Dong Li

I am a junior researcher at Shanghai AI Lab., where I work on multimodal machine learning and large language model.

Email  /  CV  /  Google Scholar  /  Github

I'm interested in Multimodal Machine Learning (MML), large language models (LLMs), efficient Transformers and optimization. Much of my research is about MML and LLM . Representative papers are highlighted.

We explore a new task for audio-visual-language modeling called fine-grained audible video description (FAVD). It aims to provide detailed textual descriptions for the given audible videos, including the appearance and spatial locations of each object, the actions of moving objects, and the sounds in videos.

We propose to model sequences with a relative position encoded Toeplitz matrix and use a Toeplitz matrix-vector production trick to reduce the space-time complexity of the sequence modeling to log linear.

We propose a new framework to find optimal architectures for efficient Transformers with the neural architecture search (NAS) technique.

We propose a feature fixation module to reweight the feature importance of the query and key before computing linear attention.

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.