Papers

New on arXiv

Fri 9 May 2025

220 papers

Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive ReviewDiffusion models → Medical imaging and segmentation
Arrow-Guided VLM: Enhancing Flowchart Understanding via Arrow Direction EncodingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Adaptive Wiping: Adaptive contact-rich manipulation through few-shot imitation learning with Force-Torque feedback and pre-trained object representationsOffline RL and imitation learning from data → Robot manipulation imitation learning
Reliable Collaborative Conversational Agent System Based on LLMs and Answer Set ProgrammingLLM agents and tool use → General LLM agent frameworks and benchmarks
Is your multimodal large language model a good science tutor?LLM reasoning → Multimodal reasoning +1
ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM AgentsLLM agents and tool use → Tool learning and function calling
Natural Reflection Backdoor Attack on Vision Language Model for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +3
Temperature-Driven Robust Disease Detection in Brain and Gastrointestinal Disorders via Context-Aware Adaptive Knowledge DistillationKnowledge distillation → Distillation for medical imaging
Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI NetworksLLM agents and tool use → Multimodal and embodied agents
DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill AcquisitionDeep reinforcement learning methods → RL training of language and agent models
A Grounded Memory System For Smart Personal AssistantsLLM agents and tool use → Agent memory systems
Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Apple: Toward General Active Perception via Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
DiffLocks: Generating 3D Hair from a Single Image using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from TextbooksMultimodal LLMs / vision-language models → Medical vision-language models
Interaction-Aware Parameter Privacy-Preserving Data Sharing in Coupled Systems via Particle Filter Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
UniVLA: Learning to Act Anywhere with Task-centric Latent ActionsVision-language-action models → Human-video and latent-action pretraining
TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with DemonstrationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-DistillationLLM safety and security → Machine unlearning +1
Efficient Information Updates in Compute-First Networking via Reinforcement Learning with Joint AoI and VoIDeep reinforcement learning methods → RL for energy, networks and operations
ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art UnderstandingRetrieval-augmented generation → Multimodal RAG
Offline Multi-agent Reinforcement Learning via Sequential Score DecompositionOffline RL and imitation learning from data → Offline multi-agent RL
Learning Power Control Protocol for In-Factory 6G SubnetworksDeep reinforcement learning methods → RL for energy, networks and operations
FloE: On-the-Fly MoE Inference on Memory-constrained GPUMixture-of-experts → Efficient MoE training and inference systems +1
NeoQA: Evidence-based Question Answering with Generated News EventsRetrieval-augmented generation → RAG robustness and adaptive retrieval
Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UIMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
A 3D pocket-aware and evolutionary conserved interaction guided diffusion model for molecular optimizationDiffusion models → Flow matching, time series and science
FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion PriorsDiffusion models → Diffusion for compression and wireless
PICD: Versatile Perceptual Image Compression with Diffusion RenderingDiffusion models → Diffusion for compression and wireless
AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM AgentsLLM reasoning → Reasoning for agents, planning and code +2
Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value DecompositionDiffusion models → Diffusion foundations and sampling
Describe Anything in Medical ImagesMultimodal LLMs / vision-language models → Medical vision-language models
3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen TasksVision-language-action models → 3D and spatial-aware VLA
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-DesignMixture-of-experts → MoE large language models
Demystifying Diffusion Policies: Action Memorization and Simple Lookup Table AlternativesDiffusion models → Diffusion and flow policies for robotics
FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market ConditionsDiffusion models → Flow matching, time series and science +1
Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIMEfficient LLM inference and serving → KV cache optimization
Multi-Agent Systems for Robotic Autonomy with LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
APOLLO: Automated LLM and Lean Collaboration for Advanced Formal ReasoningLLM reasoning → Mathematical reasoning
