approach to Automatically Generating Weakest Preconditions
An Adaptive Supervised Contrastive Learning Framework for Implicit Sexism Detection in Digital Social Networks
The role of gain neuromodulation in layer-5 pyramidal neurons
Symbiosis: Multi-Adapter Inference and Fine-Tuning
Development of an Improved Capsule-Yolo Network for Automatic Tomato Plant Disease Early Detection and Diagnosis
Disclosing Generative AI Use in Digital Humanities Research
DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
A Machine Learning Benchmarking Framework for Lipid Nanoparticle Transfection Efficiency Prediction
Weak Form Scientific Machine Learning: Test Function Construction for System Identification
AI-driven Web Application for Early Detection of Sudden Death Syndrome (SDS) in Soybean Leaves Using Hyperspectral Images and Genetic Algorithm
Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding
Quantifying Cognitive Bias Induction in LLM-Generated Content
Discovering Algorithms with Computational Language Processing
First Contact: Data-driven Friction-Stir Process Control
Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies
Understanding Knowledge Transferability for Transfer Learning: A Survey
Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data
Beyond SEO: A Transformer-Based Approach for Reinventing Web Content Optimisation

All 306