Justin Chen

dinobby's activity

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

updated a model 4 days ago

dinobby/RG-25-tasks-4-ICL-400-steps

0.8B • Updated 4 days ago • 6

published a model 4 days ago

dinobby/RG-25-tasks-4-ICL-400-steps

0.8B • Updated 4 days ago • 6

updated a model 4 days ago

dinobby/RG-25-tasks-400-steps

0.8B • Updated 4 days ago • 6

published a model 4 days ago

dinobby/RG-25-tasks-400-steps

0.8B • Updated 4 days ago • 6

published 9 models 5 days ago

dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-GPTo4-mini

4B • Updated Sep 19 • 6

dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-Self

4B • Updated Sep 19 • 9

dinobby/OctoThinker-3B-Hybrid-Zero-GRPO

4B • Updated Sep 19 • 10

dinobby/Qwen3-4B-Instruct-2507-NuRL-GPTo4-mini

4B • Updated Sep 19 • 6

dinobby/Qwen3-4B-Instruct-2507-NuRL-Self

4B • Updated Sep 19 • 7

dinobby/Qwen3-4B-Instruct-2507-GRPO

4B • Updated Sep 19 • 6

dinobby/Llama3.2-3B-Instruct-NuRL-GPTo4-mini

4B • Updated Sep 19 • 6

dinobby/Llama3.2-3B-Instruct-GRPO

4B • Updated Sep 19 • 89

dinobby/Llama3.2-3B-Instruct-NuRL-Self

4B • Updated Sep 19 • 12

commented 2 papers about 1 month ago

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

Paper • 2510.01581 • Published Oct 2 •

2

Nudging the Boundaries of LLM Reasoning

Paper • 2509.25666 • Published Sep 30 • 4 •

2

updated 5 models about 2 months ago

dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-GPTo4-mini

4B • Updated Sep 19 • 6

dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-Self

4B • Updated Sep 19 • 9

dinobby/OctoThinker-3B-Hybrid-Zero-GRPO

4B • Updated Sep 19 • 10

dinobby/Qwen3-4B-Instruct-2507-NuRL-GPTo4-mini

4B • Updated Sep 19 • 6

dinobby/Qwen3-4B-Instruct-2507-NuRL-Self

4B • Updated Sep 19 • 7