arxiv:2512.13607
Yangyi Chen
YangyiYY
AI & ML interests
Multimodal, Large Language Models
Recent Activity
upvoted a paper 2 days ago
It Takes Workflows to Evolve Better Workflows upvoted a paper 5 days ago
Sharpening Tax in Post-Training updated a model 7 days ago
YangyiYY/qwen3-8b-general-grpo-16kOrganizations
None yet
models 37
YangyiYY/qwen3-8b-general-grpo-16k
8B • Updated • 1.3k
YangyiYY/cascade-8b-code-ppo-32k
8B • Updated • 2.95k
YangyiYY/cascade-8b-toolrl-ppo
8B • Updated • 1.06k
YangyiYY/cascade-8b-math-ppo-32k
8B • Updated • 9.57k
YangyiYY/cascade-8b-general-ppo-16k
8B • Updated • 2.31k
YangyiYY/qwen3-8b-general-ppo-16k
8B • Updated • 599
YangyiYY/qwen3-8b-toolrl-ppo
8B • Updated • 232 • 3
YangyiYY/qwen3-8b-code-ppo-actor
8B • Updated • 3.61k
YangyiYY/qwen3-8b-numina-math-ppo-actor
8B • Updated • 219
YangyiYY/qwen2.5-7b-instruct-nct-ppo-critic
7B • Updated • 7
datasets 15
YangyiYY/rl-value-eval-general-ood
Viewer • Updated • 2k • 82
YangyiYY/rl-value-eval-general
Viewer • Updated • 696 • 66
YangyiYY/rl-value-confidence-train-general
Viewer • Updated • 10k • 162
YangyiYY/rl-value-eval-tool-ood
Viewer • Updated • 597 • 56
YangyiYY/rl-value-eval-tool
Viewer • Updated • 80 • 47
YangyiYY/rl-value-confidence-train-tool
Viewer • Updated • 3.92k • 88
YangyiYY/rl-value-eval-code-ood
Viewer • Updated • 193 • 67
YangyiYY/rl-value-eval-math
Viewer • Updated • 5.06k • 110
YangyiYY/rl-value-eval-code
Viewer • Updated • 2.48k • 133
YangyiYY/rl-value-confidence-train-code
Viewer • Updated • 4.94k • 122