Publications (88)
Improving Compositional Generalization with Latent Structure and Data Augmentation
Linlu Qiu, Peter Shaw, Panupong Pasupat +4
Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation
Zhiyun Lu, Eugene Ie, Fei Sha
SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models
Lizao Li, Rob Carver, Ignacio Lopez-Gomez +2
Synthesized Classifiers for Zero-Shot Learning
Soravit Changpinyo, Wei-Lun Chao, Boqing Gong +1
When MAML Can Adapt Fast and How to Assist When It Cannot
Sébastien M. R. Arnold, Shariq Iqbal, Fei Sha
Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems
Zhong Yi Wan, Leonardo Zepeda-Núñez, Anudhyan Boral +1
Marginalized Denoising Autoencoders for Domain Adaptation
Minmin Chen, Zhixiang Xu, Kilian Weinberger +1
Possibility Before Utility: Learning And Using Hierarchical Affordances
Robby Costales, Shariq Iqbal, Fei Sha
Policy Learning and Evaluation with Randomized Quasi-Monte Carlo
Sebastien M. R. Arnold, Pierre L'Ecuyer, Liyu Chen +2
Dynamical-generative downscaling of climate model ensembles
Ignacio Lopez-Gomez, Zhong Yi Wan, Leonardo Zepeda-Núñez +3
A Distributed Frank-Wolfe Algorithm for Communication-Efficient Sparse Learning
Aurélien Bellet, Yingyu Liang, Alireza Bagheri Garakani +2
Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
Shantanu Shahane, Sheide Chammas, Deniz A. Bezgin +8
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald +4
Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing
Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie +5
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Marc Finzi, Anudhyan Boral, Andrew Gordon Wilson +2
Co-training Transformer with Videos and Images Improves Action Recognition
Bowen Zhang, Jiahui Yu, Christopher Fifty +4
Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation
Yuan Shi, Fei Sha
Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations
Anudhyan Boral, Zhong Yi Wan, Leonardo Zepeda-Núñez +5
Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task
Nan Ding, Sebastian Goodman, Fei Sha +1
A High-resolution Large-eddy Simulation Framework for Wildland Fire Predictions using TensorFlow
Qing Wang, Matthias Ihme, Rod R. Linn +6
Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks
Wang Zhu, Peter Shaw, Tal Linzen +1
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald +2
A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training data
Benedikt Barthel Sorensen, Leonardo Zepeda-Núñez, Ignacio Lopez-Gomez +4
Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
Yury Zemlyanskiy, Fei Sha
LabelBank: Revisiting Global Perspectives for Semantic Segmentation
Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou +2
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
Wang Zhu, Hexiang Hu, Jiacheng Chen +4
Demystifying Information-Theoretic Clustering
Greg Ver Steeg, Aram Galstyan, Fei Sha +1
A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition
Zhiyun Lu, Dong Guo, Alireza Bagheri Garakani +8
FastMask: Segment Multi-scale Object Candidates in One Shot
Hexiang Hu, Shiyi Lan, Yuning Jiang +2
Large-Margin Determinantal Point Processes
Boqing Gong, Wei-lun Chao, Kristen Grauman +1
Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?
Linlu Qiu, Hexiang Hu, Bowen Zhang +2
Recalling Holistic Information for Semantic Segmentation
Hexiang Hu, Zhiwei Deng, Guang-tong Zhou +2
Neural Theorem Provers Do Not Learn Rules Without Exploration
Michiel de Jong, Fei Sha
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
Shariq Iqbal, Fei Sha
Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets
Wei-Lun Chao, Hexiang Hu, Fei Sha
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference
Michiel de Jong, Yury Zemlyanskiy, Joshua Ainslie +4
Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL
Sébastien M. R. Arnold, Fei Sha
Regional climate risk assessment from climate models using probabilistic machine learning
Zhong Yi Wan, Ignacio Lopez-Gomez, Robert Carver +4
A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus
Bowen Zhang, Hexiang Hu, Joonseok Lee +5
DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections
Yury Zemlyanskiy, Sudeep Gandhe, Ruining He +5
Amortized Inference of Variational Bounds for Learning Noisy-OR
Yiming Yan, Melissa Ailem, Fei Sha
Hyper-parameter Tuning under a Budget Constraint
Zhiyun Lu, Chao-Kai Chiang, Fei Sha
Kernel Approximation Methods for Speech Recognition
Avner May, Alireza Bagheri Garakani, Zhiyun Lu +9
