alex shengzhi li

alexshengzhili's activity

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

upvoted a paper about 1 month ago

IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR

Paper • 2602.15849 • Published Jan 23 • 3

commented a paper about 2 months ago

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Paper • 2511.12884 • Published Nov 17, 2025 • 28 •

6

updated a dataset about 2 months ago

alexshengzhili/dataclaw-harbor-candidates

Viewer • Updated Mar 25 • 1.47k • 14

published a dataset about 2 months ago

alexshengzhili/dataclaw-harbor-candidates

Viewer • Updated Mar 25 • 1.47k • 14

upvoted an article about 2 months ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 151

upvoted an article 2 months ago

view article

Article

Reproducing NanoBanana 2's "Window Seat" with AI-Scientist-V3

• 

alexshengzhili

•

Mar 1

• 1

published an article 2 months ago

view article

Article

Reproducing NanoBanana 2's "Window Seat" with AI-Scientist-V3

• 

alexshengzhili

•

Mar 1

• 1

upvoted an article 2 months ago

view article

Article

AI Scientist v3: Agent Native refactor. Scale from 1-hour to 24 hours with Reviewer agent

• 

alexshengzhili

•

Mar 1

• 3

updated a dataset 2 months ago

alexshengzhili/ai-scientist-blog-assets

Viewer • Updated Mar 1 • 369 • 612

published a dataset 2 months ago

alexshengzhili/ai-scientist-blog-assets

Viewer • Updated Mar 1 • 369 • 612

published an article 2 months ago

view article

Article

AI Scientist v3: Agent Native refactor. Scale from 1-hour to 24 hours with Reviewer agent

• 

alexshengzhili

•

Mar 1

• 3

commented a paper 10 months ago

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

Paper • 2507.01352 • Published Jul 2, 2025 • 60 •

7

updated a model about 1 year ago

alexshengzhili/testing_lora

Updated May 3, 2025

published a model about 1 year ago

alexshengzhili/testing_lora

Updated May 3, 2025

updated a model about 1 year ago

alexshengzhili/qwen2_5_vl_7b_repcount

8B • Updated Apr 30, 2025 • 1

published a model about 1 year ago

alexshengzhili/qwen2_5_vl_7b_repcount

8B • Updated Apr 30, 2025 • 1

updated a dataset about 1 year ago

alexshengzhili/generalreasoning-stage2-combined-filtered-kept

Viewer • Updated Apr 29, 2025 • 25.4k • 10

published a dataset about 1 year ago

alexshengzhili/generalreasoning-stage2-combined-filtered-kept

Viewer • Updated Apr 29, 2025 • 25.4k • 10

updated a dataset about 1 year ago

alexshengzhili/generalreasoning-stage2-combined-filtered

Viewer • Updated Apr 29, 2025 • 130k • 7

published a dataset about 1 year ago

alexshengzhili/generalreasoning-stage2-combined-filtered

Viewer • Updated Apr 29, 2025 • 130k • 7