Dr. Zhiwei Liu is a full-time research scientist at Salesforce AI Research. He received his Ph.D. degree from University of Illinois at Chicago, where he was advised by Prof. Philip S. Yu in the Big Data and Social Computing Lab.
Dr. Liu's research interests lie in large models, recommender systems and data mining. Specifically, those research works on graph neural networks, recommender systems, natural language understanding, etc.
Email: zhiweiliu [at] salesforce [dot] com [OR] jim96liu [at] gmail [dot] com
Latest News
[Mar. 2024] Our paper Instruction-based Hypergraph Pretraining is accepted to SIGIR 2024 Full paper track! (acceptance rate: 159/791 ~20.1%)
[Mar. 2024] Our paper BOLAA is accepted to LLMAgent@ICLR workshop!
[Mar. 2024] We released a new LLM for agent, Salesforce/xLAM-v0.1-r. Try it with AgentLite benchmark!
[Feb. 2024] Our paper AgentLite is released! Use it to build your LLM agent it at https://github.com/SalesforceAIResearch/AgentLite.
[Oct. 2023] Best short paper honorable mention in CIKM for graph alignment.
[Oct. 2023] Two papers accepted to WSDM 2024.
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Contrastive self-supervised sequential recommendation with robust augmentation
Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer
Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection