Amazon Science

Pinned Repositories

alexa-teacher-models
Language:Python363 36 726
auto-cot
Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)
Language:Jupyter Notebook2k 16 8175
bigdetection
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
Language:Python399 7 1125
chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
Language:Python4.2k 37 106480
earth-forecasting-transformer
Official implementation of Earthformer
Language:Jupyter Notebook423 11 3369
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Language:Python4k 54 57331
patchcore-inspection
Language:Python1k 15 112201
RAGChecker
RAGChecker: A Fine-grained Framework For Diagnosing RAG
Language:Python1k 11 2784
RefChecker
RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.
Language:Python399 9 1643
siam-mot
SiamMOT: Siamese Multi-Object Tracking
Language:Python487 17 5660

Amazon Science's Repositories

amazon-science/chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
Language:Python4.2k 37 106480
amazon-science/JuLS
JuLS is a Julia Local Search solver that combines Constraint Based Local Search (CBLS) and Constraint Programming (CP)
Language:Julia167 2 33
amazon-science/SWE-PolyBench
SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents
Language:Python64 3 37
amazon-science/carbon-assessment-with-ml
CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
Language:Jupyter Notebook51 7 311
amazon-science/Cyber-Zero
Cyber-Zero: Training Cybersecurity Agents Without Runtime
Language:Python387
amazon-science/BartGraphSumm
Implementation of the paper "Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters (NAACL 2021)"
Language:Python27 7 62
amazon-science/Automatic-Table-to-Graph-Generation
Language:Python9 5 26
amazon-science/LatticeAlgorithms.jl
Algorithms to solve lattice problems in Julia
Language:Julia9 1 1
amazon-science/MILE
Language:Python9 0 00
amazon-science/dstc12-controllable-conversational-theme-detection
Data & code for DSTC12, Controllable Conversational Theme Detection track
Language:Python8 6 42
amazon-science/MigrationBench
Language:Python8 0 0
amazon-science/sumren
Language:Python8 1 01
amazon-science/fmcore
Running GenAI models at every scale, on every modality
Language:Python6 2 71
amazon-science/long-context-hallucination-detection
Language:Python6 1 01
amazon-science/causal-validation
Validate your causal models!
Language:Python5 1 42
amazon-science/wraval
WRAVAL helps in evaluating LLMs for writing assistant tasks like summarization, professional tone, witty tone, etc.
Language:Jupyter Notebook5 0 13
amazon-science/BOPRO-ICLR-2025
Language:Python4 2 01
amazon-science/collage
Language:Python3 2 11
amazon-science/Generative-vs-Discriminative-Classifiers
Language:Python3
amazon-science/nowcasting-recession-risk
Language:MATLAB3 0 00
amazon-science/CTF-Dojo
Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Language:Python11
amazon-science/MemInsight
Language:Python1 0 0
amazon-science/QualityFlow
Language:Python1 0 0
amazon-science/serializeEM
Language:Python1 1 0
amazon-science/FairGen
00
amazon-science/application-eval-data
2 1
amazon-science/DiverseAgentEntropy
Language:Python
amazon-science/LARCQ
Codes of LARCQ Paper (Interspeech 2025)
Language:Python0 0
amazon-science/MDSEval
Language:Jupyter Notebook
amazon-science/weak-supervision-for-few-shot-absa
Language:Python0 0