Search papers, labs, and topics across Lattice.
AI Platform, Xiaohongshu Inc.
2
0
6
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.
Omni-modal RL post-training just got a whole lot faster: Relax delivers up to 2x speedups over existing systems, even for massive MoE models, without sacrificing reward convergence.
