Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
4
6
A reward-compatible bounded mixing mechanism for $\gamma\mathrm{OPD}$ that balances verifiable outcome feedback with the discounted OPD advantage to move beyond purely teacher-dependent optimization is developed.
Closing 97% of the performance gap between student and teacher models while cutting rollout steps by nearly three times reveals the power of adaptive domain scheduling in multi-teacher distillation.
A mere 0.01% of tokens can destabilize LLM reinforcement learning, but masking their gradient updates unlocks significant performance gains.