1 code implementation • 21 Mar 2024 • Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor
This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks.
1 code implementation • 21 Nov 2023 • Bowen Jiang, Zhijun Zhuang, Camillo Jose Taylor
This work presents an enhanced approach to generating scene graphs by incorporating a relationship hierarchy and commonsense knowledge.
no code implementations • 29 Sep 2023 • Carl Qi, Yilin Wu, Lifan Yu, Haoyue Liu, Bowen Jiang, Xingyu Lin, David Held
We propose to learn a generative model of the tool-use trajectories as a sequence of tool point clouds, which generalizes to different tool shapes.
no code implementations • 11 Sep 2023 • Mengti Sun, Bowen Jiang, Bibit Bianchini, Camillo Jose Taylor, Michael Posa
This work presents an instance-agnostic learning framework that fuses vision with dynamics to simultaneously learn shape, pose trajectories, and physical properties via the use of geometry as a shared representation.
no code implementations • 6 May 2023 • Wenxuan Zhou, Bowen Jiang, Fan Yang, Chris Paxton, David Held
In this work, we introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects using point cloud observations.
1 code implementation • 13 Mar 2023 • Bowen Jiang, Camillo J. Taylor
This paper presents a finding that leveraging the hierarchical structures among labels for relationships and objects can substantially improve the performance of scene graph generation systems.
no code implementations • 1 Nov 2022 • Maohao Shen, Bowen Jiang, Jacky Yibo Zhang, Oluwasanmi Koyejo
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators.
no code implementations • 29 Sep 2021 • Maohao Shen, Bowen Jiang, Jacky Y. Zhang, Oluwasanmi O Koyejo
We propose a novel and general framework (i. e., SABAL) that formulates batch active learning as a sparse approximation problem.
no code implementations • 8 Aug 2020 • Bowen Jiang, Maohao Shen
When performing classification tasks, raw high dimensional features often contain redundant information, and lead to increased computational complexity and overfitting.