Search papers, labs, and topics across Lattice.
5
0
9
19
ForeMoE achieves a remarkable 1.45脳 speedup in RL post-training by anticipating load imbalances, transforming how we manage expert resources in large language models.
Ditching text-based chain-of-thought unlocks better audio-visual reasoning by interleaving textual steps with a unified latent space that preserves dense sensory information.
Forget static policies: Autopoiesis uses LLMs to continuously rewrite serving policy code, adapting to runtime dynamics in ways human-designed systems can't.
DataFlex makes data-centric LLM training dramatically easier, unifying disparate methods for data selection, mixing, and reweighting into a single, efficient, and reproducible framework.
Achieve 1.69x faster Mixture-of-Experts training by dynamically re-arranging expert parameters to balance load across devices.
