xhl PRO

Xianhang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 months ago

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers

Paper • 2509.24317 • Published Sep 29, 2025 • 11

upvoted 2 papers 6 months ago

DINOv3

Paper • 2508.10104 • Published Aug 13, 2025 • 297

Thyme: Think Beyond Images

Paper • 2508.11630 • Published Aug 15, 2025 • 81

upvoted a collection 9 months ago

OpenVision

Collection

27 items • Updated Aug 15, 2025 • 33

upvoted a paper 9 months ago

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning

Paper • 2505.04601 • Published May 7, 2025 • 29

upvoted a paper over 1 year ago

What If We Recaption Billions of Web Images with LLaMA-3?

Paper • 2406.08478 • Published Jun 12, 2024 • 43

upvoted 2 papers over 2 years ago

An Inverse Scaling Law for CLIP Training

Paper • 2305.07017 • Published May 11, 2023 • 3

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

Paper • 2306.15658 • Published Jun 27, 2023 • 12