Scholar
Tianbao Xie
Google Scholar ID: 8sdGK_0AAAAJ
University of Hong Kong
Citations & Impact
Citations
4,170
H-index
18
i10-index
21
Publications
20
Co-authors
26
list available
Publications
Resume (English only)
Academic Achievements
- Qwen3-Coder: Agentic Coding in the World (NeurIPS 2025 under submission, July 2025)
- Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis (NeurIPS 2024 D&B Track, April 2024)
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (NeurIPS 2024 D&B Track, April 2024)
- OpenAgents: An Open Platform for Language Agents in the Wild (COLM 2024, October 2023)
- Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning (ICLR 2024 Spotlight, September 2023)
- Binding Language Models in Symbolic Languages (ICLR 2023 Spotlight, October 2022)
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (EMNLP 2022 Oral, January 2022)
- In-Context Learning for Few-Shot Dialogue State Tracking (EMNLP 2022 Findings, March 2022)
- NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation (arXiv, December 2021)
Background
- Third-year Ph.D. student at The University of Hong Kong
- Primary research interests in Natural Language Processing (NLP) and Artificial Intelligence (AI)
- Passionate about building applications to liberate human employees from labor-intensive tasks
- Currently focuses on agent-centric approaches to manipulate large language models for NLP and Robotics tasks
- Key projects include UnifiedSKG, Binder, Text2reward, OpenAgents, OSWorld, and OSWorld-G
