• 8 Oct 2023
• 5 Oct 2023
• 1 Oct 2023
I am excited to announce joining Kunlun 2050 Research Lab as an associate research member.
• 30 Sep 2023
• 24 Sep 2023
Invited to give a talk at MLNLP 2023, on the topic of Scene Graph-driven Structured Vision-Language Learning.
• 12 Sep 2023
We are excited to announce the release of NExT-GPT (Demo, Code, Paper), the first end-to-end MM-LLM that perceives input and generates output in arbitrary combinations (any-to-any) of text, image, video, and audio and beyond.
• 25 Aug 2023
Invited to give a talk at WING lab @ NUS, on the topic of LLM-Empowered Text-to-Vision Diffusion Models
• 23 Aug 2023
Invited to give a talk at Institute of Computing Technology, Chinese Academy of Sciences, on the topic of Scene Graph-driven Structured Vision-Language Learning
• 10 Aug 2023
• 4 Aug 2023
• 2 Aug 2023
I will serve as Senior PC of Speech & Natural Language Processing track at AAAI 2024.
• 25 July 2023
We are holding the special session at Electronics on Advances in Large Language Model Empowered Machine Learning: Design and Application, Call for papers.
• 22 July 2023
Our paper DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs has been accepted by NLPCC 2023. Congrats to my collaborators!
• 19 June 2023
I am honored to be awarded as the World AI Conference (WAIC’23) Rising Star (2023世界人工智能大会云帆奖明日之星).
• 15 June 2023
I will serve as Session Chair of Summarization Track (11:00-12:30, 11, July) at ACL 2023. Meet you there.
• 18 May 2023
I will serve as Senior Area Chair of EMNLP 2023.
• 8 May 2023
We are releasing a novel work about LLM, VPGTrans: Transfer Visual Prompt Generator across LLMs, where we release the VL-Vicuna, a multimodal version Vicuna. Twitter post, 机器之心, 新智元. Try it out at our demo page.
• 3 May 2023
Seven papers are accepted by ACL 2023, Congrats to my co-authors! Theme-A: Sentiment Analysis (Dialogue-level ABSA, and Chain-of-Though Reasoning for Implicit Sentiment), Theme-B: Information Extraction (Multimodal Relation Extraction, Cross-lingual Relation Extraction), Theme-C: Structured Multimodal learning (3D Visual Spatial Description, Cross-lingual Captioning, Inference-time Image-free Unsupervised Multimodal Machine Translation). See you in Toronto, July.
• 29 April 2023
We are holding the Deep Multimodal Learning for Information Retrieval (MMIR 2023) workshop at ACM Multimedia 2023, Call for papers.
• 30 March 2023
I will serve as Workshop Co-chair of EMNLP 2023.
• 5 March 2023
• 3 March 2023
Our student volunteers did jobs in serving the WSDM 2023 and made it big success, thank you all!
• 20 April 2023
Prof. Min-yen Kan, Tat-Seng Chua and I will host the 2023 NUS Symposium on Search and Data Mining (NSSDM 2023) on Thursday, 2 Mar in NUS at Innovation 4.0. We will invite prestigious scholars to give insightful and inspiring keynotes. Welcome participant, register at NSSDM homepage.
• 15 February 2023
• 8 December 2022
I am fortunate to have my Ph.D thesis On the Syntax-oriented Modeling and Optimization of Natural Language receive the award of Excellent Doctoral Thesis of Chinese Information Processing Society of China (CIPSC).
• 6 October 2022
Two papers are accepted by EMNLP 2022, on Entity-centered Cross-document Relation Extraction, and Conversation Disentanglement with Bi-Level Contrastive Learning, Congrats to my co-authors!
• 17 August 2022
Two papers are accepted by COLING 2022, on OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction, and Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction, Congrats to Hu Cao and Shunjie!
• 15 June 2022
I will serve as Senior Program Committee of WSDM 2023.
• 2 June 2022
I will serve as Area Chair of EMNLP 2022.
• 30 May 2022
I will serve as Student Volunteer Chair of WSDM 2023. Contact me if you are interested in offering service.