Cross-Modal and Hierarchical Modeling of Video and Text
Bowen Zhang, Hexiang Hu, Fei Sha
Learning Answer Embeddings for Visual Question Answering
Hexiang Hu, Wei-Lun Chao, Fei Sha
Attention Correctness in Neural Image Captioning
Chenxi Liu, Junhua Mao, Fei Sha +1
Sparse Compositional Metric Learning
Yuan Shi, Aurélien Bellet, Fei Sha
Topic Augmented Generator for Abstractive Summarization
Melissa Ailem, Bowen Zhang, Fei Sha
WeatherBench 2: A benchmark for the next generation of data-driven global weather models
Stephan Rasp, Stephan Hoyer, Alexander Merose +15
Synthesized Policies for Transfer and Adaptation across Tasks and Environments
Hexiang Hu, Liyu Chen, Boqing Gong +1
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
Han-Jia Ye, Hexiang Hu, De-Chuan Zhan +1
Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025
Nitya Thakkar, Mert Yuksekgonul, Jake Silberg +6
Learning Discriminative Metrics via Generative Models and Kernel Learning
Yuan Shi, Yung-Kyun Noh, Fei Sha +1
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
Thomas Mensink, Jasper Uijlings, Lluis Castrejon +6
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing
Linlu Qiu, Peter Shaw, Panupong Pasupat +5
Cross-Dataset Adaptation for Visual Question Answering
Wei-Lun Chao, Hexiang Hu, Fei Sha
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng +3
The Impact of Depth on Compositional Generalization in Transformer Language Models
Jackson Petty, Sjoerd van Steenkiste, Ishita Dasgupta +3
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
Zhiyun Lu, Avner May, Kuan Liu +8
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
Linlu Qiu, Fei Sha, Kelsey Allen +3
Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
Bowen Zhang, Hexiang Hu, Fei Sha
ALMA: Hierarchical Learning for Composite Multi-Agent Tasks
Shariq Iqbal, Robby Costales, Fei Sha
Generative AI for fast and accurate statistical computation of fluids
Roberto Molinaro, Samuel Lanthaler, Bogdan RaoniÄ +9
Multi-Task Learning for Sequence Tagging: An Empirical Study
Soravit Changpinyo, Hexiang Hu, Fei Sha
Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning
Shariq Iqbal, Fei Sha
Video Summarization with Long Short-term Memory
Ke Zhang, Wei-Lun Chao, Fei Sha +1
AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization
Sayali Kulkarni, Sheide Chammas, Wan Zhu +2
Learning to Represent Image and Text with Denotation Graph
Bowen Zhang, Hexiang Hu, Vihan Jain +2
Rapid Feature Learning with Stacked Linear Denoisers
Zhixiang Eddie Xu, Kilian Q. Weinberger, Fei Sha
Drinking from a Firehose: Continual Learning with Web-scale Natural Language
Hexiang Hu, Ozan Sener, Fei Sha +1
Classifier and Exemplar Synthesis for Zero-Shot Learning
Soravit Changpinyo, Wei-Lun Chao, Boqing Gong +1
Aligning where to see and what to tell: image caption with region-based attention and scene factorization
Junqi Jin, Kun Fu, Runpeng Cui +2
A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
Tiwalayo Eisape, MH Tessler, Ishita Dasgupta +3
Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
Soravit Changpinyo, Wei-Lun Chao, Fei Sha
DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
Yair Schiff, Zhong Yi Wan, Jeffrey B. Parker +4
Embedding Adaptation is Still Needed for Few-Shot Learning
Sébastien M. R. Arnold, Fei Sha
Two-Stage Metric Learning
Jun Wang, Ke Sun, Fei Sha +2
Graders should cheat: privileged information enables expert-level automated evaluations
Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding +3
Summary Transfer: Exemplar-based Subset Selection for Video Summarization
Ke Zhang, Wei-Lun Chao, Fei Sha +1
Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance
Xuchan Bao, Judith Yue Li, Zhong Yi Wan +5
HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
Filipe de Avila Belbute-Peres, Yi-fan Chen, Fei Sha
Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
Zhong Yi Wan, Ricardo Baptista, Yi-fan Chen +4
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
Wei-Lun Chao, Soravit Changpinyo, Boqing Gong +1
Similarity Learning for High-Dimensional Sparse Data
Kuan Liu, Aurélien Bellet, Fei Sha
V2Meow: Meowing to the Visual Beat via Video-to-Music Generation
Kun Su, Judith Yue Li, Qingqing Huang +8
An alternative text representation to TF-IDF and Bag-of-Words
Zhixiang, Xu, Minmin Chen +2
Visually Grounded Concept Composition
Bowen Zhang, Hexiang Hu, Linlu Qiu +2
ReadTwice: Reading Very Large Documents with Memories
Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong +3