Papers

New on arXiv

Wed 13 Aug 2025

334 papers

Methodological Framework for Quantifying Semantic Test Coverage in RAG SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMsLLM reasoning → Prompting and chain-of-thought reasoning
CrystalDiT: A Diffusion Transformer for Crystal GenerationDiffusion models → Flow matching, time series and science
Persuasiveness and Bias in LLM: Investigating the Impact of Persuasiveness and Reinforcement of Bias in Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
Benchmarking the Medical Understanding and Reasoning of Large Language Models in Arabic Healthcare TasksLLM reasoning → Clinical and biomedical applications
EEGDM: EEG Representation Learning via Generative Diffusion ModelDiffusion models → Medical imaging and segmentation
Apriel-Nemotron-15B-ThinkerLLM reasoning → Test-time compute and efficient thinking
MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical TextLLM reasoning → Clinical and biomedical applications
Non-asymptotic convergence bound of conditional diffusion modelsDiffusion models → Diffusion foundations and sampling
Mo' Memory, Mo' Problems: Stream-Native Machine UnlearningLLM safety and security → Machine unlearning
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning ProblemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Benchmark-Driven Selection of AI: Evidence from DeepSeek-R1LLM reasoning → Reasoning benchmarks and evaluation
SynSpill: Improved Industrial Spill Detection With Synthetic DataMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference OptimizationLLM reasoning → Test-time compute and efficient thinking +1
Improving and Evaluating Open Deep Research AgentsLLM agents and tool use → Web, search, and research agents
Agentic AI Frameworks: Architectures, Protocols, and Design ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
MCP-Orchestrated Multi-Agent System for Automated Disinformation DetectionLLM agents and tool use → Web, search, and research agents
Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMsLLM reasoning → Reasoning benchmarks and evaluation
mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy RolloutsLLM reasoning → Reinforcement learning for reasoning
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code GenerationLLM reasoning → Spatial and embodied reasoning
Less is More: Learning Graph Tasks with Just LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
SaraCoder: Orchestrating Semantic and Structural Cues for Resource-Optimized Repository-Level Code CompletionRetrieval-augmented generation → RAG for code
LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play ToolkitMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Dynamic Mixture-of-Experts for Incremental Graph LearningMixture-of-experts → MoE for time series and graphs
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
Performance of GPT-5 Frontier Models in Ophthalmology Question AnsweringLLM reasoning → Clinical and biomedical applications
Stable Diffusion Models are Secretly Good at Visual In-Context LearningDiffusion models → Image generation, text-to-image and editing
VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
AST-n: A Fast Sampling Approach for Low-Dose CT Reconstruction using Diffusion ModelsDiffusion models → Medical imaging and segmentation
A Comprehensive Evaluation framework of Alignment Techniques for LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Mathematical Computation and Reasoning Errors by Large Language ModelsLLM reasoning → Mathematical reasoning
Prototype-Guided Diffusion: Visual Conditioning without External MemoryDiffusion models → Diffusion foundations and sampling
RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QALLM agents and tool use → Web, search, and research agents
Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorldLLM agents and tool use → General LLM agent frameworks and benchmarks
COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound DatasetsMixture-of-experts → Medical and biomedical MoE
Beyond Scaling Law: A Data-Efficient Distillation Framework for ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
FedShard: Federated Unlearning with Efficiency Fairness and Performance FairnessLLM safety and security → Federated unlearning and poisoning
OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train BetterMultimodal LLMs / vision-language models → Video understanding with MLLMs
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long ContextsLLM reasoning → Reasoning benchmarks and evaluation
Enhancing Diffusion Face Generation with Contrastive Embeddings and SegFormer GuidanceDiffusion models → Image generation, text-to-image and editing
Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security ResearchLLM agents and tool use → Agent threats, guardrails and governance
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement FinetuningLLM reasoning → Multimodal reasoning
LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration RecommendationsRetrieval-augmented generation → RAG pipeline design and evaluation
Describe What You See with Multimodal Large Language Models to Enhance Video RecommendationsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
The PacifAIst Benchmark:Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety?LLM safety and security → Safety alignment, refusal and guardrails
Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional SpecializationMixture-of-experts → MoE for time series and graphs
μ-Parametrization for Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term MemoryLLM agents and tool use → Multimodal and embodied agents
Generative Modeling with Multi-Instance Reward Learning for E-commerce Creative OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Sample More to Think Less: Group Filtered Policy Optimization for Concise ReasoningLLM reasoning → Reinforcement learning for reasoning
The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR AdvancementLLM reasoning → Reinforcement learning for reasoning
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought DistillationLLM reasoning → Prompting and chain-of-thought reasoning
NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face GenerationDiffusion models → Image generation, text-to-image and editing
On Negative-aware Preference Optimization for RecommendationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification GenerationLLM agents and tool use → Software engineering coding agents
Preacher: Paper-to-Video Agentic SystemLLM agents and tool use → Multimodal and embodied agents
TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series ModelingLLM reasoning → Time series reasoning
The Surprising Effectiveness of Membership Inference with Simple N-Gram CoverageLLM safety and security → Membership inference attacks
Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative QualityDiffusion models → Image generation, text-to-image and editing
HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert SwapMixture-of-experts → Efficient MoE training and inference systems
EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-makingSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing
Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and ChallengesWorld models → World models for language agents +1
GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal ReasoningLLM reasoning → Spatial and embodied reasoning
TFRank: Think-Free Reasoning Enables Practical Pointwise LLM RankingLLM reasoning → Knowledge- and tool-augmented reasoning
From Context to Intent: Reasoning-Guided Function-Level Code CompletionLLM reasoning → Reasoning for agents, planning and code
PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic ReasoningLLM reasoning → Audio-language model reasoning
An Automated Multi-modal Evaluation Framework for Mobile Intelligent Assistants Based on Large Language Models and Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented GenerationRetrieval-augmented generation → Generation and context integration
NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
User-centric Subjective Leaderboard by Customizable Reward ModelingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesisLLM reasoning → Hallucination detection and mitigation
IAG: Input-aware Backdoor Attack on VLM-based Visual GroundingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language NavigationDiffusion models → Diffusion and flow policies for robotics
Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM InferenceEfficient LLM inference and serving → KV cache optimization
Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal NavigationLLM agents and tool use → Multimodal and embodied agents
Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction
Leveraging the Christoffel Function for Outlier Detection in Data Streams
Negative Shanshui: Real-time Interactive Ink Painting Synthesis
Quantum-Inspired DRL Approach with LSTM and OU Noise for Cut Order Planning Optimization
To Explain Or Not To Explain: An Empirical Investigation Of AI-Based Recommendations On Social Media Platforms
LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts
A BERT-based Hierarchical Classification Model with Applications in Chinese Commodity Classification
A Framework for Processing Textual Descriptions of Business Processes using a Constrained Language -- Technical Report
Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases
Do Language Models Agree with Human Perceptions of Suspense in Stories?
Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages
CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection
FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics
Parameter-Aware Ensemble SINDy for Interpretable Symbolic SGS Closure

All 334