Llama 2: Open Foundation and Fine-Tuned Chat Models

Hugo Touvron, Louis Martin, Kevin H. Stone, +65

arXiv (Cornell University)

Llm Fine-tuningChatbotEngineeringFine-tuned LlmsSpoken Dialog System +17

FLAVA: A Foundational Language And Vision Alignment Model

Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, +4

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

12-in-1: Multi-Task Vision and Language Representation Learning

Jiasen Lu, Vedanuj Goswami, Marcus Rohrbach, +2

Language Representation LearningEngineeringMachine LearningPsycholinguisticsLanguage Learning +14

No Language Left Behind: Scaling Human-Centered Machine Translation

Nllb Team, Marta R. Costa‐jussà, James H. Cross, +36

arXiv (Cornell University)

Translation StudiesArtificial IntelligenceEngineeringMachine LearningMultilingual Pretraining +16

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Douwe Kiela, Hamed Firooz, Aravind Mohan, +4

arXiv (Cornell University)

Hateful Memes ChallengeAbuse DetectionEngineeringMachine LearningMultimodal Learning +20

12-in-1: Multi-Task Vision and Language Representation Learning

Jiasen Lu, Vedanuj Goswami, Marcus Rohrbach, +2

arXiv (Cornell University)

Language Representation LearningEngineeringMachine LearningMultimodal LearningPsycholinguistics +14

FLAVA: A Foundational Language And Vision Alignment Model

Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, +4

arXiv (Cornell University)

Are we pretraining it right? Digging deeper into visio-linguistic pretraining

Amanpreet Singh, Vedanuj Goswami, Devi Parikh

arXiv (Cornell University)

MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation

Mohamed Anwar, Bowen Shi, Vedanuj Goswami, +3

Robust Speech-to-text TranslationHealth SciencesSpeech TranslationMultimodal TranslationSpeech Corpus +11

Human-Adversarial Visual Question Answering

Sasha Sheng, Amanpreet Singh, Vedanuj Goswami, +4

arXiv (Cornell University)

Artificial IntelligenceNatural Language ProcessingMultimodal LlmVqa V2Machine Vision +13