Qin Zhang

Dynamic Uncertain Causality Graph for Knowledge Representation and Probabilistic Reasoning: Directed Cyclic Graph and Joint Probability Distribution

2015 · IEEE Transactions on Neural Networks and Learning Systems

Probabilistic graphical models (PGMs) such as Bayesian network (BN) have been widely applied in uncertain causality representation and probabilistic reasoning. Dynamic uncertain causality graph (DUCG) is a newly presented model of PGMs, which can be …

Query expansion for exploratory search with subtopic discovery in Community Question Answering

2016

Exploratory search is cumbersome with today's search engines, where a user aims to better understand complex concepts. Query expansions techniques have been widely used in exploratory search. However, query expansions often recommend queries that differ …

The Optimal Combination Mode of Three-digit Cryptography Based on Letters and Numbers

2019

In order to better protect the file information from being leaked, the best combination mode with one-letter and two-digit passwords was discussed here. We mainly talked over the possible positions of the letters: firstly, according …

Meta Proximal Policy Optimization for Cooperative Multi-Agent Continuous Control

2022 · 2022 International Joint Conference on Neural Networks (IJCNN)

In this paper we propose Multi-Agent Proxy Proximal Policy Optimization (MA3PO), a novel multi-agent deep reinforcement learning algorithm that tackles the challenge of cooperative continuous multi-agent control. Our method is driven by the observation that …

Skadi: Building a Distributed Runtime for Data Systems in Disaggregated Data Centers

2023

Data-intensive systems are the backbone of today's computing and are responsible for shaping data centers. Over the years, cloud providers have relied on three principles to maintain cost-effective data systems: use disaggregation to decouple scaling, …

DeepServe: Serverless Large Language Model Serving at Scale

2025 · arXiv (Cornell University)

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving efficiency, …