no code implementations • 10 Jun 2025 • Xinyuan Wang, Dongjie Wang, Wangyang Ying, Haoyue Bai, Nanxu Gong, Sixun Dong, Kunpeng Liu, Yanjie Fu
Reasoning is a key component of language understanding in Large Language Models.
no code implementations • 21 May 2025 • Wangyang Ying, Haoyue Bai, Nanxu Gong, Xinyuan Wang, Sixun Dong, Haifeng Chen, Yanjie Fu
Foundation models showed promise in this area, but existing approaches suffer from: 1) They are pretrained on general-purpose data distributions, making them less effective for domain-specific tasks; and 2) their training objectives focus on token-level alignment, overlooking mathematical semantics, which can lead to inaccurate equations.
1 code implementation • 21 May 2025 • Nanxu Gong, Zijun Li, Sixun Dong, Haoyue Bai, Wangyang Ying, Xinyuan Wang, Yanjie Fu
Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models.
no code implementations • 21 May 2025 • Nanxu Gong, Sixun Dong, Haoyue Bai, Xinyuan Wang, Wangyang Ying, Yanjie Fu
As a widely-used and practical tool, feature engineering transforms raw data into discriminative features to advance AI model performance.
no code implementations • 12 Feb 2025 • Wangyang Ying, Cong Wei, Nanxu Gong, Xinyuan Wang, Haoyue Bai, Arun Vignesh Malarkkan, Sixun Dong, Dongjie Wang, Denghui Zhang, Yanjie Fu
This survey focuses on data-driven tabular data optimization, specifically exploring reinforcement learning (RL) and generative approaches for feature selection and feature generation as fundamental techniques for refining data spaces.
no code implementations • 17 Jan 2025 • Dongjie Wang, Yanyong Huang, Wangyang Ying, Haoyue Bai, Nanxu Gong, Xinyuan Wang, Sixun Dong, Tao Zhe, Kunpeng Liu, Meng Xiao, Pengfei Wang, Pengyang Wang, Hui Xiong, Yanjie Fu
This survey examines the key aspects of tabular data-centric AI, emphasizing feature selection and feature generation as essential techniques for data space refinement.
no code implementations • CVPR 2025 • Haoyue Bai, Yiyou Sun, Wei Cheng, Haifeng Chen
The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye.
no code implementations • 10 Nov 2024 • Tian Xie, Jifan Zhang, Haoyue Bai, Robert Nowak
Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations.
no code implementations • 8 Nov 2024 • Wangyang Ying, Haoyue Bai, Kunpeng Liu, Yanjie Fu
Feature space is an environment where data points are vectorized to represent the original dataset.
no code implementations • 25 Oct 2024 • Haoyue Bai
In this thesis, we study ways toward robust OoD generalization for deep learning, i. e., its performance is not susceptible to distribution shift in the test data.
no code implementations • 10 Oct 2024 • Haoyue Bai, Jifan Zhang, Robert Nowak
This paper introduces a novel, integrated approach AHA (Adaptive Human-Assisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild.
no code implementations • 14 Aug 2024 • Haoyue Bai, Xuefeng Du, Katie Rainey, Shibin Parameswaran, Yixuan Li
Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing multifaceted challenges of OOD generalization and OOD detection in real-world deployment environments.
1 code implementation • 12 Jun 2024 • Zhuangzhuang He, Zihan Wang, Yonghui Yang, Haoyue Bai, Le Wu
Specifically, we first use GNN to learn the representations of users and items in different modalities and split each modal representation into generic and unique parts.
1 code implementation • 31 May 2024 • Miaomiao Cai, Lei Chen, Yifan Wang, Haoyue Bai, Peijie Sun, Le Wu, Min Zhang, Meng Wang
To alleviate popularity bias, existing efforts focus on emphasizing unpopular items or separating the correlation between item representations and their popularity.
1 code implementation • 18 May 2024 • Zhuangzhuang He, Yifan Wang, Yonghui Yang, Peijie Sun, Le Wu, Haoyue Bai, Jinqi Gong, Richang Hong, Min Zhang
To tackle the above limitations, we propose a Double Correction Framework for Denoising Recommendation (DCF), which contains two correction components from views of more precise sample dropping and avoiding more sparse data.
1 code implementation • 28 Apr 2024 • Haoyue Bai, Le Wu, Min Hou, Miaomiao Cai, Zhuangzhuang He, Yuyang Zhou, Richang Hong, Meng Wang
How to quickly provide recommendations for new items at the inference time is challenging.
1 code implementation • 12 Feb 2024 • Haoyue Bai, Yifei Ming, Julian Katz-Samuels, Yixuan Li
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world.
no code implementations • 7 Nov 2023 • Ke Liu, Zhaoyi Song, Haoyue Bai
This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available.
no code implementations • 15 Jun 2023 • Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD detection respectively.
no code implementations • 29 Sep 2021 • Haoyue Bai, Ceyuan Yang, Yinghao Xu, S.-H. Gary Chan, Bolei Zhou
In this paper, we employ interpolated generative models to generate OoD samples at training time via data augmentation.
1 code implementation • ICCV 2021 • Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds.
Ranked #3 on
3D Object Detection
on waymo vehicle
(L1 mAP metric)
1 code implementation • ICCV 2021 • Jiageng Mao, Minzhe Niu, Haoyue Bai, Xiaodan Liang, Hang Xu, Chunjing Xu
To resolve the problems, we propose a novel second-stage module, named pyramid RoI head, to adaptively learn the features from the sparse points of interest.
Ranked #2 on
3D Object Detection
on waymo vehicle
(AP metric)
1 code implementation • ICCV 2021 • Haoyue Bai, Fengwei Zhou, Lanqing Hong, Nanyang Ye, S. -H. Gary Chan, Zhenguo Li
In this work, we propose robust Neural Architecture Search for OoD generalization (NAS-OoD), which optimizes the architecture with respect to its performance on generated OoD data by gradient descent.
Ranked #1 on
Domain Generalization
on NICO Vehicle
no code implementations • 20 May 2021 • Haoyue Bai, Song Wen, S. -H. Gary Chan
The classification branch extracts global group priors by learning correlations among image clusters.
no code implementations • 28 Apr 2021 • Haoyue Bai, S. -H. Gary Chan
Noting the scarcity and low quality (in terms of resolution and scene diversity) of the publicly available video crowd datasets, we have collected and built a large-scale video crowd counting datasets, VidCrowd, to contribute to the community.
1 code implementation • 31 Dec 2020 • Haoyue Bai, Jiageng Mao, S. -H. Gary Chan
Single image crowd counting is a challenging computer vision problem with wide applications in public safety, city planning, traffic management, etc.
1 code implementation • 17 Dec 2020 • Haoyue Bai, Rui Sun, Lanqing Hong, Fengwei Zhou, Nanyang Ye, Han-Jia Ye, S. -H. Gary Chan, Zhenguo Li
To address that, we propose DecAug, a novel decomposed feature representation and semantic augmentation approach for OoD generalization.
1 code implementation • 9 Sep 2019 • Haoyue Bai, Song Wen, S. -H. Gary Chan
Designing a general crowd counting algorithm applicable to a wide range of crowd images is challenging, mainly due to the possibly large variation in object scales and the presence of many isolated small clusters.