| May 31, 2025 | 📐 Introducing MMPerspective, a comprehensive benchmark for MLLMs on perspective understanding. |
| May 27, 2025 | 🌟 Started my internship as an Applied Scientist Intern at Amazon in Bellevue, WA. |
| May 03, 2025 | 🎉 Our Vid-LLM survey has been accepted by the IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)! 👉 IEEE Xplore | GitHub |
| Apr 09, 2025 | 📷 Caption Anything in Video (CAT-V) has been released 👉 arXiv | GitHub |
| Feb 26, 2025 | 🎉 Two papers have been accepted to CVPR 2025, including our VidComposition benchmark! |
| Feb 05, 2025 | I will join Amazon as an Applied Scientist Intern this summer. |
| Jan 13, 2025 | 🎨 Introducing our survey paper on GenAI for Cel-Animation 👉 arXiv | GitHub |
| Dec 09, 2024 | 🎉 Three papers on Video-LLMs have been accepted to AAAI 2025! |
| Nov 23, 2024 | We have released VidComposition, a benchmark to evaluate MLLMs’ understanding of video compositions. 👉 Project Page | Paper | Leaderboard |
| Oct 13, 2024 | 🚀 MMComposition has been publicly released. Read our Paper, check out the latest 🏆Leaderboard, and access the Code to evaluate your own models. |
| Aug 23, 2024 | Introducing CaRDiff, a framework for video saliency prediction using MLLM CoT reasoning and diffusion model. |
| Aug 05, 2024 | 🏅 We won the first place in AIM 2024 Challenge on Video Saliency Prediction @ ECCV Workshop! Thanks to Gen Zhan and Li Yang! |
| Jul 23, 2024 | 📢 We've recently updated our survey: "Video Understanding with Large Language Models: A Survey"! |
| Jul 15, 2024 | One paper about egocentric video understanding with LLM has been accepted to ACM MM 2024. |
| Jun 18, 2024 | Introducing Differentiated Beam Decoding (DBD), a novel decoding strategy for LVLM hallucination mitigation. |
| May 20, 2024 | 🌟 Started my internship at ByteDance in San Jose, CA, mentored by Yiting Liao & Gen Zhan. |
| Apr 18, 2024 | Introducing V2Xum-LLaMA model and Instruct-V2Xum dataset for cross-modal video summarization. |
| Mar 24, 2024 | Released AVicuna, an Audio-Visual LLM empowered by pseudo-untrimmed video annotations for audio-visual event localization. |
| Feb 09, 2024 | I will join ByteDance as a Research Intern this summer. |
| Dec 30, 2023 | 🔥🔥🔥 Released a survey for Video Understanding with LLMs (arXiv, GitHub). |
| Aug 28, 2023 | Officially joined in the Chenliang Xu’s Group at UR CS as a Ph.D. student🎓. |
| Jul 23, 2023 | One paper accepted to International Computer Music Conference (ICMC) 2023. |
| Jun 29, 2023 | Graduated from SUSTech, obtained my bachelor’s degree and the honor of Excellent Graduate for Exceptional Performance. |
| Jun 18, 2023 | Our team won the first place in LOVEU (Long-form Video Understanding) Challenge at CVPR’23 Workshop. |
| May 25, 2023 | Successfully defended my undergraduate thesis titled Language-Guided Video Cover Generation, which has been awarded the Excellent Undergraduate Thesis! |
| May 04, 2023 | The technical report for Caption Anything has been released! |
| Apr 12, 2023 | Our project Caption Anything has been released! Welcome to try our demo and star our GitHub repo! |
| Feb 27, 2023 | Thrilled to announce I’ll be starting my Ph.D. in Computer Science at the University of Rochester from Fall 2023, working with Prof. Chenliang Xu! |
| Sep 16, 2022 | One paper about multimodal Ad video editing has been accepted to Asian Conference on Computer Vision (ACCV) 2022. |
| Aug 16, 2022 | I left Tencent and joined SUSTech VIP Lab as an undergraduate student researcher. |
| Sep 24, 2021 | Started my part-time internship at Tencent in Shenzhen, with supervision from Dr. Wenhao Jiang and Qin Lin. I had to balance it with my university coursework. |