Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
10
LLMs can learn effective dynamic embeddings for massive combinatorial optimization problems with a shallow policy by selectively propagating memory across rollout steps, bypassing the need for expensive full recomputation or external labels.
Evolution strategies can optimize large language models for long-horizon tasks with minimal GPU resources, outperforming traditional reinforcement learning approaches.
