Fei Sha

Graders Should Cheat: Privileged Information Enables Expert-Level Automated Evaluations EMNLP 2025 A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models NAACL 2024 DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems ICML 2024 The Impact of Depth on Compositional Generalization in Transformer Language Models NAACL 2024 V2Meow: Meowing to the Visual Beat via Video-to-Music Generation AAAI 2024 Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models NeurIPS 2023 Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories ICCV 2023 Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems ICLR 2023 FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference ACL 2023 Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations NeurIPS 2023 Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute ICML 2023 User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems ICML 2023 ALMA: Hierarchical Learning for Composite Multi-Agent Tasks NeurIPS 2022 Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing EMNLP 2022 Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing COLING 2022 Improving Compositional Generalization with Latent Structure and Data Augmentation NAACL 2022 Mention Memory: incorporating textual knowledge into Transformers through entity mention attention ICLR 2022 Policy Learning and Evaluation with Randomized Quasi-Monte Carlo AISTATS 2022 Possibility Before Utility: Learning And Using Hierarchical Affordances ICLR 2022 DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections EACL 2021 Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning ICML 2021 ReadTwice: Reading Very Large Documents with Memories NAACL 2021 Systematic Generalization on gSCAN: What is Nearly Solved and What is Next? EMNLP 2021 Visually Grounded Concept Composition EMNLP 2021 When MAML Can Adapt Fast and How to Assist When It Cannot AISTATS 2021 Amortized Inference of Variational Bounds for Learning Noisy-OR AISTATS 2020 BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps ACL 2020 Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions CVPR 2020 Learning to Represent Image and Text with Denotation Graph EMNLP 2020 Actor-Attention-Critic for Multi-Agent Reinforcement Learning ICML 2019 Hyper-parameter Tuning under a Budget Constraint IJCAI 2019 Kernel Approximation Methods for Speech Recognition JMLR 2019 Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner CoNLL 2018 A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images EMNLP 2018 Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets NAACL 2018 Cross-Dataset Adaptation for Visual Question Answering CVPR 2018 Cross-Modal and Hierarchical Modeling of Video and Text ECCV 2018 Learning Answer Embeddings for Visual Question Answering CVPR 2018 Multi-Task Learning for Sequence Tagging: An Empirical Study COLING 2018 Retrospective Encoders for Video Summarization ECCV 2018 Robust Active Label Correction AISTATS 2018 Synthesized Policies for Transfer and Adaptation across Tasks and Environments NeurIPS 2018 An Empirical Study on The Properties of Random Bases for Kernel Methods NeurIPS 2017 FastMask: Segment Multi-Scale Object Candidates in One Shot CVPR 2017 Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning ICCV 2017 Summary Transfer: Exemplar-Based Subset Selection for Video Summarization CVPR 2016 Supervised Word Mover's Distance NeurIPS 2016 Synthesized Classifiers for Zero-Shot Learning CVPR 2016 Exponential Integration for Hamiltonian Monte Carlo ICML 2015 Marginalizing Stacked Linear Denoising Autoencoders JMLR 2015 Similarity Learning for High-Dimensional Sparse Data AISTATS 2015 Decorrelating Semantic Visual Attributes by Resisting the Urge to Share CVPR 2014 Demystifying Information-Theoretic Clustering ICML 2014 Diverse Sequential Subset Selection for Supervised Video Summarization NeurIPS 2014 Marginalized Denoising Auto-encoders for Nonlinear Representations ICML 2014 Two-Stage Metric Learning ICML 2014 Analogy-preserving Semantic Embedding for Visual Object Categorization ICML 2013 Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation ICML 2013 Deformable Spatial Pyramid Matching for Fast Dense Correspondences CVPR 2013 Reshaping Visual Datasets for Domain Adaptation NeurIPS 2013 Similarity Component Analysis NeurIPS 2013 Non-linear Metric Learning NeurIPS 2012 Semantic Kernel Forests from Multiple Taxonomies NeurIPS 2012 Information Theoretical Clustering via Semidefinite Programming AISTATS 2011 Learning a Tree of Metrics with Disjoint Visual Features NeurIPS 2011 Locally Linear Denoising on Image Manifolds AISTATS 2010 Unsupervised Kernel Dimension Reduction NeurIPS 2010 DiscLDA: Discriminative Learning for Dimensionality Reduction and Classification NeurIPS 2008 Graph Laplacian Regularization for Large-Scale Semidefinite Programming NeurIPS 2006 Large Margin Hidden Markov Models for Automatic Speech Recognition NeurIPS 2006 Shallow Parsing with Conditional Random Fields NAACL 2003