Papers

New on arXiv

Wed 23 Jul 2025

309 papers

PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
WaveVerify: A Novel Audio Watermarking Framework for Media Authentication and Combatting DeepfakesLLM safety and security → Watermarking generated content and models
Towards Unifying Quantitative Security Benchmarking for Multi Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
Agent WARPP: Workflow Adherence via Runtime Parallel PersonalizationLLM agents and tool use → Software engineering coding agents
Eyes Will Shut: A Vision-Based Next GPS Location Prediction Model by Reinforcement Learning from Visual Map Feed BackLLM reasoning → Spatial and embodied reasoning +1
Machine Unlearning of Traffic State Estimation and PredictionLLM safety and security → Machine unlearning
Evaluating the Performance of AI Text Detectors, Few-Shot and Chain-of-Thought Prompting Using DeepSeek Generated TextLLM reasoning → Reasoning benchmarks and evaluation
SMARTAPS: Tool-augmented LLMs for Operations ManagementLLM agents and tool use → General LLM agent frameworks and benchmarks
From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D ConsistencyDiffusion models → Medical imaging and segmentation
Action-List Reinforcement Learning Syndrome Decoding for Binary Linear Block CodesDeep reinforcement learning methods → Quantum reinforcement learning
I2I-STRADA -- Information to Insights via Structured Reasoning Agent for Data AnalysisLLM reasoning → Reasoning for agents, planning and code +1
Safe Reinforcement Learning-based Automatic Generation ControlDeep reinforcement learning methods → RL for energy, networks and operations
Detail++: Training-Free Detail Enhancer for T2I Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Dynamic and Generalizable Process Reward ModelingLLM reasoning → Reinforcement learning for reasoning +1
PinchBot: Long-Horizon Deformable Manipulation with Guided Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
GenSelect: A Generative Approach to Best-of-NLLM reasoning → Test-time compute and efficient thinking +1
LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic PredictionDiffusion models → Diffusion and flow policies for robotics
Hyperbolic Deep Learning for Foundation Models: A SurveyMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Reinforcement Learning for Accelerated Aerodynamic Shape OptimisationDeep reinforcement learning methods → RL with diffusion and flow models
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable DomainsDeep reinforcement learning methods → RL training of language and agent models
Yume: An Interactive World Generation ModelWorld models → Video-generation world models and simulators
Flow Matching Meets Biology and Life Science: A SurveyDiffusion models → Flow matching, time series and science
Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language ModelsMixture-of-experts → MoE large language models
Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool AugmentationsLLM reasoning → Test-time compute and efficient thinking +1
Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven NetworksLLM agents and tool use → Agentic AI for wireless networks
MCM: Mamba-based Cardiac Motion Tracking using Sequential Images in MRIState-space sequence models (S4, Mamba) → Mamba for medical image analysis
How Should We Meta-Learn Reinforcement Learning Algorithms?Deep reinforcement learning methods → Deep RL algorithms and representations
Perspective-Invariant 3D Object DetectionWorld models → World modeling from LiDAR generation
Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View MammographyMixture-of-experts → Medical and biomedical MoE +1
See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question AnsweringLLM reasoning → Multimodal reasoning +1
CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance ShiftsDiffusion models → Robustness, privacy and adversarial aspects
SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More TokenEfficient LLM inference and serving → Early exit and edge inference
PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
An h-space Based Adversarial Attack for Protection Against Few-shot PersonalizationDiffusion models → Robustness, privacy and adversarial aspects
CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
Anticipate, Simulate, Reason (ASR): A Comprehensive Generative AI Framework for Combating Messaging ScamsLLM reasoning → Reasoning for agents, planning and code
Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain ReasoningLLM reasoning → Clinical and biomedical applications +1
Generalized Advantage Estimation for Distributional Policy GradientsDeep reinforcement learning methods → RL theory and sample complexity
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to ManipulationLLM reasoning → Spatial and embodied reasoning +1
URPO: A Unified Reward & Policy Optimization Framework for Large Language ModelsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
Accelerating Parallel Diffusion Model Serving with Residual CompressionDiffusion models → Diffusion foundations and sampling
LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal ReasoningLLM reasoning → Reasoning benchmarks and evaluation
