Rui Hu

papers

1,416

total citations

papers (15)

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

ICLR 2024arXiv

citations

Conditional Entropy Coding for Efficient Video Compression

ECCV 2020arXiv

citations

Rethinking Closed-Loop Training for Autonomous Driving

ECCV 2022arXiv

citations

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

CVPR 2025arXiv

citations

ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming

AAAI 2025

citations

Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

CVPR 2025arXiv

citations

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

ECCV 2024arXiv

citations

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

ICCV 2025arXiv

citations

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

NEURIPS 2025arXiv

citations

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

CVPR 2025arXiv

citations

ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models

CVPR 2025arXiv

citations

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

ICML 2025arXiv

citations

Rui Hu

papers (15)

Learning Lane Graph Representations for Motion Forecasting

PnPNet: End-to-End Perception and Prediction With Tracking in the Loop

PolyTransform: Deep Polygon Transformer for Instance Segmentation

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Conditional Entropy Coding for Efficient Video Compression

Rethinking Closed-Loop Training for Autonomous Driving

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming

Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

papers (15)

Learning Lane Graph Representations for Motion Forecasting

PnPNet: End-to-End Perception and Prediction With Tracking in the Loop

PolyTransform: Deep Polygon Transformer for Instance Segmentation

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Conditional Entropy Coding for Efficient Video Compression

Rethinking Closed-Loop Training for Autonomous Driving

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming

Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models

Finite-Time Analysis of Discrete-Time Stochastic Interpolants