Papers

New on arXiv

Tue 5 Aug 2025

446 papers

RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech RecognitionRetrieval-augmented generation → Conversational and speech RAG
Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of ExpertsMixture-of-experts → Multimodal MoE models
Agoran: An Agentic Open Marketplace for 6G RAN AutomationLLM agents and tool use → Agentic AI for wireless networks
EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse ProblemsDiffusion models → Flow matching, time series and science
A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMsLLM reasoning → Mathematical reasoning
MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human ErasingDiffusion models → 3D, point cloud and scene generation
DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF BenchmarkLLM agents and tool use → Agent threats, guardrails and governance
LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Understanding protein function with a multimodal retrieval-augmented foundation modelRetrieval-augmented generation → Medical and biomedical RAG
Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTSLLM agents and tool use → General LLM agent frameworks and benchmarks
GeoFlow: Agentic Workflow Automation for Geospatial TasksLLM agents and tool use → Software engineering coding agents
Data and AI governance: Promoting equity, ethics, and fairness in large language modelsLLM safety and security → Safety alignment, refusal and guardrails
RAVID: Retrieval-Augmented Visual Detection: A Knowledge-Driven Approach for AI-Generated Image IdentificationRetrieval-augmented generation → Multimodal RAG
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?LLM reasoning → Time series reasoning
ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software AssistantsLLM safety and security → Prompt injection and agent security
Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion ModelDiffusion models → 3D, point cloud and scene generation
Comparing Normalization Methods for Portfolio Optimization with Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Sotopia-RL: Reward Design for Social IntelligenceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Reinforcement Learning in MDPs with Information-Ordered PoliciesDeep reinforcement learning methods → RL theory and sample complexity
An Entity Linking Agent for Question AnsweringLLM agents and tool use → Web, search, and research agents
Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized SafetyLLM agents and tool use → Agent threats, guardrails and governance
Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
MI9: An Integrated Runtime Governance Framework for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
Majority Bit-Aware Watermarking For Large Language ModelsLLM safety and security → Watermarking generated content and models
AttnTrace: Contextual Attribution of Prompt Injection and Knowledge CorruptionRetrieval-augmented generation → Privacy and security of RAG +1
HPSv3: Towards Wide-Spectrum Human Preference ScoreLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Probing and Enhancing the Robustness of GNN-based QEC Decoders with Reinforcement LearningDeep reinforcement learning methods → Quantum reinforcement learning
Do GNN-based QEC Decoders Require Classical Knowledge? Evaluating the Efficacy of Knowledge Distillation from MWPMKnowledge distillation → Graph neural network distillation
GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy ControlLLM reasoning → Reinforcement learning for reasoning +1
ORVIT: Near-Optimal Online Distributionally Robust Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
LiDARCrafter: Dynamic 4D World Modeling from LiDAR SequencesWorld models → World modeling from LiDAR generation
Veila: Panoramic LiDAR Generation from a Monocular RGB ImageWorld models → World modeling from LiDAR generation
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome RewardLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
Agent Lightning: Train ANY AI Agents with Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
A DbC Inspired Neurosymbolic Layer for Trustworthy Agent DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
Can Large Vision-Language Models Understand Multimodal Sarcasm?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Probing the Gaps in ChatGPT Live Video Chat for Real-World Assistance for People who are Blind or Visually ImpairedMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Improving Q-Learning for Real-World Control: A Case Study in Series Hybrid Agricultural TractorsDeep reinforcement learning methods → RL for energy, networks and operations
DiWA: Diffusion Policy Adaptation with World ModelsWorld models → Latent dynamics models and model-based RL +2
Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?Multimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
Likelihood Matching for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation FrameworkLLM reasoning → Reasoning for agents, planning and code
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-CorrectionSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided SchedulingEfficient LLM inference and serving → Serving systems and request scheduling
CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion modelsDiffusion models → Medical imaging and segmentation
