Search papers, labs, and topics across Lattice.
3
0
6
4
UltraX achieves the highest average performance across datasets while using fewer training tokens, redefining efficiency in data refinement for LLMs.
MOPD achieves superior capability integration in LLMs by distilling knowledge from multiple RL teachers without losing performance, setting a new standard for post-training methods.
Forget full attention: a hybrid sparse-linear attention model, MiniCPM-SALA, achieves 3.5x faster inference and supports 1M context length on a single GPU, all while maintaining comparable performance.
