Shang-Wen Daniel Li

swdanielli's activity

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

upvoted a paper about 1 month ago

DepthLM: Metric Depth From Vision Language Models

Paper • 2509.25413 • Published Sep 29 • 6

upvoted a collection about 2 months ago

Meta CLIP

Collection

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated Jul 21 • 1

upvoted 4 collections 3 months ago

Infrastructure

Collection

216 items • Updated 11 days ago • 8

model-architecture

Collection

3 items • Updated Aug 9 • 2

Vision LLM

Collection

1 item • Updated Aug 3 • 1

MetaCLIP

Collection

MetaCLIP & MetaCLIP2 OpenCLIP and timm models. All models are dual timm + OpenCLIP (or just timm for specific vit encoders). • 24 items • Updated Sep 19 • 3

upvoted a paper 3 months ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29 • 28

upvoted a collection 3 months ago

Meta CLIP 1/2

Collection

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 11 items • Updated Aug 25 • 15

upvoted 5 papers over 1 year ago

SUPERB: Speech processing Universal PERformance Benchmark

Paper • 2105.01051 • Published May 3, 2021 • 1

Demystifying CLIP Data

Paper • 2309.16671 • Published Sep 28, 2023 • 20

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

Paper • 2305.10615 • Published May 18, 2023 • 1

DINOv2: Learning Robust Visual Features without Supervision

Paper • 2304.07193 • Published Apr 14, 2023 • 8

MoDE: CLIP Data Experts via Clustering

Paper • 2404.16030 • Published Apr 24, 2024 • 15