AI & ML interests
None defined yet.
Recent Activity
View all activity
Resources for the Enigmata Project: https://seed-enigmata.github.io.
-
BytedTsinghua-SIA/Enigmata-Qwen2.5-32B
33B • Updated • 11 • 3 -
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Paper • 2505.19914 • Published • 46 -
BytedTsinghua-SIA/Enigmata-Eval
Viewer • Updated • 4.76k • 1.81k • 2 -
BytedTsinghua-SIA/Enigmata-Data
Preview • Updated • 234 • 4
memo
-
BytedTsinghua-SIA/DAPO-Math-17k
Viewer • Updated • 1.79M • 12.3k • 185 -
BytedTsinghua-SIA/AIME-2024
Viewer • Updated • 960 • 5.28k • 11 -
BytedTsinghua-SIA/DAPO-Qwen-32B
Text Generation • 33B • Updated • 70 • • 12 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 146
memo
Resources for the Enigmata Project: https://seed-enigmata.github.io.
-
BytedTsinghua-SIA/Enigmata-Qwen2.5-32B
33B • Updated • 11 • 3 -
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Paper • 2505.19914 • Published • 46 -
BytedTsinghua-SIA/Enigmata-Eval
Viewer • Updated • 4.76k • 1.81k • 2 -
BytedTsinghua-SIA/Enigmata-Data
Preview • Updated • 234 • 4
-
BytedTsinghua-SIA/DAPO-Math-17k
Viewer • Updated • 1.79M • 12.3k • 185 -
BytedTsinghua-SIA/AIME-2024
Viewer • Updated • 960 • 5.28k • 11 -
BytedTsinghua-SIA/DAPO-Qwen-32B
Text Generation • 33B • Updated • 70 • • 12 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 146