LaTCoder: Converting Webpage Design to Code with Layout-as-ThoughtLLM reasoning → Multimodal reasoning
VRPRM: Process Reward Modeling via Visual ReasoningLLM reasoning → Reinforcement learning for reasoning +1
MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented GenerationRetrieval-augmented generation → Hallucination detection in RAG
Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal RepresentationsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation SteeringMechanistic interpretability → Activation steering methods
SLA-MORL: SLA-Aware Multi-Objective Reinforcement Learning for HPC Resource OptimizationDeep reinforcement learning methods → RL for energy, networks and operations
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +2
Error Detection and Correction for Interpretable Mathematics in Large Language ModelsLLM reasoning → Mathematical reasoning
CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video GenerationDiffusion models → Diffusion foundations and sampling
Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
VideoGuard: Protecting Video Content from Unauthorized EditingDiffusion models → Robustness, privacy and adversarial aspects
IKOD: Mitigating Visual Attention Degradation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head GenerationDiffusion models → Audio, speech and music
CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
An Auditable Agent Platform For Automated Molecular OptimisationLLM reasoning → Clinical and biomedical applications +1
LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft ThinkingLLM reasoning → Reasoning benchmarks and evaluation
SlotMatch: Distilling Object-Centric Representations for Unsupervised Video SegmentationKnowledge distillation → Detection and dense prediction distillation
Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time ScalingLLM reasoning → Multimodal reasoning +2
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow ModelsDiffusion models → Image generation, text-to-image and editing
Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving DiagnosisLLM reasoning → Mathematical reasoning +1
Agentic AI in 6G Software Businesses: A Layered Maturity ModelLLM agents and tool use → Software engineering coding agents
Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image RestorationDiffusion models → Inverse problems and image restoration
Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game PlayLLM reasoning → Reasoning for agents, planning and code
A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign InputsLLM safety and security → Audio jailbreaks and speech backdoors
Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
GL-LCM: Global-Local Latent Consistency Models for Fast High-Resolution Bone Suppression in Chest X-Ray ImagesDiffusion models → Medical imaging and segmentation
SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step EntropyLLM reasoning → Test-time compute and efficient thinking
Adaptive AI Agent Placement and Migration in Edge Intelligence SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
What Deserves Memory: Adaptive Memory Distillation for LLM AgentsLLM agents and tool use → Agent memory systems
Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph IntegrationMultimodal LLMs / vision-language models → Video understanding with MLLMs
Beyond Illumination: Fine-Grained Detail Preservation in Extreme Dark Image RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video GenerationDiffusion models → Video generation
CTTS: Collective Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking +1
Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents ApproachLLM agents and tool use → Software engineering coding agents
Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive ReviewKnowledge distillation → Detection and dense prediction distillation
V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion ModelsDiffusion models → Video generation
Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent DiffusionDiffusion models → Image generation, text-to-image and editing
Full-History Graphs with Edge-Type Decoupled Networks for Temporal ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
Conformal Unlearning: A New Paradigm for Unlearning in Conformal PredictorsLLM safety and security → Machine unlearning
BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Navigation Pixie: Implementation and Empirical Study Toward On-demand Navigation Agents in Commercial MetaverseLLM agents and tool use → Multimodal and embodied agents
Convergence of Deterministic and Stochastic Diffusion-Model Samplers: A Simple Analysis in Wasserstein DistanceDiffusion models → Diffusion foundations and sampling
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction FollowingLLM reasoning → Prompting and chain-of-thought reasoning
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early RevisionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary ConstructionsLLM reasoning → Spatial and embodied reasoning
Quantum Spectral Reasoning: A Non-Neural Architecture for Interpretable Machine LearningLLM reasoning → Reinforcement learning for reasoning
ChartCap: Mitigating Hallucination of Dense Chart CaptioningMultimodal LLMs / vision-language models → Chart understanding and anomaly detection

All 446