Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Affiliation:
6
0
4
4
LLM reasoning distillation can be significantly improved by tailoring trace construction to the student's learning process, not just the answer.
Traditional two-tower architectures can outperform state-of-the-art models when enhanced with LLM-driven semantic representations.
Selecting relevant evidence spans for test-time training can boost long-context LLM accuracy by up to 15%.
Pruning redundant reasoning in teacher traces can boost recommendation model performance while streamlining output length.
Achieving near-autoregressive accuracy while boosting decoding speed by over 2.4 times could redefine efficiency benchmarks in generative reasoning tasks.
Highlighting pivotal evidence can boost LLM performance without altering the original context, leading to substantial improvements in reasoning tasks.