Zhi Wang

High-density Multi-tenant Bare-metal Cloud

2020

Virtualization is the cornerstone of the infrastructure-as-a-service (IaaS) cloud, where VMs from multiple tenants share a single physical server. This increases the utilization of data-center servers, allowing cloud providers to provide cost-efficient services. However, the …

Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

2021 · arXiv (Cornell University)

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with …

Optimization of dedicated domain text classification based on data augmentation using BERT generation pre-trained model

2023

Due to the excessive cost of data collection as well as annotation in dedicated domains, artificial intelligence model training is difficult to achieve optimality with insufficient data. To optimize this issue, a text generation data …

Enhancing Unsupervised Semantic Segmentation Through Context-Aware Clustering

2024 · IEEE Transactions on Multimedia

Despite the great progress of semantic segmentation with supervised learning, annotating large amounts of pixel-wise labels is, however, very expensive and time-consuming. To this end, Unsupervised Semantic Segmentation(USS) has been proposed to learn semantic segmentation, …

Staleness-Centric Optimizations for Parallel Diffusion MoE Inference

2024 · arXiv (Cornell University)

Mixture-of-Experts-based (MoE-based) diffusion models demonstrate remarkable scalability in high-fidelity image generation, yet their reliance on expert parallelism introduces critical communication bottlenecks. State-of-the-art methods alleviate such overhead in parallel diffusion inference through computation-communication overlapping, termed displaced …

BASSET: Enhancing Binary Code Clone Searching through Multi-Level Hybrid Semantic Indexing

2025

Binary code search is critical for applications such as plagiarism detection and security analysis, but it is challenging due to compiler-induced transformations at different optimization levels. Existing function similarity methods often fail in large-scale search …

Entire Space Multi-Task Model

2018

Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several …