3 code implementations • 7 Jan 2025 • Nvidia, :, Niket Agarwal, Arslan Ali, Maciej Bala, Yogesh Balaji, Erik Barker, Tiffany Cai, Prithvijit Chattopadhyay, Yongxin Chen, Yin Cui, Yifan Ding, Daniel Dworakowski, Jiaojiao Fan, Michele Fenzi, Francesco Ferroni, Sanja Fidler, Dieter Fox, Songwei Ge, Yunhao Ge, Jinwei Gu, Siddharth Gururani, Ethan He, Jiahui Huang, Jacob Huffman, Pooya Jannaty, Jingyi Jin, Seung Wook Kim, Gergely Klár, Grace Lam, Shiyi Lan, Laura Leal-Taixe, Anqi Li, Zhaoshuo Li, Chen-Hsuan Lin, Tsung-Yi Lin, Huan Ling, Ming-Yu Liu, Xian Liu, Alice Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Arsalan Mousavian, Seungjun Nah, Sriharsha Niverty, David Page, Despoina Paschalidou, Zeeshan Patel, Lindsey Pavao, Morteza Ramezanali, Fitsum Reda, Xiaowei Ren, Vasanth Rao Naik Sabavat, Ed Schmerling, Stella Shi, Bartosz Stefaniak, Shitao Tang, Lyne Tchapmi, Przemek Tredak, Wei-Cheng Tseng, Jibin Varghese, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Xinyue Wei, Jay Zhangjie Wu, Jiashu Xu, Wei Yang, Lin Yen-Chen, Xiaohui Zeng, Yu Zeng, Jing Zhang, Qinsheng Zhang, Yuxuan Zhang, Qingqing Zhao, Artur Zolkowski
We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications.
1 code implementation • 10 Sep 2024 • Yifei He, Haoxiang Wang, Ziyan Jiang, Alexandros Papangelis, Han Zhao
Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs).
2 code implementations • 18 Jun 2024 • Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang
The trained RM serves as a proxy for human preferences.
3 code implementations • 13 May 2024 • Hanze Dong, Wei Xiong, Bo Pang, Haoxiang Wang, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature.
no code implementations • 15 Mar 2024 • Xiaohang Yu, Zhengxian Yang, Shi Pan, Yuqi Han, Haoxiang Wang, Jun Zhang, Shi Yan, Borong Lin, Lei Yang, Tao Yu, Lu Fang
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios.
1 code implementation • 28 Feb 2024 • Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
1 code implementation • 5 Feb 2024 • Haoxiang Wang, Haozhe Si, Huajie Shao, Han Zhao
To delve into the CG challenge, we develop CG-Bench, a suite of CG benchmarks derived from existing real-world image datasets, and observe that the prevalent pretraining-finetuning paradigm on foundational models, such as CLIP and DINOv2, struggles with the challenge.
1 code implementation • 2 Nov 2023 • Haoxiang Wang, Gargi Balasubramaniam, Haozhe Si, Bo Li, Han Zhao
First, in the binary classification setup of Rosenfeld et al. (2021), we show that our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments.
no code implementations • 23 Oct 2023 • Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
2 code implementations • 20 Oct 2023 • Yifei He, Haoxiang Wang, Bo Li, Han Zhao
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way.
1 code implementation • 12 Sep 2023 • Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan YAO, Tong Zhang
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different alignment-forgetting trade-offs, we propose Heterogeneous Model Averaging (HMA) to Heterogeneously find various combination ratios of model layers.
no code implementations • 4 Sep 2023 • Xiaohang Yu, Haoxiang Wang, Yuqi Han, Lei Yang, Tao Yu, Qionghai Dai
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation.
no code implementations • 11 Apr 2023 • Yunheng Shen, Haoxiang Wang, Hairong Lv
Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged.
no code implementations • 9 Dec 2022 • Mingze Sun, Haoxiang Wang, Wei Yao, Jiawang Liu
Recent studies have found that pain in infancy has a significant impact on infant development, including psychological problems, possible brain injury, and pain sensitivity in adulthood.
