Ran He

20

Papers

1,007

Total Citations

Papers (20)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models

Breaking the Low-Rank Dilemma of Linear Attention

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

Heterogeneous Test-Time Training for Multi-Modal Person Re-identification

RMT: Retentive Networks Meet Vision Transformers

Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer

Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration

Backdoor Defense via Test-Time Detecting and Repairing

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification

Rectifying Magnitude Neglect in Linear Attention

Exploring Vacant Classes in Label-Skewed Federated Learning

Protecting Model Adaptation from Trojans in the Unlabeled Data