DYPO unifies SFT and RL with three new components to linearly reduce fitting bias and variance, delivering 4.8% gains on reasoning benchmarks and 13.3% on out-of-distribution tasks.
The expected squared norm is: E[∥Biassingle∥2] =E[∥b sys +b k∥2] =∥b sys∥2 +E[∥b k∥2] + 2b⊤ sys E[bk]|{z} =0 =∥b sys∥2 + ¯σ2 bias (28)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
DYPO unifies SFT and RL with three new components to linearly reduce fitting bias and variance, delivering 4.8% gains on reasoning benchmarks and 13.3% on out-of-distribution tasks.