Search papers, labs, and topics across Lattice.
Astronautics WeChat AI, Tencent ▲, Nanjing University of Aeronautics, Fudan University Independent Researcher
2
0
4
Threshold-sensitive KV cache pruning is out; ReFreeKV's adaptive approach achieves robust memory efficiency without predefined limits.
Multilingual MoEs can achieve best-in-class performance-to-compute ratios, even with extreme sparsity, by strategically upcycling from dense models and exhibiting structured expert activation patterns across languages.
