Scholar
Zilong (Ryan) Wang
Google Scholar ID: S_wQccsAAAAJ
UC San Diego
Citations & Impact
Citations
1,097
H-index
14
i10-index
16
Publications
20
Co-authors
24
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- "Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting" accepted by ICLR 2025, achieving state-of-the-art performance in accuracy and efficiency for RAG.
- "OFFICEBENCH: Benchmarking Language Agents across Multiple Applications for Office Automation" new paper alert!
- "Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step" accepted by ACL 2024 Findings!
- "Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding" accepted by ICLR 2024!
- "A Study on Robustness and Reliability of Large Language Model Code Generation" received by AAAI 2024!
Research Experience
- Conducted research at Amazon Foundation Model, Google Cloud AI, Google DeepMind, Google Research, Adobe Research, and Microsoft Research Asia.
Education
- Ph.D. in Computer Science and Engineering at UC San Diego, advised by Prof. Jingbo Shang; B.S. in Computer Science from Peking University, advised by Prof. Xiaojun Wan.
Background
- Research interests span several areas of natural language processing, including reasoning, information extraction, multimodal learning, and language modeling. Focuses on LLM post-training, aiming to align LLMs with complex reasoning and planning for knowledge-intensive queries, autonomous agents, and mathematical problem-solving. Earlier research focused on visually-rich document understanding.
