b'Fei Sha'

research

∙ 08/29/2023

WeatherBench 2: A benchmark for the next generation of data-driven global weather models

WeatherBench 2 is an update to the global, medium-range (1-14 day) weath...

0 Stephan Rasp, et al. ∙

research

∙ 06/24/2023

SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models

Probabilistic forecasting is crucial to decision-making under uncertaint...

0 Lizao Li, et al. ∙

research

∙ 06/15/2023

Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories

We propose Encyclopedic-VQA, a large scale visual question answering (VQ...

0 Thomas Mensink, et al. ∙

research

∙ 06/13/2023

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

Diffusion models are a class of probabilistic generative models that hav...

0 Marc Finzi, et al. ∙

research

∙ 05/24/2023

Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models

We introduce a two-stage probabilistic framework for statistical downsca...

0 Zhong Yi Wan, et al. ∙

research

∙ 05/11/2023

V2Meow: Meowing to the Visual Beat via Music Generation

Generating high quality music that complements the visual content of a v...

0 Kun Su, et al. ∙

research

∙ 02/12/2023

Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL

We study how to transfer representations pretrained on source tasks to t...

0 Sébastien M. R. Arnold, et al. ∙

research

∙ 01/25/2023

Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute

Retrieval-augmented language models such as Fusion-in-Decoder are powerf...

0 Michiel de Jong, et al. ∙

research

∙ 01/25/2023

Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems

We present a data-driven, space-time continuous framework to learn surro...

0 Zhong Yi Wan, et al. ∙

research

∙ 12/15/2022

FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference

Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model...

0 Michiel de Jong, et al. ∙

research

∙ 09/29/2022

Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing

A common recent approach to semantic parsing augments sequence-to-sequen...

0 Yury Zemlyanskiy, et al. ∙

research

∙ 05/27/2022

ALMA: Hierarchical Learning for Composite Multi-Agent Tasks

Despite significant progress on multi-agent reinforcement learning (MARL...

0 Shariq Iqbal, et al. ∙

research

∙ 05/24/2022

Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing

Despite their strong performance on many tasks, pre-trained language mod...

0 Linlu Qiu, et al. ∙

research

∙ 03/23/2022

Possibility Before Utility: Learning And Using Hierarchical Affordances

Reinforcement learning algorithms struggle on tasks with complex hierarc...

0 Robby Costales, et al. ∙

research

∙ 02/16/2022

Policy Learning and Evaluation with Randomized Quasi-Monte Carlo

Reinforcement learning constantly deals with hard integrals, for example...

0 Sébastien M. R. Arnold, et al. ∙

research

∙ 12/14/2021

Improving Compositional Generalization with Latent Structure and Data Augmentation

Generic unstructured neural networks have been shown to struggle on out-...

6 Linlu Qiu, et al. ∙

research

∙ 12/14/2021

Co-training Transformer with Videos and Images Improves Action Recognition

In learning action recognition, models are typically pre-trained on obje...

0 Bowen Zhang, et al. ∙

research

∙ 11/09/2021

Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks

Neural network models often generalize poorly to mismatched domains or d...

4 Wang Zhu, et al. ∙

research

∙ 10/28/2021

HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks

Many types of physics-informed neural network models have been proposed ...

0 Filipe de Avila Belbute-Peres, et al. ∙

research

∙ 10/12/2021

Mention Memory: incorporating textual knowledge into Transformers through entity mention attention

Natural language understanding tasks such as open-domain question answer...

0 Michiel de Jong, et al. ∙

research

∙ 09/29/2021

Visually Grounded Concept Composition

We investigate ways to compose complex concepts in texts from primitive ...

1 Bowen Zhang, et al. ∙

research

∙ 09/25/2021

Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?

We analyze the grounded SCAN (gSCAN) benchmark, which was recently propo...

8 Linlu Qiu, et al. ∙

research

∙ 05/10/2021

ReadTwice: Reading Very Large Documents with Memories

Knowledge-intensive tasks such as question answering often require assim...

0 Yury Zemlyanskiy, et al. ∙

research

∙ 04/15/2021

Embedding Adaptation is Still Needed for Few-Shot Learning

Constructing new and more challenging tasksets is a fruitful methodology...

0 Sébastien M. R. Arnold, et al. ∙

research

∙ 02/26/2021

DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections

This paper explores learning rich self-supervised entity representations...

19 Yury Zemlyanskiy, et al. ∙

research

∙ 11/18/2020

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus

Identifying a short segment in a long video that semantically matches a ...

0 Bowen Zhang, et al. ∙

research

∙ 10/23/2020

AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization

Summarization is the task of compressing source document(s) into coheren...

