Papers

New on arXiv

Sat 26 Apr 2025

117 papers

Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and ApplicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity OversightLLM safety and security → Prompt injection and agent security
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent DecompositionLLM agents and tool use → Agentic recommender systems
KETCHUP: K-Step Return Estimation for Sequential Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMsLLM safety and security → Jailbreaking
REED-VAE: RE-Encode Decode Training for Iterative Image Editing with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Feature Fusion Revisited: Multimodal CTR Prediction for MMCTR ChallengeMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and ScalabilityLLM reasoning → Spatial and embodied reasoning
LawFlow: Collecting and Simulating Lawyers' Thought Processes on Business Formation Case StudiesLLM reasoning → Reasoning for agents, planning and code
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling CorrectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
Advanced Longitudinal Control and Collision Avoidance for High-Risk Edge Cases in Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot LearningOffline RL and imitation learning from data → Robot manipulation imitation learning +1
Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain PartitioningDeep reinforcement learning methods → RL for energy, networks and operations
Generative to Agentic AI: Survey, Conceptualization, and ChallengesLLM agents and tool use → General LLM agent frameworks and benchmarks
Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual RepresentationMultimodal LLMs / vision-language models → Medical vision-language models
When2Call: When (not) to Call ToolsLLM agents and tool use → Tool learning and function calling
Imitation Learning for Autonomous Driving: Insights from Real-World TestingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form GenerationLLM agents and tool use → Multimodal and embodied agents
Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile RobotsDeep reinforcement learning methods → Deep RL algorithms and representations
Dynamic Action Interpolation: A Universal Approach for Accelerating Reinforcement Learning with Expert GuidanceDeep reinforcement learning methods → Deep RL algorithms and representations
A Vision for Auto Research with LLM AgentsLLM agents and tool use → Web, search, and research agents
SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum LearningSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Neurophysiologically Realistic Environment for Comparing Adaptive Deep Brain Stimulation Algorithms in Parkinson Disease
The Influence of Text Variation on User Engagement in Cross-Platform Content Sharing
Snakemaker: Seamlessly transforming ad-hoc analyses into sustainable Snakemake workflows with generative AI
Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materials
Enhancing IoT-Botnet Detection using Variational Auto-encoder and Cost-Sensitive Learning: A Deep Learning Approach for Imbalanced Datasets
Extracting Abstraction Dimensions by Identifying Syntax Pattern from Texts
Theory of Mind in Large Language Models: Assessment and Enhancement
Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
Long-Distance Field Demonstration of Imaging-Free Drone Identification in Intracity Environments
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis
QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations
AI Recommendations and Non-instrumental Image Concerns
Enhancing Cochlear Implant Signal Coding with Scaled Dot-Product Attention
Calibrating Translation Decoding with Quality Estimation on LLMs
Generative Models for Fast Simulation of Cherenkov Detectors at the Electron-Ion Collider
Improved Molecular Generation through Attribute-Driven Integrative Embeddings and GAN Selectivity
Atlantes: A system of GPS transformers for global-scale real-time maritime intelligence
On learning functions over biological sequence space: relating Gaussian process priors, regularization, and gauge fixing
VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation
Improving Pretrained YAMNet for Enhanced Speech Command Detection via Transfer Learning
DiCE-Extended: A Robust Approach to Counterfactual Explanations in Machine Learning
Smooth Approximations of the Rounding Function
GLaMoR: Consistency Checking of OWL Ontologies using Graph Language Models
Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting
Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles
Towards minimax optimal algorithms for Active Simple Hypothesis Testing
PINN - a Domain Decomposition Method for Bayesian Physics-Informed Neural Networks
Geometry-aware Active Learning of Spatiotemporal Dynamic Systems
Learning Stochastic Thermodynamics Directly from Correlation and Trajectory-Fluctuation Currents
Deep Learning-Based Multi-Modal Fusion for Robust Robot Perception and Navigation
Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizers
Dynamic Fisher-weighted Model Merging via Bayesian Optimization
LINC: Supporting Language Independent Communication and Comprehension to Enhance Contribution in Multilingual Collaborative Meetings
MediAug: Exploring Visual Augmentation in Medical Imaging
3DPyranet Features Fusion for Spatio-temporal Feature Learning
R-Sparse R-CNN: SAR Ship Detection Based on Background-Aware Sparse Learnable Proposals
Modeling Regime Structure and Informational Drivers of Stock Market Volatility via the Financial Chaos Index
Surgeons vs. Computer Vision: A comparative analysis on surgical phase recognition capabilities
Application of the Brain Drain Optimization Algorithm to the N-Queens Problem
Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness
Use of Metric Learning for the Recognition of Handwritten Digits, and its Application to Increase the Outreach of Voice-based Communication Platforms
GPU accelerated program synthesis: Enumerate semantics, not syntax!
AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depression
Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity
Clinical knowledge in LLMs does not translate to human interactions
Meta-Learning in Self-Play Regret Minimization
UnifyFL: Enabling Decentralized Cross-Silo Federated Learning
Factor Analysis with Correlated Topic Model for Multi-Modal Data
A Langevin sampling algorithm inspired by the Adam optimizer
Kinship Verification through a Forest Neural Network
Sim-to-Real: An Unsupervised Noise Layer for Screen-Camera Watermarking Robustness
ReLU integral probability metric and its applications
Exploiting Multiple Representations: 3D Face Biometrics Fusion with Application to Surveillance
A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges
TSCAN: Context-Aware Uplift Modeling via Two-Stage Training for Online Merchant Business Diagnosis
Reshaping MOFs text mining with a dynamic multi-agents framework of large language model
TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation
Latent Adversarial Training Improves the Representation of Refusal
WLTCL: Wide Field-of-View 3-D LiDAR Truck Compartment Automatic Localization System
Approximating Nash Equilibria in General-Sum Games via Meta-Learning
PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance
Spike Imaging Velocimetry: Dense Motion Estimation of Fluids Using Spike Cameras
Diffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations
Why you shouldn't fully trust ChatGPT: A synthesis of this AI tool's error rates across disciplines and the software engineering lifecycle
Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Information
Theoretical Framework for Tempered Fractional Gradient Descent: Application to Breast Cancer Classification
Introducing Interval Neural Networks for Uncertainty-Aware System Identification
Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks
A Dictionary of Closed-Form Kernel Mean Embeddings
Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy
Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning
Preserving Seasonal and Trend Information: A Variational Autoencoder-Latent Space Arithmetic Based Approach for Non-stationary Learning
Frequency-Integrated Transformer for Arbitrary-Scale Super-Resolution
Zero-Day Botnet Attack Detection in IoV: A Modular Approach Using Isolation Forests and Particle Swarm Optimization
Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning

All 117