no code implementations • 25 Apr 2024 • Peizhuang Cong, Aomufei Yuan, Shimao Chen, Yuxuan Tian, Bowen Ye, Tong Yang
To this end, we traced and analyzed loads of each expert in the training iterations for several large language models in this work, and defined the transient state with "obvious load fluctuation" and the stable state with "temporal locality".
no code implementations • NeurIPS 2023 • Di Qi, Tong Yang, Xiangyu Zhang
We hope our approach can provide preliminary understanding of the physical world and help ease future research in 3D object-centric representation learning.
1 code implementation • 6 Dec 2023 • Hailin Zhang, Zirui Liu, Boxuan Chen, Yikai Zhao, Tong Zhao, Tong Yang, Bin Cui
Guided by our design philosophy, we further propose a multi-level hash embedding framework to optimize the embedding tables of non-hot features.
no code implementations • 6 Dec 2023 • Linze Li, Sunqi Fan, Hengjun Pu, Zhaodong Bing, Yao Tang, Tianzhu Ye, Tong Yang, Liangyu Chen, Jiajun Liang
Our method's efficacy has been validated on multiple representative DreamBooth and LoRA models, delivering substantial improvements over the original outcomes in terms of facial fidelity, text-to-image editability, and video motion.
1 code implementation • 27 Nov 2023 • Hailin Zhang, Penghao Zhao, Xupeng Miao, Yingxia Shao, Zirui Liu, Tong Yang, Bin Cui
Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains.
no code implementations • 1 Nov 2023 • Tong Yang, Shicong Cen, Yuting Wei, Yuxin Chen, Yuejie Chi
Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories.
1 code implementation • NeurIPS 2023 • Longlin Yu, Tianyu Xie, Yu Zhu, Tong Yang, Xiangyu Zhang, Cheng Zhang
Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner.
1 code implementation • 16 Oct 2023 • Ruiqi Wu, Liangyu Chen, Tong Yang, Chunle Guo, Chongyi Li, Xiangyu Zhang
Specifically, we design a first-frame-conditioned pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning.
no code implementations • 5 Apr 2023 • Donglai Wei, Sipeng Zhang, Tong Yang, Yang Liu, Jing Liu
On the other hand, the Masking Caption Modeling (MCM) loss leverages a masked captions prediction task to establish detailed and generic relationships between textual and visual parts.
1 code implementation • 27 Oct 2022 • Tatjana Chavdarova, Matteo Pagliardini, Tong Yang, Michael I. Jordan
We prove its convergence and show that the gap function of the last iterate of this inexact-ACVI method decreases at a rate of $\mathcal{O}(\frac{1}{\sqrt{K}})$ when the operator is $L$-Lipschitz and monotone, provided that the errors decrease at appropriate rates.
no code implementations • 25 Oct 2022 • Tianci Liu, Tong Yang, Quan Zhang, Qi Lei
Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations.
1 code implementation • 21 Jun 2022 • Tong Yang, Michael I. Jordan, Tatjana Chavdarova
We provide convergence guarantees for ACVI in two general classes of problems: (i) when the operator is $\xi$-monotone, and (ii) when it is monotone, some constraints are active and the game is not purely rotational.
1 code implementation • 9 May 2022 • Liang Xie, Hongxiang Yu, Kechun Xu, Tong Yang, Minhang Wang, Haojian Lu, Rong Xiong, Yue Wang
This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary unseen shapes in real world with minimal sim-to-real cost.
no code implementations • 16 Apr 2022 • Tong Yang
This study clarifies the proper criteria to assess the modeling capacity of a general tensor model.
no code implementations • 16 Apr 2022 • Tong Yang
We analyze the problem of high-order polynomial approximation from a many-body physics perspective, and demonstrate the descriptive power of entanglement entropy in capturing model capacity and task complexity.
no code implementations • 15 Apr 2022 • Tong Yang, Yifei Wang, Long Sha, Jan Engelbrecht, Pengyu Hong
As far as we know, by applying abstract algebra in statistical learning, this work develops the first formal language for general knowledge graphs, and also sheds light on the problem of neural-symbolic integration from an algebraic perspective.
no code implementations • 19 Jan 2022 • Zhexin Li, Tong Yang, Peisong Wang, Jian Cheng
In this paper, we propose a fully differentiable quantization method for vision transformer (ViT) named as Q-ViT, in which both of the quantization scales and bit-widths are learnable parameters.
