Papers

New on arXiv

Wed 2 Jul 2025

324 papers

Discrete Diffusion Models for Language GenerationDiffusion models → Discrete and text diffusion
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across DomainsDeep reinforcement learning methods → Deep RL algorithms and representations
Look-Back: Implicit Visual Re-focusing in MLLM ReasoningLLM reasoning → Multimodal reasoning +1
OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question AnsweringLLM agents and tool use → Web, search, and research agents +1
Subversion via Focal Points: Investigating Collusion in LLM MonitoringLLM safety and security → Safety alignment, refusal and guardrails
Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMsLLM reasoning → Clinical and biomedical applications
ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
Latent Chain-of-Thought? Decoding the Depth-Recurrent TransformerLLM reasoning → Prompting and chain-of-thought reasoning
Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human TrustLLM agents and tool use → Social simulation and multi-agent debate
cVLA: Towards Efficient Camera-Space VLAsVision-language-action models → Generalist VLA models and benchmarks
Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language ModelsLLM agents and tool use → Software engineering coding agents
Data Diversification Methods In Alignment Enhance Math Performance In LLMsLLM reasoning → Mathematical reasoning +1
Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM SystemLLM reasoning → Reasoning for agents, planning and code +1
Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue SummarizationLLM reasoning → Reasoning benchmarks and evaluation
Generative Latent Diffusion for Efficient Spatiotemporal Data ReductionDiffusion models → Diffusion foundations and sampling
Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion FrameworkDiffusion models → Flow matching, time series and science
The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender SystemsLLM agents and tool use → Agentic recommender systems
Energy-Based Transformers are Scalable Learners and ThinkersLLM reasoning → Test-time compute and efficient thinking
Sample Complexity Bounds for Linear Constrained MDPs with a Generative ModelDeep reinforcement learning methods → RL theory and sample complexity
GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant AdaptersDiffusion models → Flow matching, time series and science
Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMsLLM reasoning → Test-time compute and efficient thinking
RoboBrain 2.0 Technical ReportMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile ManipulationDiffusion models → Diffusion and flow policies for robotics
Locality-aware Parallel Decoding for Efficient Autoregressive Image GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Test-Time Scaling with Reflective Generative ModelLLM reasoning → Test-time compute and efficient thinking
Kwai Keye-VL Technical ReportMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
A Survey on Vision-Language-Action Models: An Action Tokenization PerspectiveVision-language-action models → VLA architectures and generalization
NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning TasksLLM reasoning → Prompting and chain-of-thought reasoning +1
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual ReasoningLLM reasoning → Multimodal reasoning +1
AI4Research: A Survey of Artificial Intelligence for Scientific ResearchLLM reasoning → Knowledge- and tool-augmented reasoning
MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher AssistantsLLM reasoning → Prompting and chain-of-thought reasoning
Bridging UI Design and chatbot Interactions: Applying Form-Based Principles to Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning AgentsWorld models → Latent dynamics models and model-based RL +1
HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing SupervisionLLM reasoning → Spatial and embodied reasoning
How Do Vision-Language Models Process Conflicting Information Across Modalities?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image SynthesisLLM reasoning → Multimodal reasoning
Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-TrainingLLM safety and security → Backdoor and data poisoning attacks
SE(3)-Equivariant Diffusion Policy in Spherical Fourier SpaceDiffusion models → Diffusion and flow policies for robotics
Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AILLM agents and tool use → Web, search, and research agents
AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on HarmfulnessLLM reasoning → Reasoning benchmarks and evaluation +1
Exploring Advanced LLM Multi-Agent Systems Based on Blackboard ArchitectureLLM agents and tool use → General LLM agent frameworks and benchmarks
GPT, But Backwards: Exactly Inverting Language Model OutputsLLM safety and security → Machine unlearning
Blending Supervised and Reinforcement Fine-Tuning with Prefix SamplingLLM reasoning → Reinforcement learning for reasoning
Facial Emotion Learning with Text-Guided Multiview Fusion via Vision-Language Model for 3D/4D Facial Expression RecognitionMultimodal LLMs / vision-language models → Multimodal emotion understanding
SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature RefinementMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking RecoveryLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth EstimationDiffusion models → 3D, point cloud and scene generation
