Zobrazeno 1 - 10
of 3 697
pro vyhledávání: '"Su, Hao"'
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed.
Externí odkaz:
http://arxiv.org/abs/2406.19931
The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data formats, li
Externí odkaz:
http://arxiv.org/abs/2406.17741
Autor:
Merrill, Mike A., Paruchuri, Akshay, Rezaei, Naghmeh, Kovacs, Geza, Perez, Javier, Liu, Yun, Schenck, Erik, Hammerquist, Nova, Sunshine, Jake, Tailor, Shyam, Ayush, Kumar, Su, Hao-Wei, He, Qian, McLean, Cory Y., Malhotra, Mark, Patel, Shwetak, Zhan, Jiening, Althoff, Tim, McDuff, Daniel, Liu, Xin
Despite the proliferation of wearable health trackers and the importance of sleep and exercise to health, deriving actionable personalized insights from wearable data remains a challenge because doing so requires non-trivial open-ended analysis of th
Externí odkaz:
http://arxiv.org/abs/2406.06464
We propose a method for preparing the quantum state for a given velocity field, e.g., in fluid dynamics, via the spherical Clebsch wave function (SCWF). Using the pointwise normalization constraint for the SCWF, we develop a variational ansatz compri
Externí odkaz:
http://arxiv.org/abs/2406.04652
Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model.In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towar
Externí odkaz:
http://arxiv.org/abs/2405.19789
Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we
Externí odkaz:
http://arxiv.org/abs/2405.18418
Autor:
Feng, Yutao, Shang, Yintong, Feng, Xiang, Lan, Lei, Zhe, Shandian, Shao, Tianjia, Wu, Hongzhi, Zhou, Kun, Su, Hao, Jiang, Chenfanfu, Yang, Yin
We present ElastoGen, a knowledge-driven model that generates physically accurate and coherent 4D elastodynamics. Instead of relying on petabyte-scale data-driven learning, ElastoGen leverages the principles of physics-in-the-loop and learns from est
Externí odkaz:
http://arxiv.org/abs/2405.15056
Autor:
Li, Xuanlin, Hsu, Kyle, Gu, Jiayuan, Pertsch, Karl, Mees, Oier, Walke, Homer Rich, Fu, Chuyuan, Lunawat, Ishikaa, Sieh, Isabel, Kirmani, Sean, Levine, Sergey, Wu, Jiajun, Finn, Chelsea, Su, Hao, Vuong, Quan, Xiao, Ted
The field of robotics has made significant advances towards generalist robot manipulation policies. However, real-world evaluation of such policies is not scalable and faces reproducibility challenges, which are likely to worsen as policies broaden t
Externí odkaz:
http://arxiv.org/abs/2405.05941
Autor:
Jiang, Kaiwen, Fu, Yang, T, Mukund Varma, Belhe, Yash, Wang, Xiaolong, Su, Hao, Ramamoorthi, Ravi
Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance f
Externí odkaz:
http://arxiv.org/abs/2405.03659
Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL
Externí odkaz:
http://arxiv.org/abs/2405.03379