no code implementations • 16 Mar 2024 • Minkyu Choi, Harsh Goel, Mohammad Omama, Yunhao Yang, Sahil Shah, Sandeep Chinchali
The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks.
no code implementations • 27 Oct 2023 • Yunhao Yang, Neel P. Bhatt, Tyler Ingebrand, William Ward, Steven Carr, Zhangyang Wang, Ufuk Topcu
Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks.
no code implementations • 18 Sep 2023 • Yunhao Yang, Jean-Raphaël Gaglione, Sandeep Chinchali, Ufuk Topcu
The increasing abundance of video data enables users to search for events of interest, e. g., emergency incidents.
no code implementations • 5 Sep 2023 • Yunhao Yang, Anshul Tomar
The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines.
no code implementations • 10 Aug 2023 • Yunhao Yang, Cyrus Neary, Ufuk Topcu
We develop an algorithm that utilizes the knowledge from pretrained models to construct and verify controllers for sequential decision-making tasks, and to ground these controllers to task environments through visual observations.
no code implementations • 4 Dec 2022 • Yunhao Yang, Jean-Raphaël Gaglione, Cyrus Neary, Ufuk Topcu
However, the textual outputs from GLMs cannot be formally verified or used for sequential decision-making.
no code implementations • 25 May 2022 • Yunhao Yang, Parham Gohari, Ufuk Topcu
We study the privacy risks that are associated with training a neural network's weights with self-supervised learning algorithms.
1 code implementation • 15 Nov 2021 • Chandrajit Bajaj, Yi Wang, Yunhao Yang
Our \textit{Recursive Self Enhancement Reinforcement Learning}(RSE-RL) model views the identification and correction of artifacts as a recursive self-learning and self-improvement exercise and consists of two major sub-modules: (i) The latent feature sub-space clustering/grouping obtained through variational auto-encoders enabling rapid identification of the correspondence and discrepancy between noisy and clean image patches.
no code implementations • 6 Oct 2021 • Yunhao Yang, Parham Gohari, Ufuk Topcu
Additionally, we study the effectiveness of two prominent mitigation methods for preempting MIAs, namely weight regularization and differential privacy.
no code implementations • 25 Sep 2021 • Yunhao Yang, Zhaokun Xue, Andrew Whinston
As for the main contribution, we design a self-enhancing mechanism that uses a reinforcement learning algorithm to optimize the clustering algorithm without additional training data.
1 code implementation • 18 May 2021 • Yunhao Yang, Zhaokun Xue
A latent space transformation is applied for enhancing the quality of the representations.
1 code implementation • 1 Apr 2021 • Yunhao Yang, Yi Wang, Chandrajit Bajaj
Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks.
no code implementations • 7 Nov 2020 • Yunhao Yang, Andrew Whinston
Supervised learning is based on the assumption that the ground truth in the training data is accurate.
no code implementations • 17 Aug 2020 • Yunhao Yang, Andrew Whinston
This paper gives a detailed review of reinforcement learning (RL) in combinatorial optimization, introduces the history of combinatorial optimization starting in the 1950s, and compares it with the RL algorithms of recent years.