The Open LLM Architecture Lineage
103 open-weight architectures from Raschka's gallery, linked to their closest ancestors by config.json similarity alone and laid out by generation.
Wenhao Chai
Wenhao Chai is a first-year Ph.D. student in Computer Science at Princeton University, advised by Professor Karthik Narasimhan, and student researcher at Google DeepMind. He received his master's degree from University of Washington and bachelor's degree from Zhejiang University.
His research spans a wide range of topics in computer vision and machine learning. He has interned at Pika Labs working with Professor Christopher D. Manning, and Microsoft Research Asia.
He leads MovieChat, one of the first large multimodal models and benchmarks for hour-long video understanding with memory mechanism. He co-leads LiveCodeBench Pro, which has been listed as evaluation benchmarks by frontier models like Google Gemini and Meta Muse Spark. He has organized workshops and competitions at CVPR 2024, CVPR 2025, and CVPR 2026. His work has been featured by MIT Technology Review, and he was named to the AI25 list (AI innovators under 25) by Sequoia China and MIT Technology Review China.
He is currently working on AI for accelerating scientific research.
Life
All photos
Blog
All posts
LoopDiT: Loop Transformers for Diffusion Models
Looping DiT-B/4 under the MeanFlow one-step objective: at equal compute the looped model holds no advantage, and extra denoising steps pay off more than extra loops.
News
All news- Aug 2026One paper accepted by EMNLP 2026.
- Jul 2026One paper accepted by COLM 2026.
- Jul 2026Named to AI25 (25-under-25 AI innovators) by Sequoia China and MIT Technology Review China.
- Jun 2026One paper accepted by IJCV.
- Jun 2026Two papers accepted by ECCV 2026.
- Jun 2026We organize the 2nd Workshop on Knowledge-Intensive Multimodal Reasoning at CVPR 2026.
- May 2026I join Google DeepMind as a student researcher.
- May 2026Our FrontierCS blog post on CALICO covered by Berkeley EECS News.
- May 2026Two papers accepted by ICML 2026.
- Apr 2026We receive the Laude Institute Slingshots THREE grant to support our research.
- Feb 2026I start to serve as interview special host at Z Potentials.
- Feb 2026Two papers accepted by CVPR 2026.
- Jan 2026Five papers accepted by ICLR 2026.
- Dec 2025One paper accepted by IEEE TIP.
- Dec 2025I give an oral presentation at NeurIPS 2025 about Benchmarking Reasoning-Informed Visual Editing. Slides.
- Oct 2025Video-MMLU received the Outstanding Paper Award at ICCV 2025 Workshop @ Knowledge-Intensive Multimodal Reasoning with Travel Grant.
- Sep 2025One paper accepted by NeurIPS 2025, two papers accepted by NeurIPS 2025 Datasets and Benchmarks Track with one Oral.
- Sep 2025We receive the Lambda Research Grant $5,000 to support our research.
- Sep 2025Invited talk at Abaka AI and 2077AI titled Better and Longer Video Understanding. Slides.
- Sep 2025I join Princeton University as a CS Ph.D. student.
- Aug 2025One paper accepted by IEEE TPAMI.
- Aug 2025LiveCodeBench Pro presented in Open AGI Symposium at University of California, Berkeley. Slides.
- Jul 2025Interviewed by DeepTech and MIT Technology Review China. Post.
- Jun 2025One paper accepted by ICCV 2025.
- Jun 2025Featured in MIT Technology Review as one of the lead authors of LiveCodeBench Pro.
- Jun 2025One paper accepted by IROS 2025.
- May 2025One paper accepted by ACL 2025.
- Apr 2025We host CVPR 2025 Video Understanding Challenge @ LOVEU sponsored by Lambda.
- Mar 2025Graduated from the University of Washington with a Master's thesis on Large Multimodal Models for Video Captioning, nominated for the Distinguished Thesis Award by the ECE Department.
- Feb 2025Three papers accepted by CVPR 2025.
- Jan 2025Two papers accepted by ICLR 2025.
- Jul 2024Two papers accepted by ECCV 2024.
- Jun 2024I work with Pika Labs as intern to develop next-generation video understanding and generation models.
- Apr 2024We host CVPR 2024 Long-form Video Understanding Challenge @ LOVEU.
- Apr 2024Invited talk at AgentX seminar about our STEVE series works.
- Feb 2024Two papers accepted by CVPR 2024 with one highlight (2.81%).
- Feb 2024Invited talk at AAAI 2024 workshop @ IMAGEOMICS.
- Dec 2023One paper accepted by AAAI 2024.
- Jul 2023Two papers accepted by ICCV 2023.
- Feb 2023I become a research intern at Microsoft Research Asia (MSRA).
Office hours
FAQ for juniorsUndergraduate and master's students: if you want to talk about research ideas, career plans, or life in AI/ML, book a slot. I set aside at least 30 minutes every week for these meetings, and I encourage students from underrepresented groups to reach out. Open times are on my calendar.