Chengzu
@chengzu-li.bsky.social
55 followers 100 following 9 posts
PhD student at Language Technology Lab, University of Cambridge
Posts Media Videos Starter Packs
chengzu-li.bsky.social
Round of applause for the fantastic collaborators in this project: Wenshan Wu, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulić and Furu Wei🥳🥳
chengzu-li.bsky.social
🔗 MVoT + CoT: New Ceiling for Reasoning

MVoT doesn’t replace CoT—it elevates it. By combining MVoT and CoT, the synergy of multimodal reasoning and verbal reasoning unlocks the performance upper bound, proving that two reasoning paradigms are potentially better than one!
chengzu-li.bsky.social
🎨 Revolutionizing Visual Reasoning with Token Discrepancy Loss

Messy visuals? Not anymore. Our token discrepancy loss ensures that MVoT generates accurate, meaningful visualizations with less redundancy.

Result? Better images, clearer reasoning, stronger performance.
chengzu-li.bsky.social
🎯 Performance Boosts with MVoT

MVoT isn’t just new—it’s better.
🔥 Better and more stable performance than CoT, particularly in complex scenarios like FrozenLake.
🌟 Plug-and-play power: Supercharges models like GPT-4o for unprecedented versatility.
chengzu-li.bsky.social
🧠MVoT

MVoT moves beyond Chain-of-Thought (CoT) to enable AI to imagine what it thinks with generated visual images. By blending verbal and visual reasoning, MVoT makes tackling complex problems more intuitive, interpretable, and powerful.
chengzu-li.bsky.social
Forget just thinking in words.

🔔Our New Preprint:
🚀 New Era of Multimodal Reasoning🚨
🔍 Imagine While Reasoning in Space with MVoT

Multimodal Visualization-of-Thought (MVoT) revolutionizes reasoning by generating visual "thoughts" that transform how AI thinks, reasons, and explains itself.
chengzu-li.bsky.social
Hi would love to be added in the list! Thanks!
chengzu-li.bsky.social
🙋working on VLMs and would love to be added! Thanks!