25 citations · 39 across the 12 of their papers we have counts for
13 papers
What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute
Zhixu Du, Weijia Han, Hai Helen Li +1
Large language models spend the same amount of computation on every token they generate, regardless of how difficult each token is to produce. Methods such as speculative decoding…
AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems
Zhixu Du, Yiran Chen
Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at production rates beyond any hu…
DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions
Zishan Shao, Lixun Zhang, Kangning Cui +10
Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if any, is used at decode time r…
Swimba: Switch Mamba Model Scales State Space Models
Zhixu Du, Krishna Teja Chitty-Venkata, Murali Emani +3
Mixture-of-experts (MoE) is a common approach for increasing parameter capacity, but applying MoE to state space model (SSM) token mixers can multiply the cost of the recurrent sta…
FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
Zishan Shao, Yixiao Wang, Qinsi Wang +6
Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works…
MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing
Haiyue Ma, Zhixu Du, Yiran Chen
In multi-GPU Mixture-of-Experts (MoE) network, experts are distributed across different GPUs, which creates load imbalance as each expert processes different number of tokens. Rece…
A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models
Cong Guo, Feng Cheng, Zhixu Du +21
The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language…
Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback
Jingwei Sun, Zhixu Du, Yiran Chen
Large language models (LLMs) have demonstrated remarkable proficiency in a range of natural language processing tasks. Once deployed, LLMs encounter users with personalized factual…
FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
Jingwei Sun, Ziyue Xu, Hongxu Yin +4
Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data…
SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Zhixu Du, Shiyu Li, Yuhao Wu +7
Mixture-of-Experts (MoE) has emerged as a favorable architecture in the era of large models due to its inherent advantage, i.e., enlarging model capacity without incurring notable…
Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties
Jingwei Sun, Zhixu Du, Anna Dai +4
Vertical federated learning (VFL) enables a service provider (i.e., active party) who owns labeled features to collaborate with passive parties who possess auxiliary features to im…
Rethinking Normalization Methods in Federated Learning
Zhixu Du, Jingwei Sun, Ang Li +4
Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. In this work, we explicitly uncover extern…
Improved Input Reprogramming for GAN Conditioning
Tuan Dinh, Daewon Seo, Zhixu Du +2
We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approa…