https://github.com/amazon-science/street-reasoning
STREET: a multi-task and multi-step reasoning dataset
https://github.com/amazon-science/transformers-data-augmentation
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper
https://github.com/amazon-science/isometric-slt
Isometric Spoken Language Translation - Isometric SLT.
https://github.com/amazon-science/mintaka
Dataset from the paper "Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering" (COLING 2022)
https://github.com/amazon-science/recode
Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"
https://github.com/amazon-science/peft-design-spaces
Official implementation for "Parameter-Efficient Fine-Tuning Design Spaces"
https://github.com/amazon-science/self-supervised-amodal-video-object-segmentation
https://github.com/amazon-science/long-tailed-ood-detection
Official implementation for "Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition" (ICML'22 Long Presentation)
https://github.com/amazon-science/masked-diffusion-lm
Official implementation for the paper "A Cheaper and Better Diffusion Language Model with Soft-Masked Noise"
https://github.com/amazon-science/crossnorm-selfnorm
CrossNorm and SelfNorm for Generalization under Distribution Shifts, ICCV 2021
https://github.com/amazon-science/video-contrastive-learning
Video Contrastive Learning with Global Context, ICCVW 2021
https://github.com/amazon-science/exponential-moving-average-normalization
PyTorch implementation of EMAN for self-supervised and semi-supervised learning: https://arxiv.org/abs/2101.08482
https://github.com/amazon-science/embert
Code for EmBERT, a transformer model for embodied, language-guided visual task completion.
https://github.com/amazon-science/learning-to-generate-answers-with-citations
Repository for CaLF: Learning to Generate Answers with Citations via Factual Consistency Models. CaLF is a weakly-supervised fine-tuning method leveraging factual consistency models to improve the quality of generated answers and their citations. [ACL 2024]