Zobrazeno 1 - 10
of 746
pro vyhledávání: '"Zhou, Siyuan"'
Text-to-video models have demonstrated substantial potential in robotic decision-making, enabling the imagination of realistic plans of future actions as well as accurate environment simulation. However, one major issue in such models is generalizati
Externí odkaz:
http://arxiv.org/abs/2404.12377
Autor:
Lin, Kunyang, Wang, Yufeng, Chen, Peihao, Zeng, Runhao, Zhou, Siyuan, Tan, Mingkui, Gan, Chuang
Learning optimal behavior policy for each agent in multi-agent systems is an essential yet difficult problem. Despite fruitful progress in multi-agent reinforcement learning, the challenge of addressing the dynamics of whether two agents should exhib
Externí odkaz:
http://arxiv.org/abs/2312.05783
Autor:
Zhou, Siyuan, Du, Yilun, Zhang, Shun, Xu, Mengdi, Shen, Yikang, Xiao, Wei, Yeung, Dit-Yan, Gan, Chuang
Diffusion models have risen as a promising approach to data-driven planning, and have demonstrated impressive robotic control, reinforcement learning, and video planning performance. Given an effective planner, an important question to consider is re
Externí odkaz:
http://arxiv.org/abs/2310.09629
In this work, we present a new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are relevant to t
Externí odkaz:
http://arxiv.org/abs/2212.02871
Semantic segmentation is an important and prevalent task, but severely suffers from the high cost of pixel-level annotations when extending to more classes in wider applications. To this end, we focus on the problem named weak-shot semantic segmentat
Externí odkaz:
http://arxiv.org/abs/2210.02270
Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem
Externí odkaz:
http://arxiv.org/abs/2209.08244
Object placement aims to place a foreground object over a background image with a suitable location and size. In this work, we treat object placement as a graph completion problem and propose a novel graph completion module (GCM). The background scen
Externí odkaz:
http://arxiv.org/abs/2207.11464
Autor:
Gan, Chuang, Gu, Yi, Zhou, Siyuan, Schwartz, Jeremy, Alter, Seth, Traer, James, Gutfreund, Dan, Tenenbaum, Joshua B., McDermott, Josh, Torralba, Antonio
The way an object looks and sounds provide complementary reflections of its physical properties. In many settings cues from vision and audition arrive asynchronously but must be integrated, as when we hear an object dropped on the floor and then must
Externí odkaz:
http://arxiv.org/abs/2207.03483
We present Native Chinese Reader (NCR), a new machine reading comprehension (MRC) dataset with particularly long articles in both modern and classical Chinese. NCR is collected from the exam questions for the Chinese course in China's high schools, w
Externí odkaz:
http://arxiv.org/abs/2112.06494
Publikováno v:
In Applied Mathematics and Computation 1 August 2024 474