A 920-example distillation from DeepSeek R1 outperforms zero-RL models on the same Qwen2.5-32B base across several math and science benchmarks.
Qwq-32b: Embracing the power of reinforcement learning, March 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning
A 920-example distillation from DeepSeek R1 outperforms zero-RL models on the same Qwen2.5-32B base across several math and science benchmarks.