Shihao Liang

Bio

Hi! I am a graduate student at The University of Hong Kong. Currently, I am doing an intership in Seed-VLM department in ByteDance, working in VLM based agent. Before that, I worked as a research assistant in the THUNLP Lab, Tsinghua University, advised by Zhiyuan Liu. My academic journey began with a B.E. degree in Computer Science from Tianjin University, advised by Ruifang He.

I'm interested in Large Language Models(LLMs), NLP, grounding with LLMs and AI Agent. Moreover, I am receptive to any and all endeavors that could propel Artificial General Intelligence towards progress!

Publications

Most recent publications on Google Scholar.
^‡ indicates equal contribution.

• Selected
• All

Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution

Cheng Qian^‡, Shihao Liang^‡, Yujia Qin, Yining Ye, et al.

arXiv

Paper Code

ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs

Yujia Qin^‡, Shihao Liang^‡, Yining Ye, Kunlun Zhu, Lan Yan, et al.

ICLR 2023 Spotlight

Paper Code Data

Exploring Format Consistency for Instruction Tuning

Shihao Liang^‡, Kunlun Zhu^‡, Runchu Tian^‡, Yujia Qin, Huadong Wang, Xin Cong, Zhiyuan Liu, Xiaojiang Liu, Maosong Sun.

TMLR 2023

Paper

Tool Learning with Foundation Models

Yujia Qin^‡, Shengding Hu^‡, Yankai Lin^‡, et al.

arXiv

Paper Code

WEBCPM: Interactive Web Search for Chinese Long-form Question Answering

Yujia Qin, Zihan Cai, Dian jin, Lan Yan, Shihao Liang, Kunlun Zhu, et al.

ACL 2023

Paper Code

Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution

Cheng Qian^‡, Shihao Liang^‡, Yujia Qin, Yining Ye, et al.

arXiv

Paper Code

ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs

Yujia Qin^‡, Shihao Liang^‡, Yining Ye, Kunlun Zhu, Lan Yan, et al.

ICLR 2023 Spotlight

Paper Code Data

Exploring Format Consistency for Instruction Tuning

Shihao Liang^‡, Kunlun Zhu^‡, Runchu Tian^‡, Yujia Qin, Huadong Wang, Xin Cong, Zhiyuan Liu, Xiaojiang Liu, Maosong Sun.

TMLR 2023

Paper

Tool Learning with Foundation Models

Yujia Qin^‡, Shengding Hu^‡, Yankai Lin^‡, et al.

arXiv

Paper Code

WEBCPM: Interactive Web Search for Chinese Long-form Question Answering

Yujia Qin, Zihan Cai, Dian jin, Lan Yan, Shihao Liang, Kunlun Zhu, et al.

ACL 2023

Paper Code

Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts

Bohua Peng, Shihao Liang, Mobarakol Islam

arXiv

Paper

Talks & Projects

• Selected
• All

XAgent
An Autonomous LLM Agent for Complex Task Solving.

ToolBench
An open platform for training, serving, and evaluating large language model for tool learning.

BMTools
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins.

XAgent
An Autonomous LLM Agent for Complex Task Solving.

ToolBench
An open platform for training, serving, and evaluating large language model for tool learning.

BMTools
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins.

Vitæ

Full Resume in PDF.

• The University of Hong Kong Sep 2023 - Present

  MSc Student
  Department of Computer Science
• ByteDance August 2024 - Present

  Research Intern
  Seed-VLM
• Tsinghua University July 2022 - July 2023

  Research Assistant
  THUNLP Lab
• Baidu Oct 2021 - Apr 2022

  Research and Development Intern
  DQA Group, NLP Department
• Tianjin University Sep 2018 - June 2022

  B.Eng. Student
  Intelligence and Computing Department