Bo Liu

Benjamin-eecs's activity

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

authored 2 papers about 11 hours ago

Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

Paper • 2610.06269 • Published 6 days ago

Learning Stateful Predictive Knowledge From Experience

Paper • 2607.28638 • Published May 19 • 1

authored a paper 8 days ago

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

Paper • 2610.02202 • Published 10 days ago • 14

upvoted a paper 9 days ago

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

Paper • 2610.02202 • Published 10 days ago • 14

upvoted a paper 10 days ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 11 days ago • 274

published a dataset 17 days ago

Benjamin-eecs/openrsi-commit-runtime-assets

Updated 17 days ago • 304

updated a dataset 17 days ago

Benjamin-eecs/openrsi-commit-runtime-assets

Updated 17 days ago • 304

published an article 26 days ago

view article

Article

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

• 

quao627

•

26 days ago

• 15

upvoted an article 26 days ago

view article

Article

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

• 

quao627

•

26 days ago

• 15

updated 3 models about 2 months ago

spade-rl/SPADE-Qwen3-4B-Games

Text Generation • 4B • Updated Aug 26 • 205

spade-rl/SPADE-Qwen3-30B-A3B-Games

Text Generation • 31B • Updated Aug 26 • 183

spade-rl/SPADE-Qwen3-8B-Games

Text Generation • 8B • Updated Aug 26 • 172 • 1

updated 6 datasets about 2 months ago

spade-rl/SPADE-Grounding-Corpus-Games-15K

Viewer • Updated Aug 26 • 15k • 59

spade-rl/SPADE-Grounding-Corpus-ToolUse-15K

Viewer • Updated Aug 26 • 15.6k • 75 • 1

spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUse

Viewer • Updated Aug 26 • 11k • 106 • 1

spade-rl/SPADE-Environment-Pool-GPT5.5-Games

Preview • Updated Aug 26 • 525 • 1

spade-rl/SPADE-Environments-ToolUse

Updated Aug 26 • 523 • 2

spade-rl/SPADE-Environments-Qwen3-30B-Games

Updated Aug 26 • 727

updated a Space about 2 months ago

Running

SPADE

♠

A model that writes and solves its own environments.

upvoted a paper about 2 months ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 161