Yingyu Liang

Learning to Inference Adaptively for Multimodal Large Language Models ICCV 2025 Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025 Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers EMNLP 2025 Circuit Complexity Bounds for RoPE-based Transformer Architecture EMNLP 2025 Towards Infinite-Long Prefix in Transformer EMNLP 2025 Differential Privacy Mechanisms in Neural Tangent Kernel Regression WACV 2025 Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix ICLR 2025 NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism UAI 2025 Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities ICML 2025 Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies ICML 2025 Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs AISTATS 2025 Looped ReLU MLPs May Be All You Need as Practical Programmable Computers AISTATS 2025 When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time? AISTATS 2025 Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent AISTATS 2025 Why Larger Language Models Do In-context Learning Differently? ICML 2024 Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection ICML 2024 Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning ICLR 2024 Stratified Adversarial Robustness with Rejection ICML 2023 The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning ICLR 2023 What Knowledge Gets Distilled in Knowledge Distillation? NIPS 2023 Provable Guarantees for Neural Networks via Gradient Feature Learning NIPS 2023 When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis ICML 2023 A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features ICLR 2022 Towards Evaluating the Robustness of Neural Networks Learned by Transduction ICLR 2022 Deep Online Fused Video Stabilization WACV 2022 A New View of Multi-modal Language Analysis: Audio and Video Features as Text “Styles” EACL 2021 Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles NIPS 2021 Gradients as Features for Deep Representation Learning ICLR 2020 Functional Regularization for Representation Learning: A Unified Theoretical Perspective NIPS 2020 Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis AAAI 2020 Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer AACL 2020 Sketching Transformed Matrices with Applications to Natural Language Processing AISTATS 2020 Learning Entangled Single-Sample Distributions via Iterative Trimming AISTATS 2020 Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model COLT 2020 PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding EMNLP 2020 Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning AAAI 2019 Shallow Domain Adaptive Embeddings for Sentiment Analysis IJCNLP 2019 Recovery Guarantees For Quadratic Tensors With Sparse Observations AISTATS 2019 Robust Attribution Regularization NIPS 2019 Non-Convex Matrix Completion and Related Problems via Strong Duality JMLR 2019 Shallow Domain Adaptive Embeddings for Sentiment Analysis EMNLP 2019 Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers NIPS 2019 N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules NIPS 2019 Learning Mixtures of Linear Regressions with Nearly Optimal Complexity COLT 2018 Generalizing Word Embeddings using Bag of Subwords EMNLP 2018 A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors ACL 2018 Domain Adapted Word Embeddings for Improved Sentiment Classification ACL 2018 Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data NIPS 2018 Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations ICML 2017 Diverse Neural Network Learns True Target Functions AISTATS 2017 Generalization and Equilibrium in Generative Adversarial Nets (GANs) ICML 2017 Differentially Private Clustering in High-Dimensional Euclidean Spaces ICML 2017 Scalable Influence Maximization for Multiple Products in Continuous-Time Diffusion Networks JMLR 2017 Recovery guarantee of weighted low-rank approximation via alternating minimization ICML 2016 Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates NIPS 2016 Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients NIPS 2015 Scalable Kernel Methods via Doubly Stochastic Gradients NIPS 2014 Robust Hierarchical Clustering JMLR 2014 Influence Function Learning in Information Diffusion Networks ICML 2014 Improved Distributed Principal Component Analysis NIPS 2014 Learning Time-Varying Coverage Functions NIPS 2014 Distributed $k$-means and $k$-median Clustering on General Topologies NIPS 2013 Efficient Semi-supervised and Active Learning of Disjunctions ICML 2013