Papers

New on arXiv

Sat 19 Jul 2025

146 papers

MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuningLLM agents and tool use → GUI and mobile agents
RATE: An LLM-Powered Retrieval Augmented Generation Technology-Extraction PipelineRetrieval-augmented generation → RAG pipeline design and evaluation
Sensor-Space Based Robust Kinematic Control of Redundant Soft Manipulator by LearningOffline RL and imitation learning from data → Imitation learning methods
GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought TokenizationLLM reasoning → LLM reasoning for recommendation
Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Towards Urban Planing AI Agent in the Age of Agentic AILLM agents and tool use → Multimodal and embodied agents
Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining WallsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Policy-Grounded Safety Evaluation of 20 Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
Configurable multi-agent framework for scalable and realistic testing of llm-based agentsLLM agents and tool use → General LLM agent frameworks and benchmarks
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation RecognitionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy OptimizationLLM reasoning → Mathematical reasoning
WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image AnalysisLLM agents and tool use → Medical and scientific domain agents
Docopilot: Improving Multimodal Models for Document-Level UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative ApproachesLLM agents and tool use → Multimodal and embodied agents
Retrieval-Augmented Clinical Benchmarking for Contextual Model Testing in Kenyan Primary Care: A Methodology PaperRetrieval-augmented generation → Medical and biomedical RAG
BT-TL-DMPs: A Novel Robot TAMP Framework Combining Behavior Tree, Temporal Logic and Dynamical Movement PrimitivesOffline RL and imitation learning from data → Robot learning from demonstration
Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI TranslationDiffusion models → Medical imaging and segmentation
Kernel Based Maximum Entropy Inverse Reinforcement Learning for Mean-Field GamesOffline RL and imitation learning from data → Inverse reinforcement learning +1
Diffusion Models for Time Series Forecasting: A SurveyDiffusion models → Flow matching, time series and science
Generative Distribution DistillationKnowledge distillation → General knowledge distillation methods
Efficient Whole Slide Pathology VQA via Token CompressionMultimodal LLMs / vision-language models → Medical vision-language models +1
Federated Reinforcement Learning in Heterogeneous EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured PredictionsDiffusion models → Flow matching, time series and science
BioGraphFusion: Graph Knowledge Embedding for Biological Completion and ReasoningLLM reasoning → Clinical and biomedical applications
GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture +1
IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale BenchmarkMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Routine: A Structural Planning Framework for LLM Agent System in EnterpriseLLM agents and tool use → General LLM agent frameworks and benchmarks
Deep RL Dual Sourcing Inventory Management with Supply and Capacity Risk AwarenessDeep reinforcement learning methods → RL for energy, networks and operations
Statistical and Algorithmic Foundations of Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor DisplayLLM reasoning → Reasoning benchmarks and evaluation
It's Not That Simple. An Analysis of Simple Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
Designing Conversational AI to Support Think-Aloud Practice in Technical Interview Preparation for CS StudentsLLM reasoning → Reasoning benchmarks and evaluation
Inverse Scaling in Test-Time ComputeLLM reasoning → Test-time compute and efficient thinking
Semi-automated Fact-checking in Portuguese: Corpora Enrichment using Retrieval with Claim extraction
Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
Text2VR: Automated instruction Generation in Virtual Reality using Large language Models for Assembly Task
Patents as Knowledge Artifacts: An Information Science Perspective on Global Innovation
Discrete approach to machine learning
A Hybrid Framework for Subject Analysis: Integrating Embedding-Based Regression Models with Large Language Models
A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
ElectriQ: A Benchmark for Assessing the Response Capability of Large Language Models in Power Marketing
Kolmogorov Arnold Network Autoencoder in Medicine
Language Models for Controllable DNA Sequence Design
Applications and Manipulations of Physics-Informed Neural Networks in Solving Differential Equations
Explainable Graph Neural Networks via Structural Externalities
Caching Techniques for Reducing the Communication Cost of Federated Learning in IoT Environments
CASPER: Contrastive Approach for Smart Ponzi Scheme Detecter with More Negative Samples
PAT++: a cautionary tale about generative visual augmentation for Object Re-identification
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Combining Cost-Constrained Runtime Monitors for AI Safety
Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusion
XplainAct: Visualization for Personalized Intervention Insights
CXR-TFT: Multi-Modal Temporal Fusion Transformer for Predicting Chest X-ray Trajectories
QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
Analyzing Internal Activity and Robustness of SNNs Across Neuron Parameter Space
On the robustness of modeling grounded word learning through a child's egocentric input
Pruning Increases Orderedness in Recurrent Computation
Sampling from Gaussian Processes: A Tutorial and Applications in Global Sensitivity Analysis and Optimization
Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML
InterAct-Video: Reasoning-Rich Video QA for Urban Traffic
Disparities in Peer Review Tone and the Role of Reviewer Anonymity
Better Training Data Attribution via Better Inverse Hessian-Vector Products
MultiRetNet: A Multimodal Vision Model and Deferral System for Staging Diabetic Retinopathy
GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems
Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling
Spatial-Temporal Transformer with Curriculum Learning for EEG-Based Emotion Recognition
GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
Forecasting Faculty Placement from Patterns in Co-authorship Networks
Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks
Rethinking Suicidal Ideation Detection: A Trustworthy Annotation Framework and Cross-Lingual Model Evaluation
Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations
Large Language Models as Medical Codes Selectors: a benchmark using the International Classification of Primary Care
GCC-Spam: Spam Detection via GAN, Contrastive Learning, and Character Similarity Networks
Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective
Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images
Rec-AD: An Efficient Computation Framework for FDIA Detection Based on Tensor Train Decomposition and Deep Learning Recommendation Model
Mangosteen: An Open Thai Corpus for Language Model Pretraining
Artificial Intelligence in the Food Industry: Food Waste Estimation based on Computer Vision, a Brief Case Study in a University Dining Hall
When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
AI-Enhanced Precision in Sport Taekwondo: Increasing Fairness, Speed, and Trust in Competition (FST.ai)
Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operators
Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs
Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection
Efficient Story Point Estimation With Comparative Learning
Deep Learning-Based Survival Analysis with Copula-Based Activation Functions for Multivariate Response Prediction
Linear Relational Decoding of Morphology in Language Models
KinForm: Kinetics Informed Feature Optimised Representation Models for Enzyme kcat and KM Prediction
BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM
k-PCA for (non-squared) Euclidean Distances: Polynomial Time Approximation
VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Masking
VTarbel: Targeted Label Attack with Minimal Knowledge on Detector-enhanced Vertical Federated Learning
Real-Time Scene Reconstruction using Light Field Probes
Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
Depthwise-Dilated Convolutional Adapters for Medical Object Tracking and Segmentation Using the Segment Anything Model 2
Enhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module

All 146