Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Vemprala, Sai"'
State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its application t
Externí odkaz:
http://arxiv.org/abs/2410.06718
With the advent of large foundation model based planning, there is a dire need to ensure their output aligns with the stakeholder's intent. When these models are deployed in the real world, the need for alignment is magnified due to the potential cos
Externí odkaz:
http://arxiv.org/abs/2408.05336
Autor:
Bhattacharya, Anish, Madaan, Ratnesh, Cladera, Fernando, Vemprala, Sai, Bonatti, Rogerio, Daniilidis, Kostas, Kapoor, Ashish, Kumar, Vijay, Matni, Nikolai, Gupta, Jayesh K.
We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too fast to capture with a standa
Externí odkaz:
http://arxiv.org/abs/2310.02437
Developing machine intelligence abilities in robots and autonomous systems is an expensive and time consuming process. Existing solutions are tailored to specific applications and are harder to generalize. Furthermore, scarcity of training data adds
Externí odkaz:
http://arxiv.org/abs/2310.00887
Autor:
Wei, Yao, Sun, Yanchao, Zheng, Ruijie, Vemprala, Sai, Bonatti, Rogerio, Chen, Shuhang, Madaan, Ratnesh, Ba, Zhongjie, Kapoor, Ashish, Ma, Shuang
We introduce DualMind, a generalist agent designed to tackle various decision-making tasks that addresses challenges posed by current methods, such as overfitting behaviors and dependence on task-specific fine-tuning. DualMind uses a novel "Dual-phas
Externí odkaz:
http://arxiv.org/abs/2307.07909
Large-scale self-supervised models have recently revolutionized our ability to perform a variety of tasks within the vision and language domains. However, using such models for autonomous systems is challenging because of safety requirements: besides
Externí odkaz:
http://arxiv.org/abs/2303.04212
This paper presents an experimental study regarding the use of OpenAI's ChatGPT for robotics applications. We outline a strategy that combines design principles for prompt engineering and the creation of a high-level function library which allows Cha
Externí odkaz:
http://arxiv.org/abs/2306.17582
In this report, we present our approach and empirical results of applying masked autoencoders in two egocentric video understanding tasks, namely, Object State Change Classification and PNR Temporal Localization, of Ego4D Challenge 2022. As team TheS
Externí odkaz:
http://arxiv.org/abs/2211.15286
Complex systems are often decomposed into modular subsystems for engineering tractability. Although various equation based white-box modeling techniques make use of such structure, learning based methods have yet to incorporate these ideas broadly. W
Externí odkaz:
http://arxiv.org/abs/2210.16294
Robotics has long been a field riddled with complex systems architectures whose modules and connections, whether traditional or learning-based, require significant human expertise and prior knowledge. Inspired by large pre-trained language models, th
Externí odkaz:
http://arxiv.org/abs/2209.11133