I am an Applied Scientist at VCV-Science group at Apple where I work on vision foundation models. Prior to that, I was a CS Ph.D. student and graduate researcher at Oregon State University supervised by Prof. Fuxin Li.
My research interests mainly include foundation models, generative models, 2D/3D computer vision, interpretability, long-tail problem, self-supervised learning.
My research interests mainly include foundation models, generative models, 2D/3D computer vision, interpretability, long-tail problem, self-supervised learning.
News [outdated]
- Mar 22: Our counterfactual visual explanation paper "Cycle-Consistent Counterfactuals by Latent Transformations" (C3LT), is accepted to the CPVR 2022! (acceptance rate 25.33%) [PDF] [Github]
- Oct 21: Our paper "From Heatmaps to Structural Explanations of Image Classifiers" is accpeted to the Applied AI Journals! [PDF]
- May 21: Our paper "Re-Understanding Finite-State Representations of Recurrent Policy Networks" is accpeted to the ICML 21! (acceptance rate 21.4%) [PDF]
- May 21: Our new paper on flexible training of deep networks using ADMM titled "Stochastic Block-ADMM for Training Deep Networks " is now available on arXiv. [PDF]
- Feb 21: Code for iGOS++ is released! This repo also includes faster version of I-GOS! [Github]
- Feb 21: Our paper "iGOS++: integrated gradient optimized saliency by bilateral perturbations" is accepted to the ACM-CHIL 21! iGOS++ shows significant imporvement over I-GOS, particularly in terms of insertion score! (acceptnace rate ~27%) [PDF]
- Jan 21: I joined Scale AI as a Machine Learning Research Engineer Intern starting January 2021.
- Nov 20: Our paper "Embedding Deep Networks into Visual Explanations" is accepted to the Artificial Intelligence Journal! [Journal]
- Jul 20: Full-length paper for "Understanding Finite-State Representations of Recurrent Policy Networks" is now available at arXiv! [PDF]
- Jul 20: Our paper "Understanding Finite-State Representations of Recurrent Policy Networks" is accpeted to the ICML 20 XXAI workshop!
- Jun 20: My M.Sc. dissertation "Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization" is now publicly available! [PDF]
- Apr 20: Demo for I-GOS is updated! It now supports user-input images, comparison against GradCam, and interactive deletion/insertion games! Go check it out! [Demo v2.0]
- Mar 20: I successfully passed my Ph.D. qualifying exam and defended my M.Sc. in Computer Science at Oregon State University! Yay! [Event]
- Feb 20: Medium post for I-GOS is now available! [Medium]
- Nov 19: Our paper "Visualizing Deep Networks by Optimizing with Integrated Gradients" is accepted to the AAAI 20. (acceptance rate 20.6%) [PDF]
- Aug 19: Code for I-GOS is now available! It is easy to use, go check it out! [Github]
- Jul 19: Early-version demo for I-GOS is no available! It does not yet support user-input images due to GPU constraints. Tune in for updtaes when more resources is available! [Demo]
- Jun 19: I-GOS is accepted to the CVPR 19 Explainable AI workshop. [PDF]