Jihan Yang

Jihan Yang on Hugging Face Daily Papers: 8 papers, 2 in the top 3 of their day, 364 upvotes.

1. Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders 51 upvotes, #8 of 2026-01-23
2. Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts 7 upvotes, #9 of 2025-11-07
3. Cambrian-S: Towards Spatial Supersensing in Video 34 upvotes, #4 of 2025-11-07
4. UniTok: A Unified Tokenizer for Visual Generation and Understanding 27 upvotes, #6 of 2025-02-28
5. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 100 upvotes, #1 of 2025-01-29
6. Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces 22 upvotes, #5 of 2024-12-19
7. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs 48 upvotes, #2 of 2024-06-25
8. V-IRL: Grounding Virtual Intelligence in Real Life 16 upvotes, #11 of 2024-02-06

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.