Search papers, labs, and topics across Lattice.
2
0
4
Get RL-level multi-turn LLM performance with SFT-level efficiency by decoupling trajectory generation and optimization via importance weighting.
RAMBO's instability got you down? ROMI offers a robust, value-aware model learning approach with implicitly differentiable adaptive weighting that outperforms RAMBO and other SOTA methods in offline RL benchmarks.
