Douwe Kiela

papers

15,654

total citations

papers (13)

Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality

CVPR 2022arXiv

535

citations

True Few-Shot Learning with Language Models

NEURIPS 2021arXiv

497

citations

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

NEURIPS 2023arXiv

323

citations

Generative Representational Instruction Tuning

ICLR 2025arXiv

222

citations

DataPerf: Benchmarks for Data-Centric AI Development

NEURIPS 2023arXiv

129

citations

Human-Adversarial Visual Question Answering

NEURIPS 2021arXiv

citations

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking

NEURIPS 2021arXiv

citations

Learning Optimal Representations with the Decodable Information Bottleneck

NEURIPS 2020arXiv

citations

Great Models Think Alike and this Undermines AI Oversight

ICML 2025arXiv

citations

Douwe Kiela

papers (13)

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

FLAVA: A Foundational Language and Vision Alignment Model

Model Alignment as Prospect Theoretic Optimization

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality

True Few-Shot Learning with Language Models

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Generative Representational Instruction Tuning

DataPerf: Benchmarks for Data-Centric AI Development

Human-Adversarial Visual Question Answering

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking

Learning Optimal Representations with the Decodable Information Bottleneck

Great Models Think Alike and this Undermines AI Oversight

papers (13)

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

FLAVA: A Foundational Language and Vision Alignment Model

Model Alignment as Prospect Theoretic Optimization

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality

True Few-Shot Learning with Language Models

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Generative Representational Instruction Tuning

DataPerf: Benchmarks for Data-Centric AI Development

Human-Adversarial Visual Question Answering

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking

Learning Optimal Representations with the Decodable Information Bottleneck

Great Models Think Alike and this Undermines AI Oversight