Search papers, labs, and topics across Lattice.
3
0
8
3
Learned routers can outperform fixed-model baselines by 14.6%, revealing a new frontier in efficient LLM deployment.
Self-evolving rubric rewards can dramatically enhance audio reasoning in models, outperforming traditional methods by adapting to the model's evolving capabilities.
LLMs can now rank millions of candidates with significant accuracy gains thanks to a novel K-means clustering and graph-based ensemble approach that overcomes context length limitations.
