Zobrazeno 1 - 10
of 840
pro vyhledávání: '"Li, Zhiqi"'
Large Language Models (LLMs) are thought to struggle with arithmetic learning due to the inherent differences between language modeling and numerical computation, but concrete evidence has been lacking. This work responds to this claim through a two-
Externí odkaz:
http://arxiv.org/abs/2410.15580
Recent advancements in 2D/3D generative techniques have facilitated the generation of dynamic 3D objects from monocular videos. Previous methods mainly rely on the implicit neural radiance fields (NeRF) or explicit Gaussian Splatting as the underlyin
Externí odkaz:
http://arxiv.org/abs/2410.06756
We propose a novel solid-fluid interaction method for coupling elastic solids with impulse flow maps. Our key idea is to unify the representation of fluid and solid components as particle flow maps with different lengths and dynamics. The solid-fluid
Externí odkaz:
http://arxiv.org/abs/2409.09225
We propose a novel framework for simulating ink as a particle-laden flow using particle flow maps. Our method addresses the limitations of existing flow-map techniques, which struggle with dissipative forces like viscosity and drag, thereby extending
Externí odkaz:
http://arxiv.org/abs/2409.06246
Autor:
Li, Zhenxin, Li, Kailin, Wang, Shihao, Lan, Shiyi, Yu, Zhiding, Ji, Yishen, Li, Zhiqi, Zhu, Ziyue, Kautz, Jan, Wu, Zuxuan, Jiang, Yu-Gang, Alvarez, Jose M.
We propose Hydra-MDP, a novel paradigm employing multiple teachers in a teacher-student model. This approach uses knowledge distillation from both human and rule-based teachers to train the student model, which features a multi-head decoder to learn
Externí odkaz:
http://arxiv.org/abs/2406.06978
This paper introduces a novel Lagrangian fluid solver based on covector flow maps. We aim to address the challenges of establishing a robust flow-map solver for incompressible fluids under complex boundary conditions. Our key idea is to use particle
Externí odkaz:
http://arxiv.org/abs/2405.09801
While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work. To address this task, 1) we intr
Externí odkaz:
http://arxiv.org/abs/2403.09981
Autor:
Chen, Guo, Huang, Yifei, Xu, Jilan, Pei, Baoqi, Chen, Zhe, Li, Zhiqi, Wang, Jiahao, Li, Kunchang, Lu, Tong, Wang, Limin
Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.
Externí odkaz:
http://arxiv.org/abs/2403.09626
Federated learning (FL) involves multiple heterogeneous clients collaboratively training a global model via iterative local updates and model fusion. The generalization of FL's global model has a large gap compared with centralized training, which is
Externí odkaz:
http://arxiv.org/abs/2402.18949
In deep learning, stochastic gradient descent often yields functionally similar yet widely scattered solutions in the weight space even under the same initialization, causing barriers in the Linear Mode Connectivity (LMC) landscape. Overcoming these
Externí odkaz:
http://arxiv.org/abs/2402.01342