Xin Su, Ph.D.
Lead AI Researcher, Thoughtworks
Hi, I’m Xin Su. I’m a Lead AI Researcher at Thoughtworks, focusing on multimodal AI and autonomous agents.
My research centers on making AI systems more powerful and reliable. I develop synthetic data generation and post-training methods to improve multimodal models and agents across diverse reasoning tasks, build autonomous agents that can interact with complex environments, and create knowledge graph systems and novel retrieval-reasoning frameworks for RAG applications.
Previously, I worked on building AI systems that extract structured information from text and apply it to complex reasoning tasks, such as temporal reasoning. I also applied AI to healthcare, developing clinical NLP models for medical applications.
I received my Ph.D. in Information from the University of Arizona in 2024 at the Computational Language Understanding Lab, advised by Dr. Steven Bethard, and my M.S. in Computer Science from Loyola University Chicago in 2020, advised by Dr. Dmitriy Dligach.
News
| Jan 30, 2026 | Our paper “Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency” has been accepted to ICLR 2026! 🎉 |
|---|---|
| Nov 24, 2025 | Joined Thoughtworks as a Lead AI Researcher. Excited to build impactful AI systems with an amazing team! 🚀✨ |
| Sep 18, 2025 | Our paper “A Semantic Parsing Framework for End-to-End Time Normalization” has been accepted to NeurIPS 2025! |
| Aug 20, 2025 | Our survey paper “Transformer-Based Temporal Information Extraction and Application: A Review” has been accepted to EMNLP 2025! |
| Jan 30, 2025 | Our paper “SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs” has been accepted as a Spotlight Oral (top 1%) at ICML 2025! |
| Jan 06, 2025 | Joined Intel Labs Multimodal Cognitive AI Team full-time as an AI Research Scientist! 🎉🎉🎉 Excited to continue my research on agentic AI and multimodal models 🚀 |
| Dec 20, 2024 | Successfully defended my Ph.D. dissertation at the University of Arizona! |
| Mar 15, 2024 | Our paper “Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning” has been accepted to NAACL 2024! |
| Oct 06, 2023 | Our paper “Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering” has been accepted to EMNLP 2023 Findings! |
| May 01, 2023 | Returning to Intel Labs for my internship! |
| May 15, 2022 | Starting my internship at Intel Labs as an AI Research Intern! |
| Feb 23, 2022 | Our paper “A Comparison of Strategies for Source-Free Domain Adaptation” has been accepted to ACL 2022! |
| May 15, 2020 | Received Edsger W. Dijkstra High Achievement Award in Computer Science from Loyola University Chicago! |