1 code implementation • 15 Nov 2023 • Jinghan Yang, Shuming Ma, Furu Wei
In the era of Large Language Models (LLMs), human-computer interaction has evolved towards natural language, offering unprecedented flexibility.
no code implementations • 22 May 2023 • Jinghan Yang, Linjie Xu, Lequan Yu
When facing an unsatisfactory prediction from a machine learning model, users can be interested in investigating the underlying reasons and exploring the potential for reversing the outcome.
no code implementations • 4 Feb 2023 • Jinghan Yang, Hunmin Kim, Wenbin Wan, Naira Hovakimyan, Yevgeniy Vorobeychik
Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control.
1 code implementation • 4 Feb 2023 • Jinghan Yang, Sarthak Jain, Byron C. Wallace
We consider the problem of identifying a minimal subset of training data $\mathcal{S}_t$ such that if the instances comprising $\mathcal{S}_t$ had been removed prior to training, the categorization of a given test point $x_t$ would have been different.
1 code implementation • 21 Oct 2021 • Mingyang Xie, Manav Kulshrestha, Shaojie Wang, Jinghan Yang, Ayan Chakrabarti, Ning Zhang, Yevgeniy Vorobeychik
Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results.
1 code implementation • 17 Oct 2020 • Jinghan Yang, Adith Boloor, Ayan Chakrabarti, Xuan Zhang, Yevgeniy Vorobeychik
We propose a scalable approach for finding adversarial modifications of a simulated autonomous driving environment using a differentiable approximation for the mapping from environmental modifications (rectangles on the road) to the corresponding video inputs to the controller neural network.
1 code implementation • 4 Dec 2019 • Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik
We study this problem formally as a combinatorial optimization problem in the context of geolocation prediction facilitated by deep learning.