| 2025 | ICLR | Formation of Representations in Neural Networks. | Liu Ziyin, Isaac L. Chuang, Tomer Galanti, Tomaso A. Poggio |
| 2025 | ICLR | Remove Symmetries to Control Model Expressivity and Improve Optimization. | Liu Ziyin, Yizhou Xu, Isaac L. Chuang |
| 2025 | ICML | Compositional Generalization via Forced Rendering of Disentangled Latents. | Qiyao Liang, Daoyuan Qian, Liu Ziyin, Ila R. Fiete |
| 2025 | ICML | Understanding the Emergence of Multimodal Representation Alignment. | Megan Tjandrasuwita, Chanakya Ekbote, Liu Ziyin, Paul Pu Liang |
| 2024 | ICML | Symmetry Induces Structure and Constraint of Learning. | Liu Ziyin |
| 2023 | ICLR | What shapes the loss landscape of self supervised learning? | Liu Ziyin, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka |
| 2023 | ICML | spred: Solving L1 Penalty with SGD. | Liu Ziyin, Zihao Wang |
| 2023 | ICML | On the Stepwise Nature of Self-Supervised Learning. | James B. Simon, Maksis Knutins, Liu Ziyin, Daniel Geisz, Abraham J. Fetterman, Joshua Albrecht |
| 2022 | ICLR | Strength of Minibatch Noise in SGD. | Liu Ziyin, Kangqiao Liu, Takashi Mori, Masahito Ueda |
| 2022 | ICLR | SGD Can Converge to Local Maxima. | Liu Ziyin, Botao Li, James B. Simon, Masahito Ueda |
| 2022 | ICML | Power-Law Escape Rate of SGD. | Takashi Mori, Liu Ziyin, Kangqiao Liu, Masahito Ueda |
| 2021 | ICML | Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent. | Kangqiao Liu, Liu Ziyin, Masahito Ueda |