1 code implementation • 23 Sep 2021 • Peizhen Zhang, Zijian Kang, Tong Yang, Xiangyu Zhang, Nanning Zheng, Jian Sun
Instead, we generate an instructive knowledge based only on student representations and regular labels.
2 code implementations • 15 Sep 2021 • Yingming Wang, Xiangyu Zhang, Tong Yang, Jian Sun
Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs.
1 code implementation • CVPR 2021 • Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei zhang, Jian Sun
We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points.
6 code implementations • CVPR 2021 • Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun
From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.
Ranked #142 on Object Detection on COCO test-dev
no code implementations • 4 Dec 2020 • Leilei Cao, Tong Yang, Yixu Wang, Bo Yan, Yandong Guo
Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image.
1 code implementation • 3 Dec 2020 • Tiancai Wang, Tong Yang, Jiale Cao, Xiangyu Zhang
Object detectors usually achieve promising results with the supervision of complete instance annotations.
no code implementations • 10 Sep 2020 • Hengrui Wang, Yubo Zhang, Mingzhi Chen, Tong Yang
We first divide objects into a great many tiny clusters.
no code implementations • 13 Aug 2020 • Tong Yang, Long Sha, Pengyu Hong
While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet.
no code implementations • 9 Aug 2020 • Tong Yang, Long Sha, Justin Li, Pengyu Hong
In this work, we developed a deep learning model-based approach to forecast the spreading trend of SARS-CoV-2 in the United States.
no code implementations • 10 Jun 2020 • Xiangyi Meng, Tong Yang
Chaotic time series forecasting has been far less understood despite its tremendous potential in theory and real-world applications.
1 code implementation • 26 May 2020 • Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo
Third, we alternately use different upsampling methods in the upsampling stage to reduce the high computation complexity and still remain satisfactory performance.
Ranked #1 on Image Super-Resolution on DIV8K test - 16x upscaling
no code implementations • 22 May 2020 • Tong Yang, Long Sha, Pengyu Hong
We demonstrated the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for designing embedding models.
no code implementations • 3 May 2020 • Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru Ooba, Norimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung-Hoon Kim, JaeHyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh P. S, Densen Puthussery, Jiji C. V
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
1 code implementation • CVPR 2020 • Tiancai Wang, Tong Yang, Martin Danelljan, Fahad Shahbaz Khan, Xiangyu Zhang, Jian Sun
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
no code implementations • 25 Sep 2019 • Yichen Zhu, Xiangyu Zhang, Tong Yang, Jian Sun
We introduce the adaptive resizable networks as dynamic networks, which further improve the performance with less computational cost via data-dependent inference.
1 code implementation • 25 Sep 2019 • Yikai Zhao, Peiqing Chen, Zidong Zhao, Tong Yang, Jie Jiang, Bin Cui, Gong Zhang, Steve Uhlig
First, we introduced RP Trees into the tasks of similarity measurement such that accuracy is improved.
1 code implementation • 25 Sep 2019 • Chenxingyu Zhao, Jie Gui, Yixiao Guo, Jie Jiang, Tong Yang, Bin Cui, Gong Zhang
Unlike the densification to fill the empty bins after they undesirably occur, our design goal is to balance the load so as to reduce the empty bins in advance.
no code implementations • 25 Sep 2019 • Tong Yang, Long Sha, Pengyu Hong
We have rigorously proved the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for model design.
2 code implementations • NeurIPS 2019 • Yukang Chen, Tong Yang, Xiangyu Zhang, Gaofeng Meng, Xinyu Xiao, Jian Sun
In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.
no code implementations • NeurIPS 2018 • Tong Yang, Xiangyu Zhang, Zeming Li, Wenqiang Zhang, Jian Sun
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks.