Amazon Science's repositories
chronos-forecasting
Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
prompt-pretraining
Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"
RefChecker
RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.
long-short-term-transformer
[NeurIPS 2021 Spotlight] Official implementation of Long Short-Term Transformer for Online Action Detection
carbon-assessment-with-ml
CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
explainable-trajectory-prediction
Official code repository for the ICLR 2022 paper "You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction".
ope-learn-action-embeddings
Learning Action Embeddings for Off-Policy Evaluation
efficient-object-centric-representation-amodal-segmentation
[ICCV 2023]Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation
geographical-erasure-in-language-generation
Code accompanying 'Geographical Erasure in Language Generation', EMNLP '23 Findings.
ContextualUnderstanding-ContrastiveDecoding
Enhancing contextual understanding in large language models through contrastive decoding
mlp-rank-pruning
MLP-Rank: A graph theoretical approach to structured pruning of deep neural networks based on weighted Page Rank centrality as introduced by the related thesis.
handling-ontology-gaps-in-semantic-parsing
Repository of the paper Handling Hallucinations In Neural Semantic Parsing.
krylov-cubic-regularized-newton
Code for the AISTATS 2024 paper: "Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate".
MASSIVE-AMR
A dataset with more than 84,000 manually annotated AMR graphs for 1,685 information-seeking utterances mapped to 50+ typologically diverse languages.