Search papers, labs, and topics across Lattice.
6
0
4
3
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.
Re-ranking can make or break user engagement, and GR2 boosts performance by over 18% by harnessing the power of LLMs in ways previously unexplored.
Highlighting pivotal evidence can boost LLM performance without altering the original context, leading to substantial improvements in reasoning tasks.
