Zichen Wen

zichenwen's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 9 days ago

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published 16 days ago • 62

authored 3 papers about 1 month ago

SiMilarity-Enhanced Homophily for Multi-View Heterophilous Graph Clustering

Paper • 2410.03596 • Published Oct 4, 2024

TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration

Paper • 2506.08403 • Published Jun 10

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Paper • 2506.10100 • Published Jun 11 • 10

authored a paper 2 months ago

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Paper • 2505.19147 • Published May 25 • 146

authored 3 papers 4 months ago

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

Paper • 2503.14905 • Published Mar 19 • 20

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Paper • 2502.11494 • Published Feb 17

LEGION: Learning to Ground and Explain for Synthetic Image Detection

Paper • 2503.15264 • Published Mar 19 • 21

authored a paper 8 months ago

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Paper • 2412.02592 • Published Dec 3, 2024 • 24

authored a paper about 1 year ago

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Paper • 2407.04842 • Published Jul 5, 2024 • 57