Evolutionary thoughts: integration of large language models and evolutionary algorithmsLLM reasoning → Test-time compute and efficient thinking
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical ApplicationsLLM alignment / RLHF / preference optimisation → Medical LLM alignment
Automated Learning of Semantic Embedding Representations for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
You Are Your Best Teacher: Semi-Supervised Surgical Point Tracking with Cycle-Consistent Self-DistillationKnowledge distillation → Distillation for medical imaging
LLM-Text Watermarking based on Lagrange InterpolationLLM safety and security → Watermarking generated content and models
Assessing Robustness to Spurious Correlations in Post-Training Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
See What I Mean? CUE: A Cognitive Model of Understanding Explanations
A Data-Driven Approach to Enhancing Gravity Models for Trip Demand Prediction
Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
Multilinear subspace learning for person re-identification based fusion of high order tensor features
The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations
Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Results
Graph-based Online Monitoring of Train Driver States via Facial and Skeletal Features
Evaluating Financial Sentiment Analysis with Annotators Instruction Assisted Prompting: Enhancing Contextual Interpretation and Stock Prediction Accuracy
Efficient Fairness Testing in Large Language Models: Prioritizing Metamorphic Relations for Bias Detection
CellVerse: Do Large Language Models Really Understand Cell Biology?
QoSBERT: An Uncertainty-Aware Approach based on Pre-trained Language Models for Service Quality Prediction
Graph Laplacian Wavelet Transformer via Learnable Spectral Decomposition
KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery
PromptIQ: Who Cares About Prompts? Let System Handle It -- A Component-Aware Framework for T2I Generation
Opening the Scope of Openness in AI
Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference
Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
Structured Prediction with Abstention via the Lov'asz Hinge
Tweedie Regression for Video Recommendation System
My Emotion on your face: The use of Facial Keypoint Detection to preserve Emotions in Latent Space Editing
Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics
What Do People Want to Know About Artificial Intelligence (AI)? The Importance of Answering End-User Questions to Explain Autonomous Vehicle (AV) Decisions
MAGE:A Multi-stage Avatar Generator with Sparse Observations
Engineering Risk-Aware, Security-by-Design Frameworks for Assurance of Large-Scale Autonomous AI Models
Direct Data Driven Control Using Noisy Measurements
Camera Control at the Edge with Language Models for Scene Understanding
Towards AI-Driven Human-Machine Co-Teaming for Adaptive and Agile Cyber Security Operation Centers
Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark
Deep Learning-Based Robust Optical Guidance for Hypersonic Platforms
Embedding Atlas: Low-Friction, Interactive Embedding Visualization
RiM: Record, Improve and Maintain Physical Well-being using Federated Learning
Offensive Security for AI Systems: Concepts, Practices, and Applications
A Comprehensive Data Description for LoRaWAN Path Loss Measurements in an Indoor Office Setting: Effects of Environmental Factors
The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
LMLCC-Net: A Semi-Supervised Deep Learning Model for Lung Nodule Malignancy Prediction from CT Scans using a Novel Hounsfield Unit-Based Intensity Filtering
CAST: Time-Varying Treatment Effects with Application to Chemotherapy and Radiotherapy on Head and Neck Squamous Cell Carcinoma
Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects
Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA
Latent Diffeomorphic Dynamic Mode Decomposition
Scalable Quantum State Preparation via Large-Language-Model-Driven Discovery
Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients
NSF-MAP: Neurosymbolic Multimodal Fusion for Robust and Interpretable Anomaly Prediction in Assembly Pipelines
Mask-PINNs: Mitigating Internal Covariate Shift in Physics-Informed Neural Networks
Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
Enterprise Architecture as a Dynamic Capability for Scalable and Sustainable Generative AI adoption: Bridging Innovation and Governance in Large Organisations
Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition
Document Attribution: Examining Citation Relationships using Large Language Models
A Machine-Learning Compositional Study of Exoplanetary Material Accreted Onto Five Helium-Atmosphere White Dwarfs with textttcecilia
Anymate: A Dataset and Baselines for Learning 3D Object Rigging
Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks
VIN-NBV: A View Introspection Network for Next-Best-View Selection
Let Humanoids Hike! Integrative Skill Development on Complex Trails

All 220