Publications
Preprints
- Masked Autoencoders Are Effective Tokenizers for Diffusion Models. Hao Chen, Yujin Han, Fangyi Chen, Xiang Li, Yidong Wang, Jindong Wang, Ze Wang, Zicheng Liu, Difan Zou, Bhiksha Raj. [arxiv][Code].
- SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer. Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum. [arxiv][Code].
- On the Diversity of Synthetic Data and its Impact on Training Large Language Models. Hao Chen, Abdul Waheed, Xiang Li, Yidong Wang, Jindong Wang, Bhiksha Raj, Marah I Abdin. [arxiv]
- ControlVAR: Exploring Controllable Visual Autoregressive Modeling. Xiang Li, Kai Qiu, Hao Chen, Jason Kuen, Zhe Lin, Rita Singh, Bhiksha Raj. [arxiv]
- RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection. Fangyi Chen, Han Zhang, Zhantao Yang, Hao Chen, Kai Hu, Marios Savvides. [arxiv]
- Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond. Minghao Liu, Zonglin Di, Jiaheng Wei, Zhongruo Wang, Hengxiang Zhang, Ruixuan Xiao, Haoyu Wang, Jinlong Pang, Hao Chen, Ankit Shah, Hongxin Wei, Xinlei He, Zhaowei Zhao, Haobo Wang, Lei Feng, Jindong Wang, James Davis, Yang Liu. [arxiv]
- Learning with Noisy Foundation Models. Hao Chen, Jindong Wang, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj. [arxiv]
Papers
2025
-
Imagefolder: Autoregressive image generation with folded tokensIn International Conference on Learning Representations (ICLR) , 2025
2024
-
Slight Corruption in Pre-training Data Makes Better Diffusion ModelsIn Neural Information Processing Systems (NeurIPS), Spotlight , 2024 -
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label ConfigurationsIn Neural Information Processing Systems (NeurIPS) , 2024 -
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time AdaptationIn Neural Information Processing Systems (NeurIPS) , 2024 - AgentReview: Exploring Peer Review Dynamics with LLM AgentsIn Empirical Methods in Natural Language Processing (EMNLP) , 2024
-
A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and Technology, 2024 -
$\backslashtext {R}\^ 2$-Bench: Benchmarking the Robustness of Referring Perception Models under PerturbationsIn European Conference on Computer Vision (ECCV) , 2024 -
A General Framework for Learning from Weak SupervisionIn International Conference on Machine Learning (ICML) , 2024 -
On Catastrophic Inheritance of Large Foundation ModelsJournal of Data-centric Machine Learning Research (DMLR), 2024 -
Exploring Vision-Language Models for Imbalanced LearningIn , 2024 -
Understanding and Mitigating the Label Noise in Pre-training on Downstream TasksIn International Conference on Learning Representations (ICLR), Spotlight , 2024 - Pandalm: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationIn International Conference on Learning Representations (ICLR) , 2024
-
Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNetsIn Computer Vision and Pattern Recognition (CVPR), Prompting in Vision Workshop, Oral , 2024 -
Competeai: Understanding the Competition Behaviors in Large Language Model-based AgentsIn International Conference on Machine Learning (ICML), Oral , 2024 -
Completing Visual Objects via Bridging Generation and SegmentationIn International Conference on Machine Learning (ICML) , 2024
2023
-
Promptbench: A Unified Library for Evaluation of Large Language ModelsJournal of Machine Learning Research (JMLR), 2023 -
In , 2023 -
Boosting Transductive Few-shot Fine-tuning with Margin-based Uncertainty Weighting and Probability RegularizationIn Computer Vision and Pattern Recognition (CVPR) , 2023 -
Freematch: Self-adaptive Thresholding for Semi-supervised LearningIn International Conference on Learning Representations (ICLR) , 2023 -
Softmatch: Addressing the quantity-quality trade-off in semi-supervised learningIn International Conference on Learning Representations (ICLR) , 2023
2022
-
Usb: A Unified Semi-supervised Learning Benchmark for ClassificationIn Neural Information Processing Systems (NeurIPS), 2022. PyTorch Ecosystem Tools , 2022 -
Unitail: Detecting, Reading, and Matching in Retail SceneIn European Conference on Computer Vision (ECCV) , 2022
2021
-
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosTPAMI, 2021
2020
-
3D Human Shape and Pose from a Single Low-resolution Image with Self-supervised LearningIn European Conference on Computer Vision (ECCV) , 2020
2019
- Adversarial Large-scale Root Gap InpaintingIn Computer Vision and Pattern Recognition (CVPR), Workshop , 2019
2018
- Root Gap Correction with a Deep Inpainting ModelIn British Machine Vision Conference (BMVC), Workshop , 2018