Jiahao Xie's Homepage

Jiahao Xie

I am a Professor at the School of Artificial Intelligence, Beihang University. Previously, I was a postdoctoral researcher at Max Planck Institute for Informatics (MPI-INF), working with Prof. Bernt Schiele. I obtained my Ph.D. degree from MMLab@NTU, Nanyang Technological University, supervised by Prof. Chen Change Loy and Prof. Yew Soon Ong. I also worked closely with Prof. Ziwei Liu.

My research interests include foundation models, multimodal understanding and generation, and embodied intelligence. My objective is to develop intelligent systems that can perceive, understand, and interact with the physical world, with little to no human supervision.

I am a core developer and maintainer of OpenMMLab projects including MMSelfSup and MMPreTrain .

Email / Google Scholar / GitHub / Twitter

News

[09/2026] Serving as Area Chair for CVPR 2027.

[09/2026] One paper (STRANGE-Bench) accepted to NeurIPS 2026.

[08/2026] Two papers (Video-MME-Logical, TEVI) accepted to EMNLP Findings 2026.

[07/2026] One paper (SSL-R1) accepted to ACM MM 2026 (Oral).

[04/2026] One paper (SemanticNVS) accepted to ICML 2026.

[12/2025] Serving as Area Chair for ECCV 2026.

[06/2025] One paper (CNS-Bench) accepted to ICCV 2025.

[05/2025] Selected as Notable Reviewer for ICLR 2025.

[02/2025] One paper (VICT) accepted to CVPR 2025.

[08/2024] One paper (MosaicFusion) accepted to IJCV 2024.

[05/2023] Selected as Outstanding Reviewer for CVPR 2023.

[04/2023] We released OpenMMLab pre-training toolbox and benchmark MMPreTrain.

[02/2023] One paper (CIM) accepted to CVPR 2023.

[01/2023] One paper (MFM) accepted to ICLR 2023.

[09/2022] One paper (InterCLR) accepted to IJCV 2022.

[03/2022] One paper (UniVIP) accepted to CVPR 2022.

[12/2021] We released OpenMMLab self-supervised learning toolbox and benchmark MMSelfSup.

[09/2021] One paper (ORL) accepted to NeurIPS 2021.

[05/2021] Selected as Outstanding Reviewer for CVPR 2021.

[06/2020] We released self-supervised learning toolbox and benchmark codebase OpenSelfSup.

[03/2020] One paper (ODC) accepted to CVPR 2020.

[11/2019] Our MMLab-SelfSup team won the 1st places of all four tracks in Facebook AI Self-Supervision Challenge.

Publications

	Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models Pengyiang Liu, Junbo Niu, Wenhao Zheng, Xinchen Chen, Canyu Li, Zhongyue Shi, Jiahao Xie^†, Si Liu (^†=corresponding author) arXiv, 2026 Paper
	When Should the Count Change? Learning State Maintenance for Causal Video Counting Pengyiang Liu, Dongyue Lyu, Junbo Niu, Zhongyue Shi, Jiahao Xie^†, Si Liu (^†=corresponding author) arXiv, 2026 Paper
	MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning Yingying Fan, Penghui Du, Leyan Zhu, Runze He, Zimeng Wu, Yuxuan Zhang, Liang Chen, Jiahao Xie, Jiangtang Wang, Shuai Shao, Anchao Yang, Yutong Bai, Yan Wang arXiv, 2026 Paper / Project Page / Code / Dataset
	Stranger Things: When Objects Appear Without Their Typical Neighbours Siddhartha Gairola, Jiahao Xie, Anna Kukleva, Francesco Locatello, Bernt Schiele NeurIPS (Evaluations & Datasets Track), 2026 Paper / Dataset
	Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning Hohin Kwan, Hongyu Li, Ray Zhang, Manyuan Zhang, Xianghao Kong, Anyi Rao, Jiahao Xie^†, Si Liu (^†=corresponding author) EMNLP Findings, 2026 Paper / Project Page / Code / Dataset
	TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele (=equal contribution) EMNLP Findings*, 2026 Paper / Project Page / Code
	SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele ACM MM, 2026 (Oral Presentation) Paper / Code
	R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele arXiv, 2026 Paper / Code
	ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better Mriganka Nath, Anurag Das, Jiahao Xie^†, Bernt Schiele (^†=corresponding author) arXiv, 2026 Paper / Code
	SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis Xinya Chen, Christopher Wewer, Jiahao Xie, Xinting Hu, Jan Eric Lenssen ICML, 2026 Paper / Project Page / Code
	CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts Olaf Dünkel, Artur Jesslen, Jiahao Xie, Christian Theobalt, Christian Rupprecht, Adam Kortylewski (=equal contribution) ICCV*, 2025 Paper / Project Page / Code
	Test-Time Visual In-Context Tuning Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele CVPR, 2025 Paper / Code
	MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation Jiahao Xie, Wei Li, Xiangtai Li, Ziwei Liu, Yew Soon Ong, Chen Change Loy IJCV, 2024 Paper / Code
	Correlational Image Modeling for Self-Supervised Visual Pre-Training Wei Li, Jiahao Xie, Chen Change Loy CVPR, 2023 Paper / Code
	Masked Frequency Modeling for Self-Supervised Visual Pre-Training Jiahao Xie, Wei Li, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy ICLR, 2023 Paper / Project Page / Code
	Delving into Inter-Image Invariance for Unsupervised Visual Representations Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy IJCV, 2022 Paper / Code
	UniVIP: A Unified Framework for Self-Supervised Visual Pre-training Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang CVPR, 2022 Paper
	Unsupervised Object-Level Representation Learning from Scene Images Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy NeurIPS, 2021 Paper / Project Page / Code
	Online Deep Clustering for Unsupervised Representation Learning Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy (=equal contribution) CVPR*, 2020 Paper / Code

Professional Activities

Area Chair: CVPR 2027, ECCV 2026
Conference Reviewer: CVPR 21-26, ICCV 21-25, ECCV 24, NeurIPS 22-25, ICLR 24-26, ICML 24/26, AAAI 21/26
Journal Reviewer: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV)

Selected Awards

ICLR Notable Reviewer, 2025
CVPR Outstanding Reviewer, 2023
CVPR Outstanding Reviewer, 2021
Champions of all four tracks in Facebook AI Self-Supervision Challenge, 2019

Modified from Jon Barron