<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/41f4d2c9-7029-4321-93ed-7f025ef74a8f/480px-Google_Scholar_logo.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/41f4d2c9-7029-4321-93ed-7f025ef74a8f/480px-Google_Scholar_logo.png" width="40px" /> Google Scholar

</aside>

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

Zichang Liu, Zhaozhuo Xu*, Ben Coleman, Anshumali Shrivastava*

NeurIPS 2023

Scissorhands: Exploiting the Persistence of Importance Hypothesis for KV Cache Compression at Test Time 📄

Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava

NeurIPS 2023

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time 📄

Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhuang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, Beidi Chen

ICML 2023 (Oral)

Learning Multimodal Data Augmentation in Feature Space 📄

Zichang Liu, Zhiqiang Tang, Xingjian Shi, Aston Zhang, Mu Li, Anshumali Shrivastava, Andrew Gordon Wilson

ICLR 2023

Retaining Knowledge for Learning with Dynamic Definition 📄

Zichang Liu, Benjamin Coleman, Tianyi Zhang, Anshumali Shrivastava