Binyuan Hui

Scholar / Github / Twitter
I am currently a researcher at Alibaba Qwen Team. In addition, I am the initiator of OpenDevin, dedicated to being a truly Open Code Agent. My main research interests include:

  • 🧙🏻‍♂️ Large Language Models: Foundation Models [Qwen][Qwen-Coder], reasoning & CoT [Dater], in-context learning [Deep-thinking].
  • 👨🏻‍💻 Executable Language: Interaction with structure data (table / databases) by programming, including text-to-SQL [R²SQL][S²SQL][SUN][STAR][Graphix-T5][BIRD] and code generation [OctoPack][Lemur].
  • 🧠 World Agent: The ultimate intelligent, with omni-modal perception and embodied exploration. [SPRING]
  • 🦾 Dialog Systems: chatGPT is all your need.
I am currently hiring self-motivated researcher & interns in Beijing / Hangzhou / Shanghai. Please feel free to contact me with the subject line "Interested in Qwen Team + Your Name" with your resume.
📮 binyuan.hby [at] alibaba-inc.com

🔥 News

[2024.05] 3 paper got accepted by ACL 2024.

[2024.01] 2 paper got accepted by ICLR 2024 as Spotlight !

[2023.09] 🐦 BIRD-bench got accepted by NeurIPS 2023 as Spotlight !

[2023.08] SIGDIAL Workshop Best Paper Award !

[2023.07] I'm thrilled to announce that I've joined BigCode.

[2023.05] 3 paper got accepted by ACL 2023.

[2023.04] We released , a large-scale language model developed by Alibaba Group.

[2023.04] 1 paper got accepted by SIGIR 2023.

[2022.11] 2 paper got accepted by AAAI 2023.

[2022.11] 🏆 Achieved the 1st rank on The Third Situated Interactive MultiModal Conversations Challenge !

[2022.10] 1 paper got accepted by EMNLP 2022.

[2022.09] Awarded WAIC YunFan Award Rising Stars !

[2022.05] 1 paper got accepted by KDD 2022.

📝 Selected Publications (* = equal contribution | # = I mentored)

Qwen2.5-Coder Technical Report
Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, et al.
Report | PDF | Repo

Qwen2 Technical Report
An Yang, Baosong Yang, Binyuan Hui , Bo Zheng, Bowen Yu, Chang Zhou, et al.
Report | PDF | Repo

Qwen Technical Report
Qwen Team , Alibaba Group
Report | PDF | Repo

OctoPack: Instruction Tuning Code Large Language Models
Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, Shayne Longpre
ICLR 2024 (⭐️Spotlight) | PDF | Code

Lemur: Harmonizing Natural Language and Code for Language Agents
Yiheng Xu*, Hongjin Su*, Chen Xing*, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, Zhoujun Cheng, Siheng Zhao, Lingpeng Kong, Bailin Wang, Caiming Xiong, Tao Yu
ICLR 2024 (⭐️Spotlight) | PDF | Code | Homepage | Model | Blog

Iterative Forward Tuning Boosts In-context Learning in Language Models
Jiaxi Yang*, Binyuan Hui*#, Min Yang, Binhua Li, Fei Huang, Yongbin Li
ACL 2024 | PDF | Demo

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
Jingyang Li*, Binyuan Hui*#, Ge Qu*, Binhua Li, Jiaxi Yang, Bowen Li, Bailin Wang, et al.
NeurIPS 2023 (⭐️Spotlight) | PDF | Code | LeaderBoard

PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Yunshui Li*, Binyuan Hui*#, Zhichao Yin, Min Yang, Fei Huang, Yongbin Li
ACL 2023 | PDF | Code

Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark
Yuxing Long*, Binyuan Hui#, Caixia Yuan, Fei Huang, Yongbin Li, Xiaojie Wang
ACL 2023 | PDF | Code

Large Language Models are Versatile Decomposers for Table-based Reasoning
Yunhu Ye*, Binyuan Hui*#, Min Yang, Binhua Li, Fei Huang, Yongbin Li
Dater surpasses the human performance on Tabfact for the first time !
SIGIR 2023 | PDF | Code

SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph
Yuxing Long, Binyuan Hui#, Fulong Ye, Yanyang Li, Zhuoxin Han, Caixia Yuan, Yongbin Li, Xiaojie Wang
AAAI 2023 (Oral) | PDF | Code | Blog (Chinese)

Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
Jinyang Li, Binyuan Hui#, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Luo Si, Yongbin Li
AAAI 2023 (Oral) | PDF | Code

STAR: SQL Guided Pre-training for Context-dependent Text-to-SQL Parsing
Zefeng Cai*, Xiangyu Li*, Binyuan Hui#, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li
New SOTA performance on SParC and CoSQL benchmark.
EMNLP 2022 | PDF | Code | Blog (Chinese) | ModelScope | Cite

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers
Bowen Qin*, Lihan Wang*, Binyuan Hui*#, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li
Best paper recommonded, reviewer's score: 5 / 5 / 4
COLING 2022 | PDF | Code | Cite

Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
Lihan Wang*, Bowen Qin*,Binyuan Hui*#, Bowen Li, Min Yang, Bailin Wang, Binhua Li, Fei Huang, Luo Si, Yongbin Li
KDD 2022 | PDF | Code | Cite

S²SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers
Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Bowen Li, Jian Sun, Yongbin Li
ACL 2022 Findings | PDF | Code | Cite

R²SQL: Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing
Binyuan Hui, Ruiying Geng, Qiyu Ren, Binhua Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Pengfei Zhu, Xiaodan Zhu
AAAI 2021 | PDF | Code | Blog (Chinese) | Cite

🖊️ Professional Activities

Area Chair: ACL-24, EMNLP-24.
Program Committee / Reviewer: AAAI-21, EMNLP-21, AAAI-22, ACL-22, EMNLP-23, NAACL-24.


Updated on May, 2024.