Zobrazeno 1 - 10
of 204
pro vyhledávání: '"Fan, David P."'
Autor:
Tong, Shengbang, Fan, David, Zhu, Jiachen, Xiong, Yunyang, Chen, Xinlei, Sinha, Koustuv, Rabbat, Michael, LeCun, Yann, Xie, Saining, Liu, Zhuang
In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating both text a
Externí odkaz:
http://arxiv.org/abs/2412.14164
Autor:
Lee, Seon-Ho, Wang, Jue, Fan, David, Zhang, Zhikang, Liu, Linda, Hao, Xiang, Bhat, Vimal, Li, Xinyu
Publikováno v:
WACV 2025
Audio Description (AD) plays a pivotal role as an application system aimed at guaranteeing accessibility in multimedia content, which provides additional narrations at suitable intervals to describe visual elements, catering specifically to the needs
Externí odkaz:
http://arxiv.org/abs/2412.10002
Autor:
Wang, Yicheng, Zhang, Zhikang, Wang, Jue, Fan, David, Xu, Zhenlin, Liu, Linda, Hao, Xiang, Bhat, Vimal, Li, Xinyu
In various video-language learning tasks, the challenge of achieving cross-modality alignment with multi-grained data persists. We propose a method to tackle this challenge from two crucial perspectives: data and modeling. Given the absence of a mult
Externí odkaz:
http://arxiv.org/abs/2412.07704
Publikováno v:
NeurIPS 2024
As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in informat
Externí odkaz:
http://arxiv.org/abs/2410.23782
Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how of
Externí odkaz:
http://arxiv.org/abs/2408.00759
Traversability estimation in rugged, unstructured environments remains a challenging problem in field robotics. Often, the need for precise, accurate traversability estimation is in direct opposition to the limited sensing and compute capability pres
Externí odkaz:
http://arxiv.org/abs/2407.08720
Autor:
Ginting, Muhammad Fadhil, Kim, Sung-Kyun, Fan, David D., Palieri, Matteo, Kochenderfer, Mykel J., Agha-Mohammadi, Ali-akbar
Publikováno v:
Proc. of Robotics: Science and Systems 2024
This paper addresses the problem of object-goal navigation in autonomous inspections in real-world environments. Object-goal navigation is crucial to enable effective inspections in various settings, often requiring the robot to identify the target o
Externí odkaz:
http://arxiv.org/abs/2405.09822
Autor:
Vlahov, Bogdan, Gibson, Jason, Fan, David D., Spieler, Patrick, Agha-mohammadi, Ali-akbar, Theodorou, Evangelos A.
Publikováno v:
IEEE Robotics and Automation Letters, vol. 9, no. 5, pp.4543-4550, 2024
Sampling-based model-predictive controllers have become a powerful optimization tool for planning and control problems in various challenging environments. In this paper, we show how the default choice of uncorrelated Gaussian distributions can be im
Externí odkaz:
http://arxiv.org/abs/2404.03094
Autor:
Frey, Jonas, Patel, Manthan, Atha, Deegan, Nubert, Julian, Fan, David, Agha, Ali, Padgett, Curtis, Spieler, Patrick, Hutter, Marco, Khattak, Shehryar
Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image qualit
Externí odkaz:
http://arxiv.org/abs/2402.19341
Autor:
Ginting, Muhammad Fadhil, Fan, David D., Kim, Sung-Kyun, Kochenderfer, Mykel J., Agha-mohammadi, Ali-akbar
This paper addresses the problem of autonomous robotic inspection in complex and unknown environments. This capability is crucial for efficient and precise inspections in various real-world scenarios, even when faced with perceptual uncertainty and l
Externí odkaz:
http://arxiv.org/abs/2401.17191