0 Sayali Kulkarni, et al. ∙

research

∙ 10/06/2020

Learning to Represent Image and Text with Denotation Graph

Learning to fuse vision and language information and representing them i...

0 Bowen Zhang, et al. ∙

research

∙ 07/18/2020

Drinking from a Firehose: Continual Learning with Web-scale Natural Language

Continual learning systems will interact with humans, with each other, a...

14 Hexiang Hu, et al. ∙

research

∙ 06/13/2020

Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation

Uncertainty quantification is an important research area in machine lear...

31 Zhiyun Lu, et al. ∙

research

∙ 06/07/2020

AI-QMIX: Attention and Imagination for Dynamic Multi-Agent Reinforcement Learning

Real world multi-agent tasks often involve varying types and quantities ...

9 Shariq Iqbal, et al. ∙

research

∙ 05/10/2020

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps

Learning to follow instructions is of fundamental importance to autonomo...

18 Wang Zhu, et al. ∙

research

∙ 01/13/2020

Visual Storytelling via Predicting Anchor Word Embeddings in the Stories

We propose a learning model for the task of visual storytelling. The mai...

6 Bowen Zhang, et al. ∙

research

∙ 10/30/2019

Decoupling Adaptation from Modeling with Meta-Optimizers for Meta Learning

Meta-learning methods, most notably Model-Agnostic Meta-Learning or MAML...

11 Sébastien M. R. Arnold, et al. ∙

research

∙ 08/19/2019

Topic Augmented Generator for Abstractive Summarization

Steady progress has been made in abstractive summarization with attentio...

2 Melissa Ailem, et al. ∙

research

∙ 06/17/2019

Neural Theorem Provers Do Not Learn Rules Without Exploration

Neural symbolic processing aims to combine the generalization of logical...

1 Michiel de Jong, et al. ∙

research

∙ 06/07/2019

Learning Classifier Synthesis for Generalized Few-Shot Learning

Visual recognition in real-world requires handling long-tailed and even ...

9 Han-Jia Ye, et al. ∙

research

∙ 06/06/2019

Amortized Inference of Variational Bounds for Learning Noisy-OR

Classical approaches for approximate inference depend on cleverly design...

0 Yiming Yan, et al. ∙

research

∙ 05/28/2019

Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning

Sparse rewards are one of the most important challenges in reinforcement...

7 Shariq Iqbal, et al. ∙

research

∙ 04/05/2019

Synthesized Policies for Transfer and Adaptation across Tasks and Environments

The ability to transfer in reinforcement learning is key towards buildin...

6 Hexiang Hu, et al. ∙

research

∙ 02/01/2019

Hyper-parameter Tuning under a Budget Constraint

We study a budgeted hyper-parameter tuning problem, where we optimize th...

16 Zhiyun Lu, et al. ∙

research

∙ 12/16/2018

Classifier and Exemplar Synthesis for Zero-Shot Learning

Zero-shot learning (ZSL) enables solving a task without the need to see ...

0 Soravit Changpinyo, et al. ∙

research

∙ 12/10/2018

Learning Embedding Adaptation for Few-Shot Learning

Learning with limited data is a key challenge for visual recognition. Fe...

18 Han-Jia Ye, et al. ∙

research

∙ 10/16/2018

Cross-Modal and Hierarchical Modeling of Video and Text

Visual data and text data are composed of information at multiple granul...

0 Bowen Zhang, et al. ∙

research

∙ 10/05/2018

Actor-Attention-Critic for Multi-Agent Reinforcement Learning

Reinforcement learning in multi-agent scenarios is important for real-wo...

6 Shariq Iqbal, et al. ∙

research

∙ 08/21/2018

Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner

There have been several attempts to define a plausible motivation for a ...

4 Yury Zemlyanskiy, et al. ∙

research

∙ 08/13/2018

Multi-Task Learning for Sequence Tagging: An Empirical Study

We study three general multi-task learning (MTL) approaches on 11 sequen...

0 Soravit Changpinyo, et al. ∙

research

∙ 06/10/2018

Cross-Dataset Adaptation for Visual Question Answering

We investigate the problem of cross-dataset adaptation for visual questi...

0 Wei-Lun Chao, et al. ∙

research

∙ 06/10/2018

Learning Answer Embeddings for Visual Question Answering

We propose a novel probabilistic model for visual question answering (Vi...

0 Hexiang Hu, et al. ∙

research

∙ 04/24/2017

Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets

Visual question answering (QA) has attracted a lot of attention lately, ...

0 Wei-Lun Chao, et al. ∙

Fei Sha

Featured Co-authors