News
• 2 Nov 2024
The tutorial video record of Multimodal LLM at ACM MM 2024 are released at Youtube; all slides and materials are available at homepage.
• 25 Oct 2024
We will give a tutorial at ACM MM 2024 on Monday 28 Oct 9:00-12:30, on the hot topic of MLLMs: Architecture, Modality, Function, Instruction, Hallucination, Evaluation, Reasoning and Beyond. Please stay tuned to the program and welcome on-site or online attendance.
• 26 Sep 2024
Eight papers are accepted by NeurIPS 2024, all about Multimodal LLMs and Learnings. Congrats to all my co-authors!
• 20 Sep 2024
Three papers are accepted by EMNLP 2024 (Main/Findings), 1) Commonsense Reasoning, 2) Legal Text Generation, and 3) Survey on Conversational Understanding. Congrats to all my co-authors!
• 16 Sep 2024
Ranked as Top 2% Scientists Worldwide 2024 (Single Year) by Stanford University.
• 16 July 2024
Four papers are accepted by ACM MM 2024, 1) Multimodal Conversational ABSA, 2) Speech Event Extraction, 3) Mutimodal Coreference Resolution and 4) Visual Programs. Congrats to all my co-authors!
• 19 June 2024
Our tutorial video of Multimodal LLM at CVPR 2024 is released at Youtube; all slides and materials are available at homepage.
• 18 June 2024
We are excited to receive the World Artificial Intelligence Conference Youth Outstanding Paper Award by our paper, NExT-GPT.
• 22 May 2024
Our tutorial video of Multimodal LLM at LREC-COLING 2024 is released at Youtube; all slides and materials are available at homepage.
• 16 May 2024
Five papers are accepted by ACL 2024 (main or finding), 1) Grounded Multimodal UIE, 2) Symbolic CoT, 3) Structured Sentiment Analysis, 4) ProtT3: Protein-to-Text Generation and 5)Conversational Intent Discovery. Congrats to all my co-authors!
• 2 May 2024
Three papers are accepted by ICML 2024, 1) NExT-GPT, 2) Video-of-Thought and 3) Video-LLM Momentor. Congrats to all my co-authors!
• 25 April 2024
One paper about Video-Language Modeling is accepted by TPAMI!
• 16 April 2024
One paper about Few-shot Named Entity Recognition is accepted by TKDE!
• 15 April 2024
We are excited to announce the release of Vitron (Demo, Paper, Code), a universal pixel-level vision LLM designed for comprehensive understanding (perceiving and reasoning), generating, segmenting (grounding and tracking), editing (inpainting) of both static image and dynamic video content.
• 4 March 2024
We are holding the Grand Challenge of Visual Spatial Description (VSD) at ACM Multimedia 2023. Welcome participant!
• 27 Feb 2024
Two papers are accepted by CVPR 2024, 1) LL3DA, 2) Dysen-VDM. Congrats to all my co-authors!
• 20 Feb 2024
Our paper What Factors Influence LLMs’ Judgments? A Case Study on Question Answering is accepted by LREC-COLING 2024. Congrats to my co-authors!
• 15 Feb 2024
We are holding the special session at ACM ToMM on Deep Multimodal Generation and Retrieval, Call for submission.
• 13 Feb 2024
We will give a tutorial at CVPR 2024, on the hot topic of From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning and Beyond. Please stay tuned to the program and welcome on-site or online attendance.
• 1 Feb 2024
We will give a tutorial at LREC-COLING 2024, on the hot topic of From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and Beyond. Please stay tuned to the program and welcome on-site or online attendance.
• 23 Jan 2024
Our paper MMLSCU: A Dataset for Multi-modal Multi-domain Live Streaming Comment Understanding is accepted by TheWebConf (WWW) 2024. Congrats to my co-authors!
• 14 Dec 2023
Our paper In-Context Learning for Few-Shot Nested Named Entity Recognition is accepted by ICASSP 2024. Congrats to my co-authors!
• 9 Dec 2023
Three papers are accepted by AAAI 2024, 1) Commonsense Reasoning with Graph-of-Thought, 2) DiaASQ, 3) Spectral GNN. Congrats to my co-authors!
• 7 Dec 2023
Invited to give a talk at CIPS Youth Working Committee in A Star, Singapore, on the topic of From Multimodal LLM to AGI.
• 4 Dec 2023
SSNLP 2023 was held successfully, big thanks to invited speakers and our organizing committee.
• 8 Oct 2023
One paper is accepted by EMNLP 2023, Molca about Molecular LLM, welcome try the online demo here. Congrats to my co-authors!
• 5 Oct 2023
The 2023 Singapore Symposium on Natural Language Processing (SSNLP) will be held on Monday, December 4, at the Shaw Foundation Alumni House Auditorium, NUS. Please register!
• 1 Oct 2023
I am excited to announce joining Kunlun 2050 Research Lab as an associate research member.
• 30 Sep 2023
Two papers are accepted by NeurIPS 2023, 1) VPGTrans, 2) Abstract-to-Intricate Text-to-Image Synthesis, Congrats to my co-authors!
• 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
Four papers are accepted by ACM MM 2023, about Text-to-Image Generation, Multimodal Emotion Recognition, Video Semantic Role Labeling, and Video Moment Retrieval, Congrats to my co-authors!
• 4 Aug 2023
Our Universal Structured NLP (XNLP) demonstration system has been launched online, access it here, paper.
• 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
NSSDM 2023 was held successfully, thanks our keynote speakers; also special thanks to our co-organizers Wenjie, Yisong for the hard work! See the archive videos of the symposium at homepage.
• 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
Our newly proposed benchmark, DiaASQ: Conversational Aspect-based Sentiment Quadruple Analysis, is released on NLPCC 2023 shared task. Call for participation at DiaASQ Homepage.
• 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.