| 2026 | ACL | Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction. | Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen, Yingyu Liang, Shafiq Joty |
| 2026 | WACV | T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation. | Yubin Chen, Xuyang Guo, Zhenmei Shi, Zhao Song, Jiahao Zhang |
| 2025 | AISTATS | Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent. | Bo Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song |
| 2025 | AISTATS | Looped ReLU MLPs May Be All You Need as Practical Programmable Computers. | Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou |
| 2025 | AISTATS | When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time? | Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song |
| 2025 | AISTATS | Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs. | Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Tianyi Zhou |
| 2025 | CIKM | Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling. | Yang Cao, Bo Chen, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan |
| 2025 | EMNLP | Circuit Complexity Bounds for RoPE-based Transformer Architecture. | Bo Chen, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Jiahao Zhang |
| 2025 | EMNLP | Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers. | Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Zhuoyan Xu, Jiale Zhao, Zhen Zhuang |
| 2025 | EMNLP | Towards Infinite-Long Prefix in Transformer. | Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang |
| 2025 | ICCV | Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective. | Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Yufa Zhou |
| 2025 | ICLR | Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix. | Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou |
| 2025 | ICML | Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities. | Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song |
| 2025 | ICML | Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies. | Yuefan Cao, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Jiahao Zhang |
| 2025 | WACV | Differential Privacy Mechanisms in Neural Tangent Kernel Regression. | Jiuxiang Gu, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song |
| 2025 | UAI | NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism. | Bo Chen, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Xugang Ye |
| 2024 | ICLR | Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning. | Zhuoyan Xu, Zhenmei Shi, Junyi Wei, Fangzhou Mu, Yin Li, Yingyu Liang |
| 2024 | ICML | Why Larger Language Models Do In-context Learning Differently? | Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang |
| 2023 | ICLR | The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning. | Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha |
| 2023 | ICML | When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis. | Yiyou Sun, Zhenmei Shi, Yingyu Liang, Yixuan Li |
| 2022 | ICLR | A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features. | Zhenmei Shi, Junyi Wei, Yingyu Liang |
| 2022 | WACV | Deep Online Fused Video Stabilization. | Zhenmei Shi, Fuhao Shi, Wei-Sheng Lai, Chia-Kai Liang, Yingyu Liang |