Bo Liu

Benjamin-eecs's activity

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

upvoted a paper 23 days ago

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

Paper • 2506.22419 • Published Jun 27 • 14

New activity in spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT 25 days ago

feat(enhance dataset card): add metadata, expanded intro, and sample usage

1

#2 opened 29 days ago by

nielsr

New activity in spiral-rl/Spiral-Qwen3-4B 25 days ago

feat(improve model card): add pipeline tag, library name, quickstart, and expanded details

1

#1 opened 29 days ago by

nielsr

New activity in spiral-rl/Spiral-DeepSeek-R1-Distill-Qwen-7B 25 days ago

feat: add pipeline tag, library name, and sample usage

#1 opened 29 days ago by

nielsr

updated a dataset 25 days ago

spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT

Viewer • Updated 25 days ago • 25.5k • 197

updated 2 models 25 days ago

spiral-rl/Spiral-DeepSeek-R1-Distill-Qwen-7B

Text Generation • 8B • Updated 25 days ago • 52 • 2

spiral-rl/Spiral-Qwen3-4B

Text Generation • 4B • Updated 25 days ago • 240 • 4

authored a paper 29 days ago

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Paper • 2506.24119 • Published 30 days ago • 46

published a dataset 29 days ago

spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT

Viewer • Updated 25 days ago • 25.5k • 197

published 2 models 29 days ago

spiral-rl/Spiral-DeepSeek-R1-Distill-Qwen-7B

Text Generation • 8B • Updated 25 days ago • 52 • 2

spiral-rl/Spiral-Qwen3-4B

Text Generation • 4B • Updated 25 days ago • 240 • 4

updated a collection 29 days ago

SPIRAL

Collection

4 items • Updated 29 days ago • 2

upvoted a paper 29 days ago

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Paper • 2506.24119 • Published 30 days ago • 46

commented a paper 29 days ago

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Paper • 2506.24119 • Published 30 days ago • 46 •

3

updated a collection about 1 month ago

SPIRAL

Collection

4 items • Updated 29 days ago • 2

updated 2 models about 2 months ago

the-acorn-ai/Qwen3-4B-Base-4K-SimpleNegotiation-Self-Role-0531-Benjamin-step160

4B • Updated Jun 1 • 2

the-acorn-ai/Qwen3-4B-Base-4K-SimpleNegotiation-Self-Role-0531-Benjamin-step512

4B • Updated Jun 1 • 2

published a model about 2 months ago

the-acorn-ai/Qwen3-4B-Base-4K-SimpleNegotiation-Self-Role-0531-Benjamin-step512

4B • Updated Jun 1 • 2