Data Agent: A Holistic Architecture for Orchestrating Data+AI EcosystemsLLM agents and tool use → Web, search, and research agents
A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic SegmentationDiffusion models → Inverse problems and image restoration
Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +2
MARVIS: Modality Adaptive Reasoning over VISualizationsLLM reasoning → Multimodal reasoning
TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Chargax: A JAX Accelerated EV Charging SimulatorDeep reinforcement learning methods → RL for energy, networks and operations
Loss Functions in Diffusion Models: A Comparative StudyDiffusion models → Diffusion foundations and sampling
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore MechanismLLM reasoning → Reasoning for agents, planning and code +2
Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention AdaptationDiffusion models → Image generation, text-to-image and editing
AVC-DPO: Aligned Video Captioning via Direct Preference OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +2
BioMARS: A Multi-Agent Robotic System for Autonomous Biological ExperimentsLLM agents and tool use → Medical and scientific domain agents
Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual DisabilitiesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoalsDeep reinforcement learning methods → Deep RL algorithms and representations
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You ThinkDiffusion models → Diffusion foundations and sampling
LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token SpeculationEfficient LLM inference and serving → Speculative decoding
Using multi-agent architecture to mitigate the risk of LLM hallucinationsLLM agents and tool use → Medical and scientific domain agents
EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge DevicesEfficient LLM inference and serving → Serving systems and request scheduling
DiffMark: Diffusion-based Robust Watermark Against DeepfakesDiffusion models → Robustness, privacy and adversarial aspects +1
TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot ControlWorld models → Embodied and robot world models +4
DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow RemovalDiffusion models → 3D, point cloud and scene generation
Reinforcement Learning for Discrete-time LQG Mean Field Social Control Problems with Unknown DynamicsDeep reinforcement learning methods → RL for games and combinatorial optimization
Evaluating LLM Agent Collusion in Double AuctionsLLM agents and tool use → Financial trading and forecasting agents
MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video ParsingState-space sequence models (S4, Mamba) → Speech and audio SSMs
Distributional Soft Actor-Critic with Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics +1
RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV SwarmsLLM agents and tool use → Multimodal and embodied agents
AI Agents and Agentic AI-Navigating a Plethora of Concepts for Future ManufacturingLLM agents and tool use → General LLM agent frameworks and benchmarks
Activation Reward Models for Few-Shot Model AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet DiffusionDiffusion models → Flow matching, time series and science
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI SynergyLLM reasoning → Reinforcement learning for reasoning +1
Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMsLLM reasoning → Spatial and embodied reasoning
Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling StrategyLLM reasoning → Reinforcement learning for reasoning +1
ICLShield: Exploring and Mitigating In-Context Learning Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based AgentLLM agents and tool use → Software engineering coding agents
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball InpaintingDiffusion models → 3D, point cloud and scene generation
Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive BenchmarksRetrieval-augmented generation → RAG robustness and adaptive retrieval
VLAD: A VLM-Augmented Autonomous Driving Framework with Hierarchical Planning and Interpretable Decision ProcessMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven SummarizationLLM reasoning → Knowledge- and tool-augmented reasoning +1
Evaluating Large Language Models for Multimodal Simulated Ophthalmic Decision-Making in Diabetic Retinopathy and Glaucoma ScreeningLLM reasoning → Clinical and biomedical applications
Frequency Domain-Based Diffusion Model for Unpaired Image DehazingDiffusion models → Inverse problems and image restoration
PULSE: Practical Evaluation Scenarios for Large Multimodal Model UnlearningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
LLM-based Realistic Safety-Critical Driving Video GenerationEnd-to-end autonomous driving → Large language models for driving
Multimodal Chip Physical Design Engineer Assistant
Artificial intelligence for sustainable wine industry: AI-driven management in viticulture, wine production and enotourism
Graph Convolutional Neural Networks to Model the Brain for Insomnia
Tangma: A Tanh-Guided Activation Function with Learnable Parameters
NLP Meets the World: Toward Improving Conversations With the Public About Natural Language Processing Research
Distributed Training under Packet Loss
System Filter-Based Common Components Modeling for Cross-Subject EEG Decoding

All 324