| 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 |
| 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 | ICCV | Learning to Inference Adaptively for Multimodal Large Language Models. | Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee, Saurabh Bagchi, Somali Chaterji, Yingyu Liang, Yin Li |
| 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 | Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection. | Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha |
| 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 | Stratified Adversarial Robustness with Rejection. | Jiefeng Chen, Jayaram Raghuram, Jihye Choi, 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 | Towards Evaluating the Robustness of Neural Networks Learned by Transduction. | Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, Somesh Jha |
| 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 |
| 2021 | EACL | A New View of Multi-modal Language Analysis: Audio and Video Features as Text "Styles". | Zhongkai Sun, Prathusha Kameswara Sarma, Yingyu Liang, William A. Sethares |
| 2020 | AAAI | Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis. | Zhongkai Sun, Prathusha Kameswara Sarma, William A. Sethares, Yingyu Liang |
| 2020 | AISTATS | Sketching Transformed Matrices with Applications to Natural Language Processing. | Yingyu Liang, Zhao Song, Mengdi Wang, Lin Yang, Xin Yang |
| 2020 | AISTATS | Learning Entangled Single-Sample Distributions via Iterative Trimming. | Hui Yuan, Yingyu Liang |
| 2020 | CIKM | Can Adversarial Weight Perturbations Inject Neural Backdoors. | Siddhant Garg, Adarsh Kumar, Vibhor Goel, Yingyu Liang |
| 2020 | COLT | Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model. | Yingyu Liang, Hui Yuan |
| 2020 | EMNLP | PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding. | Jinman Zhao, Shawn Zhong, Xiaomin Zhang, Yingyu Liang |
| 2020 | ICLR | Gradients as Features for Deep Representation Learning. | Fangzhou Mu, Yingyu Liang, Yin Li |
| 2020 | IJCNLP | Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer. | Siddhant Garg, Rohit Kumar Sharma, Yingyu Liang |
| 2019 | AAAI | Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning. | Shengchao Liu, Yingyu Liang, Anthony Gitter |
| 2019 | AISTATS | Recovery Guarantees For Quadratic Tensors With Sparse Observations. | Hongyang Zhang, Vatsal Sharan, Moses Charikar, Yingyu Liang |
| 2019 | EMNLP | Shallow Domain Adaptive Embeddings for Sentiment Analysis. | Prathusha Kameswara Sarma, Yingyu Liang, William A. Sethares |
| 2018 | ACL | A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. | Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora |
| 2018 | ACL | Domain Adapted Word Embeddings for Improved Sentiment Classification. | Prathusha Kameswara Sarma, Yingyu Liang, Bill Sethares |
| 2018 | COLT | Learning Mixtures of Linear Regressions with Nearly Optimal Complexity. | Yuanzhi Li, Yingyu Liang |
| 2018 | EMNLP | Generalizing Word Embeddings using Bag of Subwords. | Jinman Zhao, Sidharth Mudgal, Yingyu Liang |
| 2017 | AISTATS | Diverse Neural Network Learns True Target Functions. | Bo Xie, Yingyu Liang, Le Song |
| 2017 | ICLR | A Simple but Tough-to-Beat Baseline for Sentence Embeddings. | Sanjeev Arora, Yingyu Liang, Tengyu Ma |
| 2017 | ICML | Generalization and Equilibrium in Generative Adversarial Nets (GANs). | Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang |
| 2017 | ICML | Differentially Private Clustering in High-Dimensional Euclidean Spaces. | Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, Hongyang Zhang |
| 2017 | ICML | Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations. | Yuanzhi Li, Yingyu Liang |
| 2016 | ESANN | Learning in indefinite proximity spaces - recent trends. | Frank-Michael Schleif, Peter Tio, Yingyu Liang |
| 2016 | ICML | Recovery guarantee of weighted low-rank approximation via alternating minimization. | Yuanzhi Li, Yingyu Liang, Andrej Risteski |
| 2016 | KDD | Communication Efficient Distributed Kernel Principal Component Analysis. | Maria-Florina Balcan, Yingyu Liang, Le Song, David P. Woodruff, Bo Xie |
| 2015 | SDM | A Distributed Frank-Wolfe Algorithm for Communication-Efficient Sparse Learning. | Aurlien Bellet, Yingyu Liang, Alireza Bagheri Garakani, Maria-Florina Balcan, Fei Sha |
| 2014 | ICML | Influence Function Learning in Information Diffusion Networks. | Nan Du, Yingyu Liang, Maria-Florina Balcan, Le Song |
| 2013 | ICML | Efficient Semi-supervised and Active Learning of Disjunctions. | Nina Balcan, Christopher Berlind, Steven Ehrlich, Yingyu Liang |
| 2012 | ICALP | Clustering under Perturbation Resilience. | Maria-Florina Balcan, Yingyu Liang |
| 2010 | MMM | Learning Vocabulary-Based Hashing with AdaBoost. | Yingyu Liang, Jianmin Li, Bo Zhang |