Thinking Space

community

https://thinking-space.github.io/

Thinking-Space

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

hbx authored a paper about 7 hours ago

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

hbx authored a paper about 7 hours ago

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

hbx authored a paper about 7 hours ago

CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning

View all activity

Papers

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

View all Papers

Collections 2

models 4

datasets 1

Thinking-Space/OpenThought3-Qwen3-4B

Viewer • Updated May 12 • 305k • 73 • 2

Thinking Space

AI & ML interests

Recent Activity

Papers

Collections 2

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Thinking-Space/UltraData-IF-1.5B

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Thinking-Space/Qwen3-1.7B-SFT

Thinking-Space/Qwen3-4B-Base-GRPO

Thinking-Space/OpenThought3-Qwen3-4B

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Thinking-Space/UltraData-IF-1.5B

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Thinking-Space/Qwen3-1.7B-SFT

Thinking-Space/Qwen3-4B-Base-GRPO

Thinking-Space/OpenThought3-Qwen3-4B

models 4

Thinking-Space/UltraData-IF-1.5B

Thinking-Space/Qwen3-1.7B-Base-OPD

Thinking-Space/Qwen3-1.7B-SFT

Thinking-Space/Qwen3-4B-Base-GRPO

datasets 1

Thinking-Space/OpenThought3-Qwen3-4B

AI & ML interests

Recent Activity

Papers

Team members 4

Collections 2

models 4 Sort: Recently updated

datasets 1

models 4