xhl

xhl on Hugging Face Daily Papers: 7 papers, 1 in the top 3 of their day, 164 upvotes.

1. Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers 6 upvotes, #48 of 2025-09-30
2. OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning 28 upvotes, #12 of 2025-09-03
3. OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning 20 upvotes, #7 of 2025-05-08
4. MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine 23 upvotes, #4 of 2024-08-07
5. What If We Recaption Billions of Web Images with LLaMA-3? 35 upvotes, #4 of 2024-06-13
6. CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \10,000 Budget; An Extra 4,000 Unlocks 81.8% Accuracy 13 upvotes, #3 of 2023-06-28
7. An Inverse Scaling Law for CLIP Training 3 upvotes, #6 of 2023-05-12

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.