Pinned Repositories
alexa-teacher-models
auto-cot
Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)
bigdetection
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
chronos-forecasting
Chronos: Pretrained Models for Probabilistic Time Series Forecasting
earth-forecasting-transformer
Official implementation of Earthformer
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
patchcore-inspection
RAGChecker
RAGChecker: A Fine-grained Framework For Diagnosing RAG
RefChecker
RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.
siam-mot
SiamMOT: Siamese Multi-Object Tracking
Amazon Science's Repositories
amazon-science/chronos-forecasting
Chronos: Pretrained Models for Probabilistic Time Series Forecasting
amazon-science/RAGChecker
RAGChecker: A Fine-grained Framework For Diagnosing RAG
amazon-science/alexa-teacher-models
amazon-science/ReFinED
ReFinED is an efficient and accurate entity linking (EL) system.
amazon-science/azcausal
Causal Inference in Python
amazon-science/carbon-assessment-with-ml
CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
amazon-science/AdaSlot
Official implementation of the CVPR'24 paper [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number]
amazon-science/PAE
amazon-science/llm-code-preference
Training and Benchmarking LLMs for Code Preference.
amazon-science/SetLexSem-Challenge
amazon-science/factual-confidence-of-llms
Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"
amazon-science/synthesizrr
Synthesizing realistic and diverse text-datasets from augmented LLMs
amazon-science/llm-rank-pruning
LLM-Rank: A graph theoretical approach to structured pruning of large language models based on weighted Page Rank centrality as introduced by the related paper.
amazon-science/MILE
amazon-science/dataflow-evaluation-toolkit
amazon-science/job-posting-structure
Extract structured information from job postings.
amazon-science/snakes_and_ladders_adapting_the_surface_code_to_defects
Tools to build STIM circuits for the rotated surface code in presence of non-operational qubits and gates.
amazon-science/icbs
Iterative Combinatorial Brain Surgeon (iCBS)
amazon-science/LatticeAlgorithms.jl
Algorithms to solve lattice problems in Julia
amazon-science/NARVL
amazon-science/aws-research-science
amazon-science/entity-salience-short-documents
A dataset for evaluating entity salience prediction on extremely short documents
amazon-science/llm-pieval
amazon-science/SigExt
Implementation of the EMNLP'24 paper: Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
amazon-science/VideoLISA
amazon-science/BeyondCorrelation
Implementation of the paper: Beyond Correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
amazon-science/conversational-ambiguous-unanswerable-text2sql
amazon-science/llm-asymptotic-decoding
amazon-science/llm-qmia
amazon-science/PIXELS
Official implementation for the AAAI2025 paper "PIXELS - Progressive Image Xemplar-based Editing with Latent Surgery"