no code implementations • 13 Aug 2024 • Sruthi Sudhakar, Ruoshi Liu, Basile Van Hoorick, Carl Vondrick, Richard Zemel
Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action.
no code implementations • 24 Jun 2024 • Junbang Liang, Ruoshi Liu, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, Carl Vondrick
A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments.
no code implementations • 7 Jun 2023 • Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising.
no code implementations • 8 Feb 2023 • Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar, Judy Hoffman
We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix.
no code implementations • ICCV 2023 • Sruthi Sudhakar, Jon Hanzelka, Josh Bobillot, Tanmay Randhavane, Neel Joshi, Vibhav Vineet
An emerging alternative is to use synthetic data, but if the synthetic data is not similar enough to the real data, the performance is typically below that of training with real data.
1 code implementation • 29 Oct 2021 • Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations.