[Under Review] Argument Reconstruction as Supervision for Critical Thinking in LLMs
ChuGyouk PRO
ChuGyouk
AI & ML interests
LLM towards SuperIntelligence
Recent Activity
liked a model about 7 hours ago
deepseek-ai/DeepSeek-V4.1-Flash upvoted a paper 7 days ago
WHALE: A Simple Recipe for Joint Harness-Weight Optimization updated a model 8 days ago
ChuGyouk/Qwen3-4B-DeepWriting-RL-retryOrganizations
None yet
models 23
ChuGyouk/Qwen3-4B-DeepWriting-RL-retry
4B • Updated • 40
ChuGyouk/Qwen3-4B-DeepWriting-RL
4B • Updated • 64
ChuGyouk/DR-Tulu-SFT-4B
Text Generation • 4B • Updated • 158
ChuGyouk/Qwen3-4B-DeepWriting-SFT
Text Generation • 4B • Updated • 1.14k • 1
ChuGyouk/J-Zero-8B
Updated
ChuGyouk/J-Zero-4B
Updated
ChuGyouk/ours-fix
Updated
ChuGyouk/c4m2v6t8
Updated
ChuGyouk/x3j8k2v9
Updated
ChuGyouk/q8z1w7k3
Updated
datasets 83
ChuGyouk/DeepWriting-RL-logs-retry
Viewer • Updated • 256 • 192
ChuGyouk/DeepWriting-RL-logs
Viewer • Updated • 448 • 364
ChuGyouk/DeepWriting-20K-SFT
Viewer • Updated • 8.68k • 49
ChuGyouk/DeepWriting-20K-RL
Viewer • Updated • 6.57k • 47
ChuGyouk/cw-rp-glm-5.2-32k
Viewer • Updated • 114k • 79 • 1
ChuGyouk/RL-Math-Test
Preview • Updated • 27 • 1
ChuGyouk/DAPO-DeepScaleR-Filtered
Viewer • Updated • 30.3k • 20
ChuGyouk/Arguinas
Viewer • Updated • 3.18k • 61 • 6
ChuGyouk/CoderForge-Preview-Filtered
Viewer • Updated • 155k • 32
ChuGyouk/FakeFrontierMath-Samples
Viewer • Updated • 12 • 8