孔令鹏博士是大语言模型与多智能体系统领域的国际知名学者，在NeurIPS、ICML、ICLR、ACL等顶级会议发表论文120+篇，其中顶会论文80+篇，获得ACL 2024 Outstanding Paper Award等重要奖项。h-index达52，总引用数超10,000次，多篇论文单篇引用超过400次，研究成果在学术界产生了广泛影响。孔博士在大模型推理、扩散模型、长序列处理、多智能体协作等前沿方向有深厚积累和原创性贡献:其开发的L-Eval基准和AgentBoard评估框架已成为领域标准工具。除此之外，他还担任NeurIPS、ICML、ICLR等顶级会议高级领域主席/领域主席，以及TMLR和ACL Rolling Review编辑，在学术界有广泛认可度。

工作经历:

 2017.09–2019.06   Google DeepMind     研究科学家

 2019.06–2020.08   Google DeepMind     高级研究科学家

 2020.09–至今        香港大学计算机科学系  助理教授

大语言模型的推理与规划能力研究

多智能体系统与社交智能（Social Agents）

超长序列神经架构与高效注意力机制

扩散模型在语言生成和推理中的应用

大模型在游戏理论场景中的博弈与协作

1. Shansan Gong, Mukai Li, Jiangtao Feng, Zhiyong Wu, Lingpeng Kong. DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models, arXiv 2022, citation = 562

2. Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong，Random Feature Attention, arXiv 2021, citation = 481

3. Zhen Qin, Weixuan Sun, Hui Deng, Dongxu Li, Yunshen Wei, Baohong Lv, Junjie Yan, Lingpeng Kong, Yiran Zhong. cosFormer: Rethinking Softmax In Attention, ICLR 2022, citation = 366

4. Chenxin An, Shansan Gong, Ming Zhong, Xingjian Zhao, Mukai Li, Jun Zhang, Lingpeng Kong, XipengQiu.L-Eval: Instituting Standardized Evaluation for Long Context Language Models, ACL 2024 (Outstanding Paper Award), citation = 164

5. Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujun Yang, Yaohui Jin, Zhengzhong Lan,  Lingpeng Kong, Junxian He . AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents, NeurIPS 2024 (Oral), citation = 114

6. Jiacheng Ye, Shansan Gong, Liheng Chen, Lin Zheng, Jiahui Gao, Han Shi, Chuan Wu, Xin Jiang, Zhenguo Li, Wei Bi, Lingpeng Kong ，Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models, NeurIPS 2024, citation = 46

7. AdhigunaKuncoro*, Lingpeng Kong*, Daniel Fried, Dani Yogatama, Laura Rimell, Chris Dyer, Phil Blunsom, Syntactic Structure Distillation Pretraining For Bidirectional Encoders, Transactions of the Association for Computational Linguistics , September 2020. (*equal contribution) (TACL 2020)

8. Lingpeng Kong, Cyprien de Masson d'Autume, Wang Ling, Lei Yu, Zihang Dai, Dani Yogatama, A Mutual Information Maximization Perspective of Language Representation Learning, In International Conference on Learning Representations, Ethiopia, April 2020. (ICLR 2020)

9. Cyprien de Masson d'Autume, Sebastian Ruder, Lingpeng Kong, Dani Yogatama, Episodic Memory in Lifelong Language Learning, In Advances in Neural Information Processing Systems, Vancouver, Canada, December 2019. (NeurIPS 2019)

10. Lingpeng Kong, Gabor Melis, Wang Ling, Lei Yu, Dani Yogatama, Variational Smoothing in Recurrent Neural Network Language Models, In International Conference on Learning Representations, New Orleans, Louisiana, May 2019. (ICLR 2019)

项目经历

1. 大语言模型驱动的多智能体协作框架研究，项目负责人

2. 长上下文语言模型标准化评估基准（L-Eval）构建，主要负责人

3. 扩散推理模型（Diffusion Reasoning Models）理论与应用，核心研究者

4. 蛋白质表示学习与序列增强研究，合作研究者