Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology of China
2
0
5
LLMs can be sped up by over 2x without sacrificing accuracy, by compressing the input and predicting multiple output tokens at once using a unified framework.
End-to-end retrosynthetic planning, previously reliant on fragmented prediction-search hybrids, now achieves state-of-the-art performance thanks to a unified, reasoning-driven generative framework.
