Papers

New on arXiv

Thu 31 Jul 2025

313 papers

Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process DiagnosisLLM reasoning → Multimodal reasoning +1
From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge BaseRetrieval-augmented generation → RAG pipeline design and evaluation
GanitBench: A bi-lingual benchmark for evaluating mathematical reasoning in Vision Language ModelsLLM reasoning → Multimodal reasoning +1
StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region HarmonizationDiffusion models → Image generation, text-to-image and editing
CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement LearningLLM reasoning → Clinical and biomedical applications +1
Optimizing Vision-Language Consistency via Cross-Layer Regional Attention AlignmentMultimodal LLMs / vision-language models → Visual token pruning and efficiency
LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought MonitoringLLM reasoning → Prompting and chain-of-thought reasoning
Latent Diffusion Based Face Enhancement under Degraded Conditions for Forensic Face RecognitionDiffusion models → Inverse problems and image restoration
BarlowWalk: Self-supervised Representation Learning for Legged Robot Terrain-adaptive LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Measuring Harmfulness of Computer-Using AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy OptimizationLLM reasoning → Reinforcement learning for reasoning
Tabular Data Understanding with LLMs: A Survey of Recent Advances and ChallengesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation SystemsDeep reinforcement learning methods → RL training of language and agent models
Comparison of Large Language Models for Deployment RequirementsMixture-of-experts → MoE large language models
RL as Regressor: A Reinforcement Learning Approach for Function ApproximationDeep reinforcement learning methods → Interpretable and logic-guided RL
Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMsLLM safety and security → Backdoor and data poisoning attacks
GeoExplorer: Active Geo-localization with Curiosity-Driven ExplorationDeep reinforcement learning methods → RL for robot navigation and UAV control
INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural NetworksDeep reinforcement learning methods → RL for games and combinatorial optimization
Hyperproperty-Constrained Secure Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
A Survey on Code Generation with LLM-based AgentsLLM agents and tool use → Software engineering coding agents
Rethinking Evidence Hierarchies in Medical Language Benchmarks: A Critical Evaluation of HealthBenchLLM reasoning → Clinical and biomedical applications
PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics ProblemsLLM reasoning → Spatial and embodied reasoning
Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable DomainsDeep reinforcement learning methods → Deep RL algorithms and representations
Gaussian Variation Field Diffusion for High-fidelity Video-to-4D SynthesisDiffusion models → 3D, point cloud and scene generation
Phi-Ground Tech Report: Advancing Perception in GUI GroundingLLM reasoning → Multimodal reasoning +1
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative DecodingEfficient LLM inference and serving → Speculative decoding
General Agentic Planning Through Simulative Reasoning with World ModelsWorld models → World models for language agents +2
SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian SplattingLLM reasoning → Spatial and embodied reasoning
Slot Attention with Re-Initialization and Self-DistillationKnowledge distillation → Detection and dense prediction distillation
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasksLLM reasoning → Prompting and chain-of-thought reasoning +1
Distributed AI Agents for Cognitive Underwater Robot AutonomyLLM agents and tool use → Multimodal and embodied agents
Seed-Prover: Deep and Broad Reasoning for Automated Theorem ProvingLLM reasoning → Mathematical reasoning
DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape MatchingDiffusion models → 3D, point cloud and scene generation
Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
A survey of multi-agent geosimulation methodologies: from ABM to LLMLLM agents and tool use → Multimodal and embodied agents
UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image RestorationDiffusion models → Inverse problems and image restoration
I2V-GS: Infrastructure-to-Vehicle View Transformation with Gaussian Splatting for Autonomous Driving Data GenerationEnd-to-end autonomous driving → Generative simulation for driving
villa-X: Enhancing Latent Action Modeling in Vision-Language-Action ModelsWorld models → Embodied and robot world models +1
One-Step Flow Policy Mirror DescentDiffusion models → Diffusion and flow policies for robotics +1
MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided QueryingLLM agents and tool use → Agent memory systems
DivControl: Knowledge Diversion for Controllable Image GenerationDiffusion models → Image generation, text-to-image and editing
Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object DetectionState-space sequence models (S4, Mamba) → Vision Mamba backbones
MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar ReconstructionDiffusion models → 3D, point cloud and scene generation
Can LLM-Reasoning Models Replace Classical Planning? A Benchmark StudyLLM reasoning → Spatial and embodied reasoning
GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +2
Semantic Chain-of-Trust: Autonomous Trust Orchestration for Collaborator Selection via Hypergraph-Aided Agentic AILLM agents and tool use → Agent threats, guardrails and governance
Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic PlatformDeep reinforcement learning methods → Spiking and neuromorphic RL
DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge TransferLLM agents and tool use → General LLM agent frameworks and benchmarks
Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement LearningLLM reasoning → Clinical and biomedical applications +1
A Unified Perception-Language-Action Framework for Adaptive Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
H-RDT: Human Manipulation Enhanced Bimanual Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics +1
Adaptive Ensemble Aggregation for Actor-CriticsDeep reinforcement learning methods → RL theory and sample complexity
Causal Reasoning in Pieces: Modular In-Context Learning for Causal DiscoveryLLM reasoning → Causal reasoning in LLMs
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene UnderstandingLLM reasoning → Spatial and embodied reasoning +1
Role-Aware Language Models for Secure and Contextualized Access Control in OrganizationsLLM safety and security → Prompt injection and agent security
Mitigating Resolution-Drift in Federated Learning: Case of Keypoint DetectionKnowledge distillation → Federated, robust and private distillation
Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation SystemsLLM safety and security → Prompt injection and agent security
Adjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion ModelsDiffusion models → Flow matching, time series and science
Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style ClassificationKnowledge distillation → General knowledge distillation methods
Policy Learning from Large Vision-Language Model Feedback without Reward ModelingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Multi-Prompt Progressive Alignment for Multi-Source Unsupervised Domain AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
VMatcher: State-Space Semi-Dense Local Feature MatchingState-space sequence models (S4, Mamba) → Vision Mamba backbones
Trae Agent: An LLM-based Agent for Software Engineering with Test-time ScalingLLM reasoning → Reasoning for agents, planning and code +1
Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant LayersMultimodal LLMs / vision-language models → Visual token pruning and efficiency
SWE-Debate: Competitive Multi-Agent Debate for Software Issue ResolutionLLM reasoning → Reasoning for agents, planning and code +1
Learning to Drift with Individual Wheel Drive: Maneuvering Autonomous Vehicle at the Handling LimitsEnd-to-end autonomous driving → Reinforcement learning for driving +1
DSBC : Data Science task Benchmarking with Context engineeringLLM agents and tool use → Web, search, and research agents
MUST-RAG: MUSical Text Question Answering with Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World ModelsWorld models → World models for autonomous driving +1
FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token PruningVision-language-action models → VLA for autonomous driving +2
Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math LearnerLLM reasoning → Reinforcement learning for reasoning
The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image ModelsDiffusion models → Image generation, text-to-image and editing
Training-free Geometric Image Editing on Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Evaluating the Dynamics of Membership Privacy in Deep LearningLLM safety and security → Membership inference attacks
Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Unveiling Super Experts in Mixture-of-Experts Large Language ModelsMixture-of-experts → MoE large language models
PixNerd: Pixel Neural Field DiffusionDiffusion models → Diffusion foundations and sampling
DynaSwarm: Dynamically Graph Structure Selection for LLM-based Multi-agent SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
Efficient Machine Unlearning via Influence ApproximationLLM safety and security → Machine unlearning
P-ReMIS: Pragmatic Reasoning in Mental Health and a Social ImplicationLLM reasoning → Clinical and biomedical applications
Annotation-Free Reinforcement Learning Query Rewriting via Verifiable Search RewardRetrieval-augmented generation → Agentic RAG, agents and memory +1
Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry ExploitationRetrieval-augmented generation → Privacy and security of RAG
Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
Adversarial-Guided Diffusion for Multimodal LLM AttacksDiffusion models → Robustness, privacy and adversarial aspects
Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics TasksDeep reinforcement learning methods → RL for robot locomotion and manipulation
BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and ReasoningLLM reasoning → Test-time compute and efficient thinking
Computational Resolution of Hadamard Product Factorization for 4 × 4 Matrices
From Image Captioning to Visual Storytelling
Vibe2Spike: Batteryless Wireless Tags for Vibration Sensing with Event Cameras and Spiking Networks
Uncovering Latent Connections in Indigenous Heritage: Semantic Pipelines for Cultural Preservation in Brazil
Data-driven global ocean model resolving ocean-atmosphere coupling dynamics
To Theoretically Understand Transformer-Based In-Context Learning for Optimizing CSMA
MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer
Zero-Shot Retrieval for Scalable Visual Search in a Two-Sided Marketplace
A Modified VGG19-Based Framework for Accurate and Interpretable Real-Time Bone Fracture Detection
Improve Retinal Artery/Vein Classification via Channel Couplin
Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapping in Smart Cities

All 313