by Edith Ngai Papers
2 papers found
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
Jinze Li, Yixing Xu, Haiduo Huang et al.
ICML 2025posterarXiv:2503.10135
Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
Yun-Hin Chan, Rui Zhou, Running Zhao et al.
ICLR 2024spotlight