Papers

New on arXiv

Fri 25 Jul 2025

308 papers

Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language modelsRetrieval-augmented generation → Medical and biomedical RAG
Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, ScissorsLLM reasoning → Reasoning for agents, planning and code
AquiLLM: a RAG Tool for Capturing Tacit Knowledge in Research GroupsRetrieval-augmented generation → RAG pipeline design and evaluation
Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought ProcessesLLM reasoning → Test-time compute and efficient thinking
A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom DocumentsRetrieval-augmented generation → Multimodal RAG
CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-AnsweringMixture-of-experts → MoE large language models
From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
OneShield -- the Next Generation of LLM GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
Generating Adversarial Point Clouds Using Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
MAC: Masked Agent Collaboration Boosts Large Language Model Medical Decision-MakingLLM agents and tool use → Medical and scientific domain agents
Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Ultracoarse Equilibria and Ordinal-Folding Dynamics in Operator-Algebraic Models of Infinite Multi-Agent GamesLLM agents and tool use → Social simulation and multi-agent debate
KD-GAT: Combining Knowledge Distillation and Graph Attention Transformer for a Controller Area Network Intrusion Detection SystemKnowledge distillation → Detection and dense prediction distillation
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging ChallengesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
Reward-Augmented Reinforcement Learning for Continuous Control in Precision Autonomous Parking via Policy Optimization MethodsDeep reinforcement learning methods → RL for autonomous driving and traffic
Efficient and Scalable Agentic AI with Heterogeneous SystemsLLM agents and tool use → Software engineering coding agents
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific TalksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Quantum Reinforcement Learning by Adaptive Non-local ObservablesDeep reinforcement learning methods → Quantum reinforcement learning
MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis OptimizationLLM agents and tool use → Software engineering coding agents
Joint Feature and Output Distillation for Low-complexity Acoustic Scene ClassificationKnowledge distillation → Speech and audio distillation
Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI AgentsLLM agents and tool use → GUI and mobile agents
Back to the Features: DINO as a Foundation for Video World ModelsWorld models → Video-generation world models and simulators
Hierarchical Deep Reinforcement Learning Framework for Multi-Year Asset Management Under Budget ConstraintsDeep reinforcement learning methods → RL for energy, networks and operations
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective DecodingMixture-of-experts → Efficient MoE training and inference systems
Modality Agnostic Efficient Long Range EncoderEfficient LLM inference and serving → Early exit and edge inference
LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User PreferencesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
EffiComm: Bandwidth Efficient Multi Agent CommunicationMixture-of-experts → Vision mixture-of-experts
Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized GroupsDiffusion models → Video generation
RemoteReasoner: Towards Unifying Geospatial Reasoning WorkflowLLM reasoning → Spatial and embodied reasoning
Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible PerceptionKnowledge distillation → Detection and dense prediction distillation
OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFVDeep reinforcement learning methods → RL for energy, networks and operations
Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text GenerationLLM reasoning → Reasoning for agents, planning and code +3
PRE-MAP: Personalized Reinforced Eye-tracking Multimodal LLM for High-Resolution Multi-Attribute Point PredictionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Comparison of Knowledge Distillation Methods for Low-complexity Multi-microphone Speech Enhancement using the FT-JNF ArchitectureKnowledge distillation → Speech and audio distillation
Joint Holistic and Lesion Controllable Mammogram Synthesis via Gated Conditional Diffusion ModelDiffusion models → Medical imaging and segmentation
Towards Multimodal Social Conversations with Robots: Using Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?LLM safety and security → Safety alignment, refusal and guardrails
Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRIDiffusion models → Medical imaging and segmentation
Diverse and Adaptive Behavior Curriculum for Autonomous Driving: A Student-Teacher Framework with Multi-Agent RLEnd-to-end autonomous driving → Reinforcement learning for driving
A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous IntegrationMixture-of-experts → Efficient MoE training and inference systems
RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-ResolutionDiffusion models → Inverse problems and image restoration
OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?LLM agents and tool use → GUI and mobile agents
LISA: A Layer-wise Integration and Suppression Approach for Hallucination Mitigation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow MatchingDiffusion models → Medical imaging and segmentation
Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model AgentsLLM agents and tool use → Social simulation and multi-agent debate
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware RefinementDiffusion models → Discrete and text diffusion
Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained ExpertsMixture-of-experts → Mixture of LoRA experts
SP-Mamba: Spatial-Perception State Space Model for Unsupervised Medical Anomaly DetectionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Cross-Subject Mind Decoding from Inaccurate RepresentationsDiffusion models → Medical imaging and segmentation
Negation-Aware Test-Time Adaptation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
PurpCode: Reasoning for Safer Code GenerationLLM reasoning → Reasoning for agents, planning and code
A New One-Shot Federated Learning Framework for Medical Imaging Classification with Feature-Guided Rectified Flow and Knowledge DistillationDiffusion models → Robustness, privacy and adversarial aspects +1
MLLM-based Speech Recognition: When and How is Multimodality Beneficial?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code GenerationRetrieval-augmented generation → RAG for code
ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offsKnowledge distillation → Graph neural network distillation
A Survey of Multimodal Hallucination Evaluation and DetectionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU ClusterMixture-of-experts → MoE in reinforcement learning and robotics
A diffusion-based generative model for financial time series via geometric Brownian motionDiffusion models → Flow matching, time series and science
Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image AlignmentLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-ResolutionState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced RecommendationsLLM agents and tool use → Agentic recommender systems
Reinforcement Learning via Conservative Agent for Environments with Random DelaysDeep reinforcement learning methods → Deep RL algorithms and representations
A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool AggregationLLM reasoning → Mathematical reasoning
SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered AgentsLLM agents and tool use → Software engineering coding agents
PDT: Point Distribution Transformation with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG TasksLLM reasoning → Multimodal reasoning
MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion RecognitionMultimodal LLMs / vision-language models → Multimodal emotion understanding
Uncovering Cross-Linguistic Disparities in LLMs using Sparse AutoencodersMechanistic interpretability → SAE features and their applications
A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future DirectionsRetrieval-augmented generation → RAG pipeline design and evaluation
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?LLM agents and tool use → Web, search, and research agents
MindFlow+: A Self-Evolving Agent for E-Commerce Customer ServiceLLM agents and tool use → General LLM agent frameworks and benchmarks +1
Success in Humanoid Reinforcement Learning under Partial ObservationDeep reinforcement learning methods → RL for robot locomotion and manipulation
PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
Physics-Informed Regression: Parameter Estimation in Parameter-Linear Nonlinear Dynamic Models
Computing with Canonical Microcircuits
The ISLab Solution to the Algonauts Challenge 2025: A Multimodal Deep Learning Approach to Brain Response Prediction
AI Guided Accelerator For Search Experience
Learning from B Cell Evolution: Adaptive Multi-Expert Diffusion for Antibody Design via Online Optimization
Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
Generative Logic: A New Computer Architecture for Deterministic Reasoning and Knowledge Generation
Opacity as Authority: Arbitrariness and the Preclusion of Contestation
A chart review process aided by natural language processing and multi-wave adaptive sampling to expedite validation of code-based algorithms for large database studies
SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology
PARROT: An Open Multilingual Radiology Reports Dataset
CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback
Multi-fidelity Bayesian Data-Driven Design of Energy Absorbing Spinodoid Cellular Structures
Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
Trustworthy AI: UK Air Traffic Control Revisited
Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
ChartM3: Benchmarking Chart Editing with Multimodal Instructions
The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models
Querying GI Endoscopy Images: A VQA Approach

All 308