Papers

New on arXiv

Sun 4 May 2025

158 papers

Dialz: A Python Toolkit for Steering VectorsMechanistic interpretability → Activation steering methods
Language translation, and change of accent for speech-to-speech task using diffusion modelDiffusion models → Audio, speech and music
Universal Approximation Theorem of Deep Q-NetworksDeep reinforcement learning methods → Deep RL algorithms and representations
A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)LLM agents and tool use → Agent threats, guardrails and governance
Compositional Image-Text Matching and Retrieval by Grounding EntitiesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Real-time Spatial Retrieval Augmented Generation for Urban EnvironmentsRetrieval-augmented generation → RAG pipeline design and evaluation
Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic DatasetDiffusion models → Diffusion foundations and sampling
Sampling-Aware Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Coupled Distributional Random Expert Distillation for World Model Online Imitation LearningWorld models → Embodied and robot world models +1
Interpretable Emergent Language Using Inter-Agent TransformersDeep reinforcement learning methods → Multi-agent reinforcement learning
A New HOPE: Domain-agnostic Automatic Evaluation of Text ChunkingRetrieval-augmented generation → Multimodal RAG
CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair UseRetrieval-augmented generation → Legal and financial RAG
Adaptive Social Learning via Mode Policy Optimization for Language AgentsLLM reasoning → Reasoning for agents, planning and code +1
Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal InterventionsMechanistic interpretability → Knowledge and representations inside LLMs
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text InstructionsVision-language-action models → Generalist VLA models and benchmarks
VECSR: Virtually Embodied Common Sense Reasoning SystemLLM reasoning → Reasoning for agents, planning and code
Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary StudyLLM reasoning → Reinforcement learning for reasoning +1
Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge DistillationKnowledge distillation → General knowledge distillation methods
Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and LatencyLLM agents and tool use → Software engineering coding agents
DriveAgent: Multi-Agent Structured Reasoning with LLM and Multimodal Sensor Fusion for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based AgentsLLM agents and tool use → Agent memory systems
SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy DemonstrationsDeep reinforcement learning methods → Deep RL algorithms and representations
Retrieval-augmented in-context learning for multimodal large language models in disease classificationMultimodal LLMs / vision-language models → Medical vision-language models +1
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI AgentsLLM safety and security → Prompt injection and agent security
Leveraging LLM Agents and Digital Twins for Fault Handling in Process PlantsLLM agents and tool use → General LLM agent frameworks and benchmarks
Learning Local Causal World Models with State Space Models and AttentionWorld models → World models for language agents
Express Your Doubts -- Probabilistic World Modeling Should not be Based on Token logprobsWorld models → World models for language agents
RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time VideoLLM reasoning → Multimodal reasoning +1
Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated MarginMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Regression is all you need for medical image translationDiffusion models → Medical imaging and segmentation
From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning EvaluationLLM reasoning → Multimodal reasoning
Meta-Black-Box-Optimization through Offline Q-function LearningState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMsLLM safety and security → Safety alignment, refusal and guardrails
Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance FieldsMixture-of-experts → Vision mixture-of-experts
A Synergistic Framework of Nonlinear Acoustic Computing and Reinforcement Learning for Real-World Human-Robot InteractionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning ApproachLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation DetectionDeep reinforcement learning methods → Deep RL algorithms and representations
A Survey on Privacy Risks and Protection in Large Language ModelsLLM safety and security → Membership inference attacks
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Training Environment for High Performance Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
AI-Driven Generation of Data Contracts in Modern Data Engineering Systems
Ubiquitous Symmetry at Critical Points Across Diverse Optimization Landscapes
Probing Audio-Generation Capabilities of Text-Based Language Models
FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review
From Biometrics to Environmental Control: AI-Enhanced Digital Twins for Personalized Health Interventions in Healing Landscapes
Modeling supply chain compliance response strategies based on AI synthetic data with structural path regression: A Simulation Study of EU 2027 Mandatory Labor Regulations
Explainable Face Recognition via Improved Localization
Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery
The Shift Towards Preprints in AI Policy Research: A Comparative Study of Preprint Trends in the U.S., Europe, and South Korea
PointExplainer: Towards Transparent Parkinson's Disease Diagnosis
Video Forgery Detection for Surveillance Cameras: A Review
A Comprehensive Analysis of Adversarial Attacks against Spam Filters
Uncertainty Quantification for Machine Learning in Healthcare: A Survey
Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles
Epistemic Wrapping for Uncertainty Quantification
On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles
Demystifying optimized prompts in language models
Robust Localization, Mapping, and Navigation for Quadruped Robots
Parameter-Efficient Transformer Embeddings
Bayesian Federated Cause-of-Death Classification and Quantification Under Distribution Shift
Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models
Heterosynaptic Circuits Are Universal Gradient Machines
RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
Cricket: A Self-Powered Chirping Pixel
Federated Causal Inference in Healthcare: Methods, Challenges, and Applications
Improving Physical Object State Representation in Text-to-Image Generative Systems
SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation
Prompt-responsive Object Retrieval with Memory-augmented Student-Teacher Learning
The Gen AI Generation: Student Views of Awareness, Preparedness, and Concern
Enhanced Outsourced and Secure Inference for Tall Sparse Decision Trees
Practical Efficiency of Muon for Pretraining
LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
An Empirical Study of Qwen3 Quantization
Exogenous Isomorphism for Counterfactual Identifiability
Intelligent Diagnosis Using Dual-Branch Attention Network for Rare Thyroid Carcinoma Recognition with Ultrasound Imaging
DNAZEN: Enhanced Gene Sequence Representations via Mixed Granularities of Coding Units
Exploring new Approaches for Information Retrieval through Natural Language Processing
Student Perspectives on the Benefits and Risks of AI in Education
DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
Latent Variable Estimation in Bayesian Black-Litterman Models
Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes
Robust AI-Generated Face Detection with Imbalanced Data
Efficient FPGA Implementation of Time-Domain Popcount for Low-Complexity Machine Learning
ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications
Sparfels: Fast Reconstruction from Sparse Unposed Imagery
Measuring Hong Kong Massive Multi-Task Language Understanding
Saliency-Guided Training for Fingerprint Presentation Attack Detection
SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting
Ranked differences Pearson correlation dissimilarity with an application to electricity users time series clustering
Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization
A data-driven framework for team selection in Fantasy Premier League
Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matching
Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
Pickup & Delivery with Time Windows and Transfers: combining decomposition with metaheuristics
A Monotone Single-Index Modal Regression Powered by Deep Neural Networks for Non-Gaussian Periodontal Data
Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

All 158