Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:, University of Michigan
2
0
3
57
Finite Littlestone dimension unlocks optimal no-regret language generation, achieving sublinear mistakes even with arbitrary demonstrations.
Training LLMs to explicitly optimize for how they're *actually* used at inference time unlocks substantial performance gains compared to standard fine-tuning.