1 code implementation • 30 Nov 2022 • Haoxiang Wang, Maurice Weber, Josh Izaac, Cedric Yen-Yu Lin
For many ground states of gapped Hamiltonians, generative models can learn from measurements of a single quantum state to reconstruct the state accurately enough to predict local observables.
no code implementations • 23 Oct 2022 • Yao Wei, Haoxiang Wang, Mingze Sun, Jiawang Liu
In this paper, we propose a novel Attention Based Relation Network (ABRNet) for AU recognition, which can automatically capture AU relations without unnecessary or even disturbing predefined rules.
no code implementations • 2 Sep 2022 • Mao Ye, Ruichen Jiang, Haoxiang Wang, Dhruv Choudhary, Xiaocong Du, Bhargav Bhushanam, Aryan Mokhtari, Arun Kejariwal, Qiang Liu
One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error.
no code implementations • 28 Aug 2022 • Haoxiang Wang, Zhanhong Jiang, Chao Liu, Soumik Sarkar, Dongxiang Jiang, Young M. Lee
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.
3 code implementations • 18 Apr 2022 • Haoxiang Wang, Bo Li, Han Zhao
Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.
1 code implementation • CVPR 2022 • Haoxiang Wang, Yite Wang, Ruoyu Sun, Bo Li
We show that the performance of MetaNTK-NAS is comparable or better than the state-of-the-art NAS method designed for few-shot learning while enjoying more than 100x speedup.
1 code implementation • 30 Jan 2022 • Haoxiang Wang, Haozhe Si, Bo Li, Han Zhao
Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).
1 code implementation • 16 Jun 2021 • Haoxiang Wang, Han Zhao, Bo Li
Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation.
Ranked #18 on
Few-Shot Image Classification
on FC100 5-way (1-shot)
no code implementations • 12 Nov 2020 • Haoxiang Wang, Jiasheng Zhang, Chenbei Lu, Chenye Wu
In this paper, we cast one-shot non-intrusive load monitoring (NILM) in the compressive sensing framework, and bridge the gap between theoretical accuracy of NILM inference and differential privacy's parameters.
2 code implementations • 25 Jun 2020 • Haoxiang Wang, Ruoyu Sun, Bo Li
Gradient-based meta-learning (GBML) with deep neural nets (DNNs) has become a popular approach for few-shot learning.
no code implementations • 12 Dec 2019 • Jingshi Cui, Haoxiang Wang, Chenye Wu, Yang Yu
To enable an efficient electricity market, a good pricing scheme is of vital importance.
no code implementations • NeurIPS 2019 • Yingxiang Yang, Haoxiang Wang, Negar Kiyavash, Niao He
The nonparametric learning of positive-valued functions appears widely in machine learning, especially in the context of estimating intensity functions of point processes.
no code implementations • 18 Nov 2019 • Jingshi Cui, Haoxiang Wang, Chenye Wu, Yang Yu
In this paper, from an adversarial machine learning point of view, we examine the vulnerability of data-driven electricity market design.
no code implementations • 22 Jun 2017 • Rongcui Dong, Haoxiang Wang
This thesis describes a study to perform change detection on Very High Resolution satellite images using image fusion based on 2D Discrete Wavelet Transform and Fuzzy C-Means clustering algorithm.
no code implementations • 14 Dec 2016 • Zeling Wu, Haoxiang Wang
In this article, we propose a super-resolution method to resolve the problem of image low spatial because of the limitation of imaging devices.
no code implementations • 22 Apr 2016 • Ru-Ze Liang, Lihui Shi, Haoxiang Wang, Jiandong Meng, Jim Jing-Yan Wang, Qingquan Sun, Yi Gu
To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure.
no code implementations • 25 Aug 2015 • Jingbin Wang, Haoxiang Wang, Yihua Zhou, Nancy McDonald
The learning of the classifier parameter and the kernel weight are unified in a single objective function considering to minimize the upper boundary of the given multivariate performance measure.
no code implementations • 18 Aug 2015 • Jing-Yan Wang, Yihua Zhou, Haoxiang Wang, Xiaohong Yang, Feng Yang, Austin Peterson
The problem of tag completion is to learn the missing tags of an image.