bighuang624 / algorithms-notes Goto Github PK

Hi! I am Siteng Huang (黄思腾 in Chinese). I received my Ph.D. degree from Zhejiang University (Hangzhou, China) in June 2024, affiliated with a joint-supervision program with Westlake University (Hangzhou, China) at Machine Intelligence Laboratory (MiLAB) and advised by Prof. Donglin Wang. Before that, I received my B.Eng. Degree from School of Computer Science, Wuhan University (Wuhan, China) in June 2019.

🔍 Currently, My research has centered on multi-modal large models, especially vision-language models (VLMs), including

• Generation/AIGC: text-to-image/video (T2I/V) generation^ADI,SimM, customized & controllable generation^ADI,SimM, test-time diffusion intervention^{SimM,VGDiffZero}, multi-modal large language models (MLLMs)^{Cobra, PiTe}
• Understanding: text-video retrieval (TVR)^VoP, compositional zero-shot learning (CZSL)^Troika, few-shot learning (FSL)^AGAM,HTS, visual grounding^{VGDiffZero,DARA}
• Transfer: parameter-efficient fine-tuning (PEFT/PETL)^{VoP,DARA,Sparse-Tuning}, meta-learning^MRN, domain adaptation^PDA
• Embodied AI: vision-language-action models (VLAs)^QUAR-VLA, foundation models for robotics

I am always looking for related collaborations, and most of them have produced top-level publications. Feel free to drop me an email if you are interested!

💬 News:

• [July 1, 2024] Two papers (PiTe and QUAR-VLA) got accepted for ECCV 2024.
• [June 4, 2024] I successfully defended my dissertation. So many thanks to my Ph.D. committee (Prof. Xiaogang Jin, Prof. Mai Xu, Prof. Changxin Gao, Prof. Fajie Yuan, Prof. Peidong Liu, Prof. Xiaofei Li) and my advisor!
• [May 5, 2024] Our Cobra was selected for VALSE 2024 Annual Progress Representation. Thanks to all the committee for the approval!
• [March 29, 2024] Troika got accepted as VALSE 2024 Poster!
• [March 21, 2024] Cobra, an efficient multi-modal large language model, was released. Project page has been available. The paper has been featured by Hugging Face Daily Papers! Demo has been available!
• [March 13, 2024] One paper about parameter-efficient tuning for visual grounding got accepted for ICME 2024 (Oral).
• [February 27, 2024] Awarded as Zhejiang University 2024 Outstanding Graduates!
• [February 27, 2024] Three papers (ADI, Troika, SimM) as first/co-first author got accepted for CVPR 2024. Congratulations to all collaborators!
• [December 13, 2023] The paper of VGDiffZero on diffusion model-based zero-shot visual grounding got accepted for ICASSP 2024. Congratulations to all collaborators!
• [December 9, 2023] One paper on VLM-based unsupervised domain adaptation got accepted for AAAI 2024.
• [July 24, 2023] 2023 Scholar Metrics was released by Google Scholar. Our paper "DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting" ranked 8th of the CIKM 2019 conference according to the citations, and 26th within five years.
• [April 2, 2023] The paper of RL-CZSL about reference-limited compositional learning got accepted for ICMR 2023. Congratulations to all collaborators!
• [February 28, 2023] The paper of VoP about parameter-efficient text-video retrieval got accepted for CVPR 2023. Congratulations to all collaborators!

📫 Contact me by:

• Email: siteng.huang[at]gmail.com (Please change [at] to @)