Chengzu Li

chengzu's activity

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

upvoted a paper about 12 hours ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

Paper • 2602.01851 • Published 1 day ago • 13

upvoted a paper 3 months ago

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

Paper • 2510.24514 • Published Oct 28, 2025 • 22

upvoted a paper 5 months ago

Lost in Embeddings: Information Loss in Vision-Language Models

Paper • 2509.11986 • Published Sep 15, 2025 • 29

upvoted 2 papers 9 months ago

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Paper • 2501.07542 • Published Jan 13, 2025 • 3

Visual Planning: Let's Think Only with Images

Paper • 2505.11409 • Published May 16, 2025 • 57