no code implementations • 24 Jan 2024 • Ke Ye, Heinrich Jiang, Afshin Rostamizadeh, Ayan Chakrabarti, Giulia Desalvo, Jean-François Kagy, Lazaros Karydas, Gui Citovsky, Sanjiv Kumar
In this paper, we present SpacTor, a new training procedure consisting of (1) a hybrid objective combining span corruption (SC) and token replacement detection (RTD), and (2) a two-stage curriculum that optimizes the hybrid objective over the initial $\tau$ iterations, then transitions to standard SC loss.
no code implementations • 8 Nov 2023 • Miao Kang, Shengqi Wang, Sanping Zhou, Ke Ye, Jingjing Jiang, Nanning Zheng
In this paper, we propose a novel Future Feedback Interaction Network (FFINet) to aggregate features the current observations and potential future interactions for trajectory prediction.
no code implementations • 12 Oct 2022 • Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, Sanjiv Kumar
This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse.
no code implementations • 25 Jun 2020 • Ke Ye, Mu Niu, Pokman Cheung, Zhenwen Dai, YuAn Liu
The introduction of our strip algorithm, tailored for manifolds with extra symmetries, and the ball algorithm, designed for arbitrary manifolds, constitutes our significant contribution.
1 code implementation • 18 Dec 2018 • Tingran Gao, Lek-Heng Lim, Ke Ye
We introduce in this paper a manifold optimization framework that utilizes semi-Riemannian structures on the underlying smooth manifolds.
Optimization and Control Numerical Analysis 90C30, 53C50, 53B30, 49M05, 49M15 F.2.1; G.1.6
no code implementations • 5 Apr 2016 • Ke Ye, Lek-Heng Lim
The goal of cryo-electron microscopy (EM) is to reconstruct the 3-dimensional structure of a molecule from a collection of its 2-dimensional projected images.