no code implementations • 3 Jan 2025 • Zeke Xie, Zheng He, Nan Lu, Lichen Bai, Bao Li, Shuo Yang, Mingming Sun, Ping Li
Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores.
no code implementations • 17 Dec 2024 • Zipeng Qi, Buhua Liu, Shiyan Zhang, Bao Li, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e. g., ~1000 seconds per classifying single image on ImageNet).
1 code implementation • 14 Dec 2024 • Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions.
2 code implementations • 16 Nov 2024 • Shitong Shao, Zikai Zhou, Tian Ye, Lichen Bai, Zhiqiang Xu, Zeke Xie
Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis.
1 code implementation • 14 Nov 2024 • Zikai Zhou, Shitong Shao, Lichen Bai, Zhiqiang Xu, Bo Han, Zeke Xie
With the prepared NPD as the training dataset, we trained a small \textit{noise prompt network}~(NPNet) that can directly learn to transform a random noise into a golden noise.
no code implementations • 3 Nov 2024 • Tianhao Peng, Yuchen Li, Xuhong LI, Jiang Bian, Zeke Xie, Ning Sui, Shahid Mumtaz, Yanwu Xu, Linghe Kong, Haoyi Xiong
Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science.
1 code implementation • 5 Oct 2024 • Shitong Shao, Zikai Zhou, Lichen Bai, Haoyi Xiong, Zeke Xie
While there have been rapid advancements in developing inference-heavy algorithms for improved image generation, relatively little work has explored inference scaling laws in video diffusion models (VDMs).
1 code implementation • 11 Sep 2024 • Buhua Liu, Shitong Shao, Bao Li, Lichen Bai, Zhiqiang Xu, Haoyi Xiong, James Kwok, Sumi Helal, Zeke Xie
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications.
no code implementations • 27 Aug 2024 • Muyao Wang, Zeke Xie, Bo Chen
To fill this gap, we propose a channel-wise influence function, which is the first method that can estimate the influence of different channels in MTS, utilizing a first-order gradient approximation that leverages the more informative average gradient of the data set.
no code implementations • 19 Jul 2024 • Zipeng Qi, Lichen Bai, Haoyi Xiong, Zeke Xie
We are the first to hypothesize and empirically observe that the generation quality of diffusion models significantly depend on the noise inversion stability.
no code implementations • 11 Jul 2024 • Haoyi Xiong, Zhiyuan Wang, Xuhong LI, Jiang Bian, Zeke Xie, Shahid Mumtaz, Anwer Al-Dulaimi, Laura E. Barnes
This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements.
no code implementations • 29 Mar 2024 • Zhongrui Yu, Haoran Wang, Jinze Yang, Hanzhang Wang, Zeke Xie, Yunfeng Cai, Jiale Cao, Zhong Ji, Mingming Sun
To tackle this problem, we propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model along with complementary multi-modal data.
no code implementations • 2 Mar 2024 • Xindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun
We successfully propose a novel Neural Field Classifier (NFC) framework which formulates existing neural field methods as classification tasks rather than regression tasks.
no code implementations • 11 Jan 2024 • Hanzhang Wang, Haoran Wang, Jinze Yang, Zhongrui Yu, Zeke Xie, Lei Tian, Xinyan Xiao, Junjun Jiang, Xianming Liu, Mingming Sun
In the specific, our model is constructed based on Latent Diffusion Model (LDM) and elaborately designed to absorb content and style instance as conditions of LDM.
1 code implementation • ICCV 2023 • Zeke Xie, Xindi Yang, Yujie Yang, Qi Sun, Yixiang Jiang, Haoran Wang, Yunfeng Cai, Mingming Sun
Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images.
1 code implementation • 17 Jun 2022 • Zheng He, Zeke Xie, Quanzhi Zhu, Zengchang Qin
People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity.
no code implementations • 19 May 2022 • Shuo Yang, Zeke Xie, Hanyu Peng, Min Xu, Mingming Sun, Ping Li
To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap.
no code implementations • 31 Jan 2022 • Zeke Xie, Qian-Yuan Tang, Yunfeng Cai, Mingming Sun, Ping Li
It is well-known that the Hessian of deep loss landscape matters to optimization, generalization, and even robustness of deep learning.
no code implementations • 29 Sep 2021 • Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and flat minima selection.
1 code implementation • 31 Mar 2021 • Zeke Xie, Li Yuan, Zhanxing Zhu, Masashi Sugiyama
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks.
1 code implementation • NeurIPS 2023 • Zeke Xie, Zhiqiang Xu, Jingzhao Zhang, Issei Sato, Masashi Sugiyama
Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs).
1 code implementation • 12 Nov 2020 • Zeke Xie, Fengxiang He, Shaopeng Fu, Issei Sato, DaCheng Tao, Masashi Sugiyama
Thus it motivates us to design a similar mechanism named {\it artificial neural variability} (ANV), which helps artificial neural networks learn some advantages from ``natural'' neural networks.
no code implementations • 28 Sep 2020 • Zeke Xie, Issei Sato, Masashi Sugiyama
\citet{loshchilov2018decoupled} demonstrated that $L_{2}$ regularization is not identical to weight decay for adaptive gradient methods, such as Adaptive Momentum Estimation (Adam), and proposed Adam with Decoupled Weight Decay (AdamW).
1 code implementation • 29 Jun 2020 • Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and minima selection.
no code implementations • ICLR 2021 • Zeke Xie, Issei Sato, Masashi Sugiyama
Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice.
no code implementations • 22 Nov 2017 • Zeke Xie, Issei Sato
The contribution of this work is two-fold, a novel ensemble regression algorithm inspired by quantum mechanics and the theoretical connection between quantum interpretations and machine learning algorithms.