Yue Song

I am a tenure-track Assistant Professor at the College of AI, Tsinghua University, leading the Structured Representation Learning Lab (SRL Lab). Our lab always welcomes applications from motivated interns, PhD students, and postdocs. Please email your CV and transcripts if you are interested.

My research lies at the Science—AI Interface, with a focus on Structured Representation Learning. Scientific data are inherently structured, shaped by geometric, temporal, and topological regularities rooted in the laws of physics, biology, and chemistry. I aim to develop machine learning models that explicitly encode these structures, leading to representations that are more interpretable, generalizable, and data-efficient.

My work is centered around three core perspectives:

Geometry — learning on structured, non-Euclidean spaces
Symmetry — modeling invariances and equivaraint transformations
Dynamics — incorporating dynamical systems principles for learning

A key philosophy of my research is the interplay between Science4AI and AI4Science. I incorporate inductive biases from scientific fields such as differential geometry, dynamical systems, numerical analysis, and computational neuroscience into machine learning models, while also using these structured models to better understand complex scientific phenomenan. Rather than focusing on specific tasks, I aim to develop general, principled methods that can be broadly applied across scientific domains.

Previously, I was a postdoctoral research associate in Computing & Mathematical Sciences at California Institute of Technology (Caltech), supervised by Yisong Yue, Pietro Perona, and Max Welling. I pursued doctoral studies under European Laboratory for Learning and Intelligent Systems (ELLIS), where I was affiliated with Multimedia and Human Understanding Group (MHUG) at University of Trento, Italy and Amsterdam Machine Learning Lab (AMLab) at University of Amsterdam, the Netherlands, advised by Nicu Sebe and Max Welling.

Prior to my Ph.D. studies, I received the B.Sc. cum laude from KU Leuven, Belgium and the joint M.Sc. summa cum laude from University of Trento, Italy and KTH Royal Institute of Technology, Sweden. Besides the technical master's degree, I also completed a minor in Innovation & Entrepreneurship from European Institute of Innovation and Technology (EIT Digital).

News

2025/12: Give an invited talk at the NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations.
2025/06: Our book Structured Representation Learning: From Homomorphisms and Disentanglement to Equivariance and Topography is now published with Springer Nature.
2025/04: Serve as Area Chair for NeurIPS 2025.
2024/02: Give CVPR and ECCV tutorials on disentangled&equivariant representation learning.

Selected Publications

	Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe International Conference on Learning Representations (ICLR), 2026 paper / code / bibtex
	Kuramoto Orientation Diffusion Models Yue Song, T. Anderson Keller, Sevan Brodjian, Takeru Miyato, Yisong Yue, Pietro Perona, Max Welling Advances in Neural Information Processing Systems (NeurIPS), 2025 paper / code / bibtex
	Is CLIP ideal? No. Can we fix it? Yes! Raphi Kang, Yue Song, Georgia Gkioxari, Pietro Perona International Conference on Computer Vision (ICCV), 2025 paper / code / bibtex
	Langevin Flows for Modeling Neural Latent Dynamics Yue Song, T. Anderson Keller, Yisong Yue, Pietro Perona, Max Welling Cognitive Computational Neuroscience (CCN), 2025 paper / code / bibtex
	Unsupervised Representation Learning from Sparse Transformation Analysis Yue Song, T. Anderson Keller, Yisong Yue, Pietro Perona, Max Welling IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025 paper / code / bibtex
	Gyrogroup Batch Normalization Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe International Conference on Learning Representations (ICLR), 2025 paper / code / bibtex
	RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection Yue Song, Wei Wang, Nicu Sebe IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024 paper / code / bibtex
	Navigating Chemical Space with Latent Flows Guanghao Wei, Yining Huang, Chenru Duan, Yue Song♦, Yuanqi Du♦ Advances in Neural Information Processing Systems (NeurIPS), 2024 paper / code / bibtex (♦ denotes equal supervision)
	RMLR: Extending Multinomial Logistic Regression into General Geometries Ziheng Chen, Yue Song♠, Rui Wang, Xiaojun Wu, Nicu Sebe Advances in Neural Information Processing Systems (NeurIPS), 2024 paper / code / bibtex (♠ denotes the corresponding author)
	A Lie Group Approach to Riemannian Batch Normalization Ziheng Chen, Yue Song♠, Yunmei Liu, Nicu Sebe International Conference on Learning Representations (ICLR), 2024 paper / code / bibtex (♠ denotes the corresponding author)
	Flow Factorized Representation Learning Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling Advances in Neural Information Processing Systems (NeurIPS), 2023 paper / code / bibtex
	Householder Projector for Unsupervised Latent Semantics Discovery Yue Song, Jichao Zhang, Nicu Sebe, Wei Wang International Conference on Computer Vision (ICCV), 2023 paper / code / bibtex
	Latent Traversals in Generative Models as Potential Flows Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling International Conference on Machine Learning (ICML), 2023 paper / code / bibtex
	Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers Bin Ren♣, Yahui Liu♣, Yue Song, Wei Bi, Rita Cucchiara, Nicu Sebe, Wei Wang International Conference on Computer Vision and Pattern Recognition (CVPR), 2023 paper / code / bibtex (♣ denotes co-first author)
	Orthogonal SVD Covariance Conditioning and Latent Disentanglement Yue Song, Nicu Sebe, Wei Wang IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022 paper / code / bibtex
	Fast Differentiable Matrix Square Root and Inverse Square Root Yue Song, Nicu Sebe, Wei Wang IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022 paper / code / bibtex
	RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection Yue Song, Nicu Sebe, Wei Wang Advances in Neural Information Processing Systems (NeurIPS), 2022 paper / code / slides / bibtex
	Batch-efficient EigenDecomposition for Small and Medium Matrices Yue Song, Nicu Sebe, Wei Wang European Conference on Computer Vision (ECCV), 2022 paper / code / slides / bibtex
	Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality Yue Song, Nicu Sebe, Wei Wang European Conference on Computer Vision (ECCV), 2022 paper / code / slides / bibtex
	On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition Yue Song, Nicu Sebe, Wei Wang IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022 paper / code / bibtex
	Fast Differentiable Matrix Square Root Yue Song, Nicu Sebe, Wei Wang International Conference on Learning Representations (ICLR), 2022, (Top 2.9%) paper / code / slides / bibtex
	Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? Yue Song, Nicu Sebe, Wei Wang International Conference on Computer Vision (ICCV), 2021 paper / supplementary / code / slides / poster / bibtex

Books

Structured Representation Learning: From Homomorphisms and Disentanglement to Equivariance and Topography
Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling
Springer Nature, 2025