Papers

New on arXiv

Sun 14 Sep 2025

212 papers

Pathological Truth Bias in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score AlignmentLLM reasoning → Reasoning benchmarks and evaluation
LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE MethodsMixture-of-experts → Mixture of LoRA experts
Self-Evolving LLMs via Continual Instruction TuningMixture-of-experts → Mixture of LoRA experts +1
CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AILLM agents and tool use → General LLM agent frameworks and benchmarks
Agentic UAVs: LLM-Driven Autonomy with Integrated Tool-Calling and Cognitive ReasoningLLM reasoning → Spatial and embodied reasoning +1
Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic PlanningLLM reasoning → Reasoning for agents, planning and code
PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answeringLLM reasoning → Audio-language model reasoning
Knowledge-Guided Adaptive Mixture of Experts for Precipitation PredictionMixture-of-experts → MoE for time series and graphs
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward WeightingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Securing AI Agents: Implementing Role-Based Access Control for Industrial ApplicationsLLM agents and tool use → Agent threats, guardrails and governance +1
Trading-R1: Financial Trading with LLM Reasoning via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained RepresentationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Solving ill-conditioned polynomial equations using score-based priors with application to multi-target detectionDiffusion models → Inverse problems and image restoration
Quantum deep reinforcement learning for humanoid robot navigation taskDeep reinforcement learning methods → Quantum reinforcement learning
Detecting Model Drifts in Non-Stationary Environment Using Edit Operation MeasuresDeep reinforcement learning methods → Deep RL algorithms and representations
MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
On Linear Mode Connectivity of Mixture-of-Experts ArchitecturesMixture-of-experts → MoE theory and gating functions
MatQnA: A Benchmark Dataset for Multi-modal Large Language Models in Materials Characterization and AnalysisMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Prompts to Proxies: Emulating Human Preferences via a Compact LLM EnsembleLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural ContextLLM reasoning → Reasoning benchmarks and evaluation
When Are Two RLHF Objectives the Same?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting HallucinationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
PINGS: Physics-Informed Neural Network for Fast Generative SamplingDiffusion models → Diffusion foundations and sampling
ICR-RL: Deep Reinforcement Learning via In-Context RegressionDeep reinforcement learning methods → Deep RL algorithms and representations
Environmental Injection Attacks against GUI Agents in Realistic Dynamic EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance
CORB-Planner: Corridor as Observations for RL Planning in High-Speed FlightDeep reinforcement learning methods → RL for robot navigation and UAV control
TransZero: Parallel Tree Expansion in MuZero using Transformer NetworksDeep reinforcement learning methods → RL theory and sample complexity
Beyond Sliders: Mastering the Art of Diffusion-based Image ManipulationDiffusion models → Image generation, text-to-image and editing
Traffic-MLLM: Curiosity-Regularized Supervised Learning for Traffic Scenario Case-Based ReasoningLLM reasoning → Chain-of-thought reasoning for driving
Dual Reinforcement Learning Synergy in Resource Allocation: Emergence of Self-Organized Momentum StrategyDeep reinforcement learning methods → RL for games and combinatorial optimization
AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMsEfficient LLM inference and serving → KV cache optimization
Text2Mem: A Unified Memory Operation Language for Memory Operating SystemLLM agents and tool use → Agent memory systems
Rethinking Technology Stack Selection with AI Coding ProficiencyLLM reasoning → Reasoning for agents, planning and code
ERIS: Evolutionary Real-world Interference Scheme for Jailbreaking Audio Large ModelsLLM safety and security → Audio jailbreaks and speech backdoors
Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy ClassificationLLM reasoning → Reasoning for agents, planning and code
ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D RepresentationsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Seeing is Not Understanding: A Benchmark on Perception-Cognition Disparities in Large Language ModelsMultimodal LLMs / vision-language models → Multimodal emotion understanding
Membership Inference Attacks on Recommender System: A SurveyLLM safety and security → Membership inference attacks
Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent WorkflowsLLM agents and tool use → Software engineering coding agents
Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient DataLLM agents and tool use → Medical and scientific domain agents +1
The System Description of CPS Team for Track on Driving with Language of CVPR 2024 Autonomous Grand ChallengeMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and OrchestrationLLM agents and tool use → Software engineering coding agents
Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research PresentationsLLM agents and tool use → Educational agents and math problem solving
Data-Efficient Ensemble Weather Forecasting with Diffusion ModelsDiffusion models → Flow matching, time series and science
Free-MAD: Consensus-Free Multi-Agent DebateLLM reasoning → Reasoning for agents, planning and code +1
Rethinking Human Preference Evaluation of LLM RationalesLLM reasoning → Reasoning benchmarks and evaluation
Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation ModelDeep reinforcement learning methods → RL for games and combinatorial optimization
Beyond IVR Touch-Tones: Customer Intent Routing using LLMs
Towards Better Health Conversations: The Benefits of Context-seeking
Quantum and Classical Machine Learning in Decentralized Finance: Comparative Evidence from Multi-Asset Backtesting of Automated Market Makers
RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Markets
Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
Quantifying Compositionality of Classic and State-of-the-Art Embeddings
Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention
LibEMER: A novel benchmark and algorithms library for EEG-based Multimodal Emotion Recognition
Human Activity Recognition Based on Electrocardiogram Data Only
A Machine Learning Framework for Pathway-Driven Therapeutic Target Discovery in Metabolic Disorders
Comparative Analysis of FOLD-SE vs. FOLD-R++ in Binary Classification and XGBoost in Multi-Category Classification
Rank-Induced PL Mirror Descent: A Rank-Faithful Second-Order Algorithm for Sleeping Experts
From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
SDGF: Fusing Static and Multi-Scale Dynamic Correlations for Multivariate Time Series Forecasting
A Weighted Gradient Tracking Privacy-Preserving Method for Distributed Optimization
Position Paper: Integrating Explainability and Uncertainty Estimation in Medical AI
Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches
Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling
Synthetic Data and the Shifting Ground of Truth
Hybrid Quantum-Classical Model for Image Classification
Prediction of Stocks Index Price using Quantum GANs
Deriving the Scaled-Dot-Function via Maximum Likelihood Estimation and Maximum Entropy Approach
AISSISTANT: Human-AI Collaborative Review and Perspective Research Workflows in Data Science
Meta-model Neural Process for Probabilistic Power Flow under Varying N-1 System Topologies
Domain Adaptive SAR Wake Detection: Leveraging Similarity Filtering and Memory Guidance
GraphDerm: Fusing Imaging, Physical Scale, and Metadata in a Population-Graph Classifier for Dermoscopic Lesions
Developing an aeroponic smart experimental greenhouse for controlling irrigation and plant disease detection using deep learning and IoT
LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
Designing and Evaluating a Conversational Agent for Early Diagnosis of Alzheimer's Disease and Related Dementias
Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervision
Improving LLMs' Learning for Coreference Resolution
CEMTM: Contextual Embedding-based Multimodal Topic Modeling
CareerPooler: AI-Powered Metaphorical Pool Simulation Improves Experience and Outcomes in Career Exploration
Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking
Tabular Data with Class Imbalance: Predicting Electric Vehicle Crash Severity with Pretrained Transformers (TabPFN) and Mamba-Based Models
CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media
A Transformer-Based Cross-Platform Analysis of Public Discourse on the 15-Minute City Paradigm
MultiMAE for Brain MRIs: Robustness to Missing Inputs Using Multi-Modal Masked Autoencoder
Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery
A Particle-Flow Algorithm for Free-Support Wasserstein Barycenters
Long-time dynamics and universality of nonconvex gradient descent
FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs
Continually Adding New Languages to Multilingual Language Models
Framing AI System Benchmarking as a Learning Task: FlexBench and the Open MLPerf Dataset
On the Skinning of Gaussian Avatars
No Modality Left Behind: Dynamic Model Generation for Incomplete Medical Data
From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation
Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning

All 212