Search Results for author: Haoyue Bai

Found 30 papers, 13 papers with code

Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback

no code implementations21 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.

Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation

1 code implementation21 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.

Decoder

Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories

no code implementations21 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.

Decision Making Feature Engineering +3

A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective

no code implementations12 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.

Feature Engineering feature selection +3

Where's the Liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content

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.

Misinformation

Deep Active Learning in the Open World

no code implementations10 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.

Active Learning Diversity +2

Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches

no code implementations25 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.

Data Augmentation Neural Architecture Search +1

AHA: Human-Assisted Out-of-Distribution Generalization and Detection

no code implementations10 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.

Out-of-Distribution Generalization

Out-of-Distribution Learning with Human Feedback

no code implementations14 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.

It is Never Too Late to Mend: Separate Learning for Multimedia Recommendation

1 code implementation12 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.

cross-modal alignment Multimedia recommendation +1

Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias

1 code implementation31 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.

Collaborative Filtering Contrastive Learning

Double Correction Framework for Denoising Recommendation

1 code implementation18 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.

Denoising Model Optimization +1

HYPO: Hyperspherical Out-of-Distribution Generalization

1 code implementation12 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.

Out-of-Distribution Generalization

Image change detection with only a few samples

no code implementations7 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.

Change Detection object-detection +1

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

no code implementations15 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.

Out-of-Distribution Generalization

Improving Out-of-Distribution Robustness of Classifiers Through Interpolated Generative Models

no code implementations29 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.

Data Augmentation Diversity

Voxel Transformer for 3D Object Detection

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)

3D Object Detection Computational Efficiency +3

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

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.

3D Object Detection object-detection

NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization

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.

Domain Generalization Neural Architecture Search +1

Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting

no code implementations28 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.

Crowd Counting

A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal

1 code implementation31 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.

Crowd Counting Management +1

Crowd Counting on Images with Scale Variation and Isolated Clusters

1 code implementation9 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.

Clustering Crowd Counting

Cannot find the paper you are looking for? You can Submit a new open access paper.