Dongxu Li

Dongxu Li on Hugging Face Daily Papers: 4 papers, 2 in the top 3 of their day, 188 upvotes.

1. MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer 49 upvotes, #2 of 2025-09-22
2. ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks 3 upvotes, #34 of 2025-03-11
3. Aria: An Open Multimodal Native Mixture-of-Experts Model 102 upvotes, #1 of 2024-10-10
4. Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions 16 upvotes, #5 of 2024-01-04

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.