On the Opportunities and Risks of Foundation Models

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, +109

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningAi FoundationAi Safety +18

A Simple but Tough-to-Beat Baseline for Sentence Embeddings

Sanjeev Arora, Yingyu Liang, Tengyu Ma

International Conference on Learning Representations

EngineeringMachine LearningCross-lingual RepresentationTextual EntailmentMultilingual Pretraining +14

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

Long Ma, Tengyu Ma, Risheng Liu, +2

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

EngineeringMachine LearningComputational IlluminationToward FastVisual Quality +15

A Latent Variable Model Approach to PMI-based Word Embeddings

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, +2

Transactions of the Association for Computational Linguistics

EngineeringSemanticsPmi-based Word EmbeddingsText MiningSemantic Word Embeddings +17

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Wenxuan Zhou, Kevin Huang, Tengyu Ma, +1

Proceedings of the AAAI Conference on Artificial Intelligence

Structured PredictionEngineeringAdaptive ThresholdingCorpus LinguisticsText Mining +16

Provable Bounds for Learning Some Deep Representations

Sanjeev Arora, Aditya Bhaskara, Rong Ge, +1

arXiv (Cornell University)

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Kaidi Cao, Colin Wei, Adrien Gaidon, +2

arXiv (Cornell University)

Semi-supervised LearningData AugmentationEngineeringMachine LearningData Science +13

MOPO: Model-based Offline Policy Optimization

Tianhe Yu, Garrett Thomas, Lantao Yu, +5

arXiv (Cornell University)

Mathematical ProgrammingArtificial IntelligenceEngineeringMachine LearningOffline Setting +18

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

Sanjeev Arora, Rong Ge, Yingyu Liang, +2

arXiv (Cornell University)

Artificial IntelligenceGenerative Adversarial NetsMachine LearningEngineeringGenerative Adversarial Network +9

SAM 2: Segment Anything in Images and Videos

Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, +15

arXiv (Cornell University)