An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMsLLM reasoning → Reasoning benchmarks and evaluation
Probing Vision-Language Understanding through the Visual Entailment Task: promises and pitfallsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
ERMV: Editing 4D Robotic Multi-view images to enhance embodied agentsVision-language-action models → 3D and spatial-aware VLA +1
RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement LearningLLM reasoning → Clinical and biomedical applications
Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence ScoringLLM reasoning → Mathematical reasoning +1
Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Efficient and Robust Semantic Image Communication via Stable CascadeDiffusion models → Diffusion for compression and wireless
Millions of GeAR-s: Extending GraphRAG to Millions of DocumentsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Confidence Calibration in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
DeMo++: Motion Decoupling for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
Confounded Causal Imitation Learning with Instrumental VariablesOffline RL and imitation learning from data → Imitation learning methods
R-Stitch: Dynamic Trajectory Stitching for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking +1
A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language ModelLLM reasoning → Clinical and biomedical applications +1
PointLAMA: Latent Attention meets Mamba for Efficient Point Cloud PretrainingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile FeedbackVision-language-action models → Tactile, force-aware and humanoid VLA
Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise EnvironmentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Prolonging Tool Life: Learning Skillful Use of General-purpose Tools through Lifespan-guided Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Leveraging Knowledge Graphs and LLM Reasoning to Identify Operational Bottlenecks for Warehouse Planning AssistanceLLM reasoning → Reasoning for agents, planning and code
PolarAnything: Diffusion-based Polarimetric Image SynthesisDiffusion models → 3D, point cloud and scene generation
Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMsLLM safety and security → Membership inference attacks
Agent Identity Evals: Measuring Agentic IdentityLLM agents and tool use → General LLM agent frameworks and benchmarks
R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation SystemsLLM reasoning → LLM reasoning for recommendation
MaskedCLIP: Bridging the Masked and CLIP Space for Semi-Supervised Medical Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Medical vision-language models
Improving LLMs' Generalized Reasoning Abilities by Graph ProblemsLLM reasoning → Knowledge- and tool-augmented reasoning
SADA: Stability-guided Adaptive Diffusion AccelerationDiffusion models → Diffusion foundations and sampling
BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMsMixture-of-experts → Efficient MoE training and inference systems
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop GuidanceLLM agents and tool use → General LLM agent frameworks and benchmarks +1
BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference ServingEfficient LLM inference and serving → Serving systems and request scheduling
Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
ZORMS-LfD: Learning from Demonstrations with Zeroth-Order Random Matrix SearchOffline RL and imitation learning from data → Robot learning from demonstration
FedVLM: Scalable Personalized Vision-Language Models through Federated LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers
Detection of Autonomic Dysreflexia in Individuals With Spinal Cord Injury Using Multimodal Wearable Sensors
"Think First, Verify Always": Training Humans to Face AI Risks
On Improving PPG-Based Sleep Staging: A Pilot Study
Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models
Reproducibility of Machine Learning-Based Fault Detection and Diagnosis for HVAC Systems in Buildings: An Empirical Study
GNN-ASE: Graph-Based Anomaly Detection and Severity Estimation in Three-Phase Induction Machines
Multi-Relation Extraction in Entity Pairs using Global Context
Using Sentiment Analysis to Investigate Peer Feedback by Native and Non-Native English Speakers
Advancing Wildfire Risk Prediction via Morphology-Aware Curriculum Contrastive Learning
Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents
The Geometry of Harmfulness in LLMs through Subconcept Probing
Fuzzy Theory in Computer Vision: A Review
VGS-ATD: Robust Distributed Learning for Multi-Label Medical Image Classification Under Heterogeneous and Imbalanced Conditions
Synthesis of timeline-based planning strategies avoiding determinization
Bearded Dragon Activity Recognition Pipeline: An AI-Based Approach to Behavioural Monitoring
How K-12 Educators Use AI: LLM-Assisted Qualitative Analysis at Scale
Machine Learning Workflow for Analysis of High-Dimensional Order Parameter Space: A Case Study of Polymer Crystallization from Molecular Dynamics Simulations
SIFOTL: A Principled, Statistically-Informed Fidelity-Optimization Method for Tabular Learning
MeAJOR Corpus: A Multi-Source Dataset for Phishing Email Detection

All 309