activity
20202024
most citedDeja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

19 citations · 27 across the 6 of their papers we have counts for

collaborators

7 papers

cs.LG2024

Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts

Zichang Liu, Qingyun Liu, Yuening Li +6

Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experimen…

cs.LG2023

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

Aditya Desai, Benjamin Meisburger, Zichang Liu +1

Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models a…

cs.LG202319 cited

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Zichang Liu, Jue Wang, Tri Dao +8

Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference t…

cs.LG20211 cited

Efficient Inference via Universal LSH Kernel

Zichang Liu, Benjamin Coleman, Anshumali Shrivastava

Large machine learning models achieve unprecedented performance on various tasks and have evolved as the go-to technique. However, deploying these compute and memory hungry models…

cs.DC20214 cited

Efficient and Less Centralized Federated Learning

Li Chou, Zichang Liu, Zhuang Wang +1

With the rapid growth in mobile computing, massive amounts of data and computing resources are now located at the edge. To this end, Federated learning (FL) is becoming a widely ad…

eess.SP2020

Neighbor Oblivious Learning (NObLe) for Device Localization and Tracking

Zichang Liu, Li Chou, Anshumali Shrivastava

On-device localization and tracking are increasingly crucial for various applications. Along with a rapidly growing amount of location data, machine learning (ML) techniques are be…