24 citations · 38 across the 24 of their papers we have counts for
7 papers · 1 filter
Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent
Zixiao Wang, Xingbo Du, Duzhen Zhang +1
Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regulator, the proxy reward mode…
FloE: On-the-Fly MoE Inference on Memory-constrained GPU
Yuxin Zhou, Zheng Li, Jun Zhang +5
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters…
HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models
Jun Zhang, Jue Wang, Huan Li +6
The significant computational demands of pretrained language models (PLMs), which often require dedicated hardware, present a substantial challenge in serving them efficiently, esp…
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
Jun Zhang, Jue Wang, Huan Li +6
Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effec…
Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI
Lingxi Cui, Huan Li, Ke Chen +2
Machine learning (ML) on tabular data is ubiquitous, yet obtaining abundant high-quality tabular data for model training remains a significant obstacle. Numerous works have focused…
FL-GUARD: A Holistic Framework for Run-Time Detection and Recovery of Negative Federated Learning
Hong Lin, Lidan Shou, Ke Chen +2
Federated learning (FL) is a promising approach for learning a model from data distributed on massive clients without exposing data privacy. It works effectively in the ideal feder…
LINDT: Tackling Negative Federated Learning with Local Adaptation
Hong Lin, Lidan Shou, Ke Chen +2
Federated Learning (FL) is a promising distributed learning paradigm, which allows a number of data owners (also called clients) to collaboratively learn a shared model without dis…