All News
05/25/2023: Releasing our third paper TOAST in the Top-Down Attention series of work. A flexible tuning method that surpass full fine-tuning for adapting LLMs and large vision models!
05/25/2023: Introducing Gorilla, which teaches LLMs for API calls. Your open-sourced, one-stop API marketplace. Join the discord community!
05/2022: Our work, VARS, a new visual attention formulation, accepted at ICML 2022.
03/2022: 3 papers on robust contrastive learning, unsupervised pretraining and OOD detection accepted at CVPR 2022.
07/2021: 2 papers on OOD and continual online object detection accepted at ICCV 2021.
05/2021: I started at Microsoft Research, Redmond.
11/2020: Selected as one of the rising stars in EECS 2020 by UC Berkeley.
08/2020: Co-orgnized the Women in Computer Vision (WiCV) workshop at ECCV 2020.
07/2020: Presented our paper on Frustratingly Simple Few-Shot Object Detection at ICML 2020. We find a simple fine-tuning approach can outperform all the previous meta learning appraoches for few-shot object detection.
07/2020: Co-organized the second Human in the Loop Learning (HILL) workshop at ICML 2020.
06/2020: Gave a keynote talk on Motion Understanding via Heterogenous Multitask Learning at the fifth BMTT MOT Challenge workshop at CVPR 2020.
06/2020: Presented our work on BDD100K, the largeset driving video dataset with a new benchmark of 10 heterogenous perception tasks, at CVPR 2020.
06/2020: Presented our work on ShapeProp, which utlizes an iterative message passsing method to propagate the saliency regions for semi-supervised instance segmentation, at CVPR 2020.
02/2020: Gave an invited talk at Max Planck Institute for Informatics, Saarbrcken, Germany on Towards Human-Level Recognition and Generalization via Dynamic Representations.