Papers

New on arXiv

Sat 5 Jul 2025

150 papers

FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial ScenariosLLM agents and tool use → Financial trading and forecasting agents
LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA SharingLLM safety and security → Vision-language and text-to-image safety
A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics TeachersLLM agents and tool use → Educational agents and math problem solving
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship UnderstandingLLM reasoning → Reasoning benchmarks and evaluation
Where to Intervene: Action Selection in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
LVLM-Composer's Explicit Planning for Image GenerationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation StrategiesLLM reasoning → Clinical and biomedical applications
Pedestrian Intention Prediction via Vision-Language Foundation ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
A Technical Survey of Reinforcement Learning Techniques for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
Towards Accurate and Efficient 3D Object Detection for Autonomous Driving: A Mixture of Experts Computing System on EdgeEnd-to-end autonomous driving → VLMs for autonomous driving +1
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You NeedKnowledge distillation → General knowledge distillation methods
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual LearningLLM safety and security → Backdoor and data poisoning attacks
Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized SmoothingLLM agents and tool use → General LLM agent frameworks and benchmarks
How to Train Your LLM Web Agent: A Statistical DiagnosisLLM agents and tool use → Web, search, and research agents
Conversation Forests: The Key to Fine Tuning Large Language Models for Multi-Turn Medical Conversations is BranchingLLM reasoning → Clinical and biomedical applications +1
Are Learning-Based Approaches Ready for Real-World Indoor Navigation? A Case for Imitation LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
Accurate and Efficient World Modeling with Masked Latent TransformersWorld models → Latent dynamics models and model-based RL
Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
HAWK: A Hierarchical Workflow Framework for Multi-Agent CollaborationLLM agents and tool use → Software engineering coding agents
DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +3
Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic EnvironmentsLLM agents and tool use → Social simulation and multi-agent debate
PresentAgent: Multimodal Agent for Presentation Video GenerationLLM agents and tool use → Multimodal and embodied agents
Lyria: A Genetic Algorithm-Driven Neuro-Symbolic Reasoning Framework for LLMsLLM reasoning → Reasoning benchmarks and evaluation
Patient-Centered RAG for Oncology Visit Aid Following the Ottawa Decision GuideRetrieval-augmented generation → Medical and biomedical RAG
Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language ModelsLLM reasoning → Mathematical reasoning
Nunchi-Bench: Benchmarking Language Models on Cultural Reasoning with a Focus on Korean SuperstitionLLM reasoning → Reasoning benchmarks and evaluation
NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World ModelsWorld models → World models for autonomous driving +1
Scalable Learning of High-Dimensional Demonstrations with Composition of Linear Parameter Varying Dynamical SystemsOffline RL and imitation learning from data → Robot learning from demonstration
CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
A Comparative Study of Specialized LLMs as Dense RetrieversMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive StudyDiffusion models → Robustness, privacy and adversarial aspects
RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without RobotOffline RL and imitation learning from data → Robot manipulation imitation learning
CortexDebate: Debating Sparsely and Equally for Multi-Agent DebateLLM reasoning → Reasoning for agents, planning and code +1
MCST-Mamba: Multivariate Mamba-Based Model for Traffic PredictionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse RenderingDiffusion models → 3D, point cloud and scene generation
Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
Agent Exchange: Shaping the Future of AI Agent EconomicsLLM agents and tool use → General LLM agent frameworks and benchmarks
Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEMRetrieval-augmented generation → Agentic RAG, agents and memory +1
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inferenceEfficient LLM inference and serving → KV cache optimization
Interpretable Diffusion Models with B-cos NetworksDiffusion models → Image generation, text-to-image and editing
Generative AI for CAD Automation: Leveraging Large Language Models for 3D Modelling
Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
Absorption and Inertness in Coarse-Grained Arithmetic: A Heuristic Application to the St. Petersburg Paradox
A Biomimetic Way for Coral-Reef-Inspired Swarm Intelligence for Carbon-Neutral Wastewater Treatment
SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents
View Invariant Learning for Vision-Language Navigation in Continuous Environments
RepeaTTS: Towards Feature Discovery through Repeated Fine-Tuning
False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems
We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
Enhancing Learning Path Recommendation via Multi-task Learning
Physics-Informed Graph Neural Networks to Reconstruct Local Fields Considering Finite Strain Hyperelasticity
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
Towards Spatially-Varying Gain and Binning
Voyaging into Perpetual Dynamic Scenes from a Single View
Navigating Speech Recording Collections with AI-Generated Illustrations
skfolio: Portfolio Optimization in Python
Uncertainty Quantification in the Tsetlin Machine
Efficient Detection of Intermittent Job Failures Using Few-Shot Learning
Generative Regression with IQ-BART
Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization
Physics-informed neural networks and neural operators for a study of EUV electromagnetic wave diffraction from a lithography mask
Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
Large Language Models for Zero-Shot Multicultural Name Recognition
A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality
Driver-Net: Multi-Camera Fusion for Assessing Driver Take-Over Readiness in Automated Vehicles
Detecting Token-Level Hallucinations Using Variance Signals: A Reference-Free Approach
Online Convex Optimization with Switching Cost with Only One Single Gradient Evaluation
An HTR-LLM Workflow for High-Accuracy Transcription and Analysis of Abbreviated Latin Court Hand
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
Graph Neural Networks as a Substitute for Transformers in Single-Cell Transcriptomics
Model selection for stochastic dynamics: a parsimonious and principled approach
PromptSR: Cascade Prompting for Lightweight Image Super-Resolution
Relational inductive biases on attention mechanisms
Integrated Gaussian Processes for Robust and Adaptive Multi-Object Tracking
VICI: VLM-Instructed Cross-view Image-localisation
Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems
Human-centered AI with focus on Human-robot interaction (Book chapter)
MMMOS: Multi-domain Multi-axis Audio Quality Assessment
Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning
XISM: an eXploratory and Interactive Graph Tool to Visualize and Evaluate Semantic Map Models
Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
Consistent and Invariant Generalization Learning for Short-video Misinformation Detection
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
Attributing Data for Sharpness-Aware Minimization
Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG
TopoMAS: Large Language Model Driven Topological Materials Multiagent System
Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
Predictive Modeling of Effluent Temperature in SAT Systems Using Ambient Meteorological Data: Implications for Infiltration Management
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study
T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Images
Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models
Differentiable High-Performance Ray Tracing-Based Simulation of Radio Propagation with Point Clouds
Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning
Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning
Habitat Classification from Ground-Level Imagery Using Deep Neural Networks
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
PASC-Net:Plug-and-play Shape Self-learning Convolutions Network with Hierarchical Topology Constraints for Vessel Segmentation

All 150