Zobrazeno 1 - 10
of 112
pro vyhledávání: '"Walter, Matthew R."'
Humans naturally obtain intuition about the interactions between and the stability of rigid objects by observing and interacting with the world. It is this intuition that governs the way in which we regularly configure objects in our environment, all
Externí odkaz:
http://arxiv.org/abs/2409.18098
Autor:
Yunis, David, Patel, Kumar Kshitij, Wheeler, Samuel, Savarese, Pedro, Vardi, Gal, Livescu, Karen, Maire, Michael, Walter, Matthew R.
We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in optimization
Externí odkaz:
http://arxiv.org/abs/2408.11804
Autor:
Fang, Jiading, Tan, Xiangshan, Lin, Shengjie, Vasiljevic, Igor, Guizilini, Vitor, Mei, Hongyuan, Ambrus, Rares, Shakhnarovich, Gregory, Walter, Matthew R
If robots are to work effectively alongside people, they must be able to interpret natural language references to objects in their 3D environment. Understanding 3D referring expressions is challenging -- it requires the ability to both parse the 3D s
Externí odkaz:
http://arxiv.org/abs/2404.19221
Counterfactual explanations (CFEs) are sets of actions that an agent with a negative classification could take to achieve a (desired) positive classification, for consequential decisions such as loan applications, hiring, admissions, etc. In this wor
Externí odkaz:
http://arxiv.org/abs/2404.17034
Autor:
Ding, Peng, Fang, Jiading, Li, Peng, Wang, Kangrui, Zhou, Xiaochen, Yu, Mo, Li, Jing, Walter, Matthew R., Mei, Hongyuan
Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a benchmark to evaluate their capabilities to perform text-based mappin
Externí odkaz:
http://arxiv.org/abs/2403.19913
A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning, with limited
Externí odkaz:
http://arxiv.org/abs/2310.17649
While reinforcement learning (RL) has shown promising performance, its sample complexity continues to be a substantial hurdle, restricting its broader application across a variety of domains. Imitation learning (IL) utilizes oracles to improve sample
Externí odkaz:
http://arxiv.org/abs/2310.01737
Shared autonomy enables novice remote users to conduct deep-ocean science operations with robotic manipulators.
Externí odkaz:
http://arxiv.org/abs/2309.08555
Autor:
Yoneda, Takuma, Fang, Jiading, Li, Peng, Zhang, Huanyu, Jiang, Tianchong, Lin, Shengjie, Picker, Ben, Yunis, David, Mei, Hongyuan, Walter, Matthew R.
There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and observation
Externí odkaz:
http://arxiv.org/abs/2306.17840
Reinforcement learning (RL) has made significant strides in various complex domains. However, identifying an effective policy via RL often necessitates extensive exploration. Imitation learning aims to mitigate this issue by using expert demonstratio
Externí odkaz:
http://arxiv.org/abs/2306.10259