Papers

New on arXiv

Tue 1 Jul 2025

314 papers

FreqCross: A Multi-Modal Frequency-Spatial Fusion Network for Robust Detection of Stable Diffusion 3.5 Generated ImagesDiffusion models → Image generation, text-to-image and editing
MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy OptimizationLLM reasoning → Clinical and biomedical applications
`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm ContextsLLM safety and security → Safety alignment, refusal and guardrails
GAF-Guard: An Agentic Framework for Risk Management and Governance in Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-ThoughtLLM reasoning → Multimodal reasoning +1
We Need Knowledge Distillation for Solving Math Word ProblemsKnowledge distillation → Knowledge distillation for LLMs
Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
STELLA: Self-Evolving LLM Agent for Biomedical ResearchLLM agents and tool use → Medical and scientific domain agents
Unsupervised Cardiac Video Translation Via Motion Feature Guided Diffusion ModelDiffusion models → Medical imaging and segmentation
Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Temporal Chain of Thought: Long-Video Understanding by Thinking in FramesLLM reasoning → Multimodal reasoning +1
Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network TroubleshootingLLM agents and tool use → Agentic AI for wireless networks
Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Rethinking the Illusion of ThinkingLLM reasoning → Test-time compute and efficient thinking
Diffusion Explorer: Interactive Exploration of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Imitation Learning for Satellite Attitude Control under Unknown PerturbationsOffline RL and imitation learning from data → Imitation learning methods +1
Geometry-aware 4D Video Generation for Robot ManipulationWorld models → Embodied and robot world models
MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAGRetrieval-augmented generation → RAG pipeline design and evaluation
Agentic AI in Product Management: A Co-Evolutionary ModelLLM agents and tool use → Software engineering coding agents
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action TokenizersVision-language-action models → Efficient VLA inference and adaptation
DAM-VSR: Disentanglement of Appearance and Motion for Video Super-ResolutionDiffusion models → Inverse problems and image restoration
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement LearningLLM reasoning → Multimodal reasoning +1
DMCIE: Diffusion Model with Concatenation of Inputs and Errors to Improve the Accuracy of the Segmentation of Brain Tumors in MRI ImagesDiffusion models → Medical imaging and segmentation
Enhancing LLM Agent Safety via Causal Influence PromptingLLM agents and tool use → Agent threats, guardrails and governance
Reasoning as an Adaptive Defense for SafetyLLM reasoning → Reasoning for agents, planning and code +1
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
From Sentences to Sequences: Rethinking Languages in Biological SystemLLM reasoning → Clinical and biomedical applications
Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal ImpactLLM reasoning → Reasoning benchmarks and evaluation
WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv TasksLLM agents and tool use → Web, search, and research agents
A Survey: Learning Embodied Intelligence from Physical Simulators and World ModelsWorld models → World models for navigation
Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and ApplicationsLLM agents and tool use → Multimodal and embodied agents
ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and BeyondLLM reasoning → Spatial and embodied reasoning +1
UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile AgentsLLM safety and security → Jailbreaking
HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM ReasoningLLM reasoning → Spatial and embodied reasoning
CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMsLLM reasoning → Reasoning for agents, planning and code +1
Many LLMs Are More Utilitarian Than OneLLM reasoning → Reasoning benchmarks and evaluation
VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible AcceleratorEfficient LLM inference and serving → KV cache optimization
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior SamplingDiffusion models → Inverse problems and image restoration
OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token SelectionDiffusion models → Image generation, text-to-image and editing +1
LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative WritingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning EnvironmentsDeep reinforcement learning methods → RL for games and combinatorial optimization
A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate ModelDiffusion models → Flow matching, time series and science
Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMsLLM reasoning → Multimodal reasoning
Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement LearningLLM reasoning → Multimodal reasoning +1
Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning ChessLLM reasoning → Reasoning for agents, planning and code
Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic TurbulenceDiffusion models → Flow matching, time series and science
Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectoriesLLM reasoning → Test-time compute and efficient thinking
TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in EnglishMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
A Test-Function Approach to Incremental StabilityDeep reinforcement learning methods → RL theory and sample complexity
Walk Like Dogs: Learning Steerable Imitation Controllers for Legged Robots from Unlabeled Motion DataOffline RL and imitation learning from data → Real-world robot offline RL
Harnessing the Power of Reinforcement Learning for Adaptive MCMCDeep reinforcement learning methods → RL theory and sample complexity
SAFER: Probing Safety in Reward Models with Sparse AutoencoderLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Generative Exaggeration in LLM Social Agents: Consistency, Bias, and ToxicityLLM agents and tool use → Social simulation and multi-agent debate
Generalization performance of narrow one-hidden layer networks in the teacher-student settingKnowledge distillation → General knowledge distillation methods
Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in RoboticsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive StrategiesLLM reasoning → Prompting and chain-of-thought reasoning
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World ModelWorld models → World models for autonomous driving +1
Quantum Circuit Structure Optimization for Quantum Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
BadViM: Backdoor Attack against Vision MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision SupportLLM agents and tool use → Agentic recommender systems
Box-QAymo: Box-Referring VQA Dataset for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web BrowsersRetrieval-augmented generation → Vector search and ANN indexes
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher SamplingDeep reinforcement learning methods → Deep RL algorithms and representations
TeamCMU at Touch'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational SearchRetrieval-augmented generation → Privacy and security of RAG
SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Laplace-Mamba: Laplace Frequency Prior-Guided Mamba-CNN Fusion Network for Image DehazingState-space sequence models (S4, Mamba) → Mamba for image restoration
Just Noticeable Difference for Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
PNAct: Crafting Backdoor Attacks in Safe Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-trainingRetrieval-augmented generation → RAG robustness and adaptive retrieval
Bisecle: Binding and Separation in Continual Learning for Video Language UnderstandingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Parameter-aware high-fidelity microstructure generation using stable diffusionDiffusion models → Flow matching, time series and science
Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face RestorationDiffusion models → Inverse problems and image restoration
Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular DesignDiffusion models → Flow matching, time series and science
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM ReasoningLLM reasoning → Mathematical reasoning
DiGA3D: Coarse-to-Fine Diffusional Propagation of Geometry and Appearance for Versatile 3D InpaintingDiffusion models → 3D, point cloud and scene generation
Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated LearningLLM safety and security → Federated unlearning and poisoning
ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-ContextLLM reasoning → Knowledge- and tool-augmented reasoning
Evo-0: Vision-Language-Action Model with Implicit Spatial UnderstandingVision-language-action models → 3D and spatial-aware VLA
Diffusion Disambiguation Models for Partial Label LearningDiffusion models → Diffusion foundations and sampling
MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoEMixture-of-experts → MoE large language models
Causal Prompting for Implicit Sentiment Analysis with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
iPanda: An LLM-based Agent for Automated Conformance Testing of Communication ProtocolsLLM agents and tool use → Software engineering coding agents
MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image SynthesisDiffusion models → Medical imaging and segmentation
Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning ProblemsDeep reinforcement learning methods → RL for games and combinatorial optimization
Question Decomposition for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Steering Protein Language Models
QU-NLP at CheckThat! 2025: Multilingual Subjectivity in News Articles Detection using Feature-Augmented Transformer Models with Sequential Cross-Lingual Fine-Tuning
The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis
Strongly Solving 7 × 6 Connect-Four on Consumer Grade Hardware
Kronecker-factored Approximate Curvature (KFAC) From Scratch
EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement
Learning Beyond Euclid: Curvature-Adaptive Generalization for Neural Networks on Manifolds
A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies
What to Do Next? Memorizing skills from Egocentric Instructional Video
Text-Guided Multi-Instance Learning for Scoliosis Screening via Gait Video Analysis

All 314