Taki WU

taki555's activity

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

authored a paper 21 days ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 25 days ago • 79

upvoted a paper 22 days ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 25 days ago • 79

upvoted a paper 26 days ago

OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence

Paper • 2604.07296 • Published 28 days ago • 39

upvoted a collection about 1 month ago

The Art of Efficient Reasoning

Collection

Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2

New activity in taki555/Qwen3-30B-A3B-Thinking-2507-Art about 1 month ago

Improve model card metadata and content

#1 opened about 1 month ago by

nielsr

New activity in taki555/Qwen3-30B-A3B-Instruct-2507-Art about 1 month ago

Add pipeline tag, library name, and paper link to model card

#1 opened about 1 month ago by

nielsr

New activity in taki555/Qwen3-4B-Instruct-2507-Art about 1 month ago

Add metadata and improve model card

#1 opened about 1 month ago by

nielsr

New activity in taki555/Qwen3-1.7B-Art about 1 month ago

Improve model card: add metadata and links

#1 opened about 1 month ago by

nielsr

New activity in taki555/Qwen3-0.6B-Art about 1 month ago

Add pipeline tag, library name, and link to paper

#1 opened about 1 month ago by

nielsr

New activity in taki555/Qwen3-4B-Thinking-2507-Art about 1 month ago

Update model card with metadata and paper link

#1 opened about 1 month ago by

nielsr

updated a collection about 2 months ago

The Art of Efficient Reasoning

Collection

Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2

updated a model about 2 months ago

taki555/Qwen3-30B-A3B-Thinking-2507-Art

Text Generation • 31B • Updated Mar 24 • 63

published a model about 2 months ago

taki555/Qwen3-30B-A3B-Thinking-2507-Art

Text Generation • 31B • Updated Mar 24 • 63

updated a collection 2 months ago

The Art of Efficient Reasoning

Collection

Project: https://wutaiqiang.github.io/project/Art • 8 items • Updated Mar 18 • 2

updated a model 2 months ago

taki555/Qwen3-4B-Thinking-2507-Art

Text Generation • 4B • Updated Mar 24 • 51

published a model 2 months ago

taki555/Qwen3-4B-Thinking-2507-Art

Text Generation • 4B • Updated Mar 24 • 51

upvoted a paper 2 months ago

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

Paper • 2603.00889 • Published Mar 1 • 56

upvoted a collection 2 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.59k

updated 2 models 2 months ago

taki555/Qwen3-30B-A3B-Instruct-2507-Art

Text Generation • 31B • Updated Mar 24 • 65

taki555/Qwen3-4B-Instruct-2507-Art

Text Generation • 4B • Updated Mar 24 • 54 • 1