Amazon Science

All

400 repositories

h3-indexer
Public
The h3-indexer is an open source package for indexing geospatial data using PySpark, Apache Sedona and the H3 hierarchical spatial indexing system. The h3-indexer maps any number of vector-type geospatial data sets to H3 grids for efficient spatial analysis and querying.
geospatial
Python
•
Apache License 2.0
•3•6•0•0•Updated Aug 19, 2025Aug 19, 2025
LatticeAlgorithms.jl
Public
Algorithms to solve lattice problems in Julia
lattice lattice-reduction gottesman-kitaev-preskill-code
Julia
•
Apache License 2.0
•0•8•1•0•Updated Aug 16, 2025Aug 16, 2025
cceval
Public
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)
Python
•
Apache License 2.0
•23•153•4•0•Updated Aug 15, 2025Aug 15, 2025
object-centric-learning-framework
Public
Python
•
Apache License 2.0
•6•80•7•1•Updated Aug 13, 2025Aug 13, 2025
generalized-fairness-metrics
Public
Jupyter Notebook
•
Apache License 2.0
•3•14•0•12•Updated Aug 12, 2025Aug 12, 2025
fair-pca
Public
Python
•
Apache License 2.0
•1•6•0•3•Updated Aug 12, 2025Aug 12, 2025
cocomic
Public
CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context
Python
•
Apache License 2.0
•4•17•1•10•Updated Aug 12, 2025Aug 12, 2025
supervised-intent-clustering
Public
This is a package to fine-tune language models in order to create clustering-friendly embeddings.
clustering embeddings sentence-transformers
Python
•
Other
•0•3•1•1•Updated Aug 12, 2025Aug 12, 2025
carbon-assessment-with-ml
Public
CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
Jupyter Notebook
•
Apache License 2.0
•10•50•0•1•Updated Aug 6, 2025Aug 6, 2025
serializeEM
Public
Python
•
Apache License 2.0
•0•1•0•2•Updated Aug 6, 2025Aug 6, 2025
llm-asymptotic-decoding
Public
Jupyter Notebook
•
Other
•0•10•0•8•Updated Aug 6, 2025Aug 6, 2025
AnoLLM-large-language-models-for-tabular-anomaly-detection
Public
Python
•
Apache License 2.0
•1•16•4•1•Updated Aug 6, 2025Aug 6, 2025
wraval
Public
WRAVAL helps in evaluating LLMs for writing assistant tasks like summarization, professional tone, witty tone, etc.
Jupyter Notebook
•2•5•0•10•Updated Aug 6, 2025Aug 6, 2025
controllable-readability-summarization
Public
Generating Summaries with Controllable Readability Levels (EMNLP 2023)
readability generation summarization controllable
Python
•
Other
•5•14•1•1•Updated Aug 6, 2025Aug 6, 2025
CiteEval
Public
Official repository for CiteEval: Principle-Driven Citation Evaluation for Source Attribution
Python
•
Other
•2•4•0•2•Updated Aug 6, 2025Aug 6, 2025
THRONE
Public
Code release for THRONE, a CVPR 2024 paper on measuring object hallucinations in LVLM generated text.
benchmark hallucination hallucinations large-language-models large-language-model vision-language-model large-vision-language-model large-vision-language-models cvpr2024 hallucination-evaluation
Python
•
Other
•0•3•1•2•Updated Aug 6, 2025Aug 6, 2025
avgen-eval-toolkit
Public
Python
•
Apache License 2.0
•4•11•0•4•Updated Aug 6, 2025Aug 6, 2025
dstc12-controllable-conversational-theme-detection
Public
Data & code for DSTC12, Controllable Conversational Theme Detection track
nlp theme challenge machine-learning natural-language-processing deep-learning neural-network dialog intent conversational-ai
Python
•
Other
•2•8•2•2•Updated Aug 6, 2025Aug 6, 2025
chronos-forecasting
Public
Chronos: Pretrained Models for Probabilistic Time Series Forecasting
machine-learning timeseries time-series transformers artificial-intelligence forecasting pretrained-models time-series-forecasting huggingface huggingface-transformers
Python
•
Apache License 2.0
•412•3.5k•20•1•Updated Aug 5, 2025Aug 5, 2025
Cyber-Zero
Public
Cyber-Zero: Training Cybersecurity Agents Without Runtime
agent cybersecurity ctf offensive-security large-language-models llm llm-training
Python
•
Other
•2•8•1•0•Updated Aug 5, 2025Aug 5, 2025
document-haystack
Public
Python
•
Other
•1•1•0•0•Updated Jul 30, 2025Jul 30, 2025
Query-Conditioned-NLI
Public
Python
•
Other
•0•0•0•0•Updated Jul 28, 2025Jul 28, 2025
application-eval-data
Public
Other
•0•0•0•0•Updated Jul 25, 2025Jul 25, 2025
CSR-Bench
Public
CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories
naacl naacl-paper llm-agents llm-benchmarking naacl2025
Python
•1•2•1•0•Updated Jul 23, 2025Jul 23, 2025
nowcasting-recession-risk
Public
MATLAB
•
Apache License 2.0
•1•1•0•0•Updated Jul 23, 2025Jul 23, 2025
calfwsat
Public
C
•
MIT No Attribution
•0•0•0•0•Updated Jul 22, 2025Jul 22, 2025
TurboFuzzLLM
Public
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
jailbreaking ai-safety red-teaming guardrails responsible-ai large-language-models
Python
•
Apache License 2.0
•2•14•0•0•Updated Jul 21, 2025Jul 21, 2025
MixtureOfAdapters
Public
Jupyter Notebook
•
Apache License 2.0
•0•0•0•0•Updated Jul 18, 2025Jul 18, 2025
SWE-PolyBench
Public
SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents
Python
•
MIT License
•5•58•1•0•Updated Jul 16, 2025Jul 16, 2025
fmcore
Public
Running GenAI models at every scale, on every modality
machine-learning natural-language-processing computer-vision artificial-intelligence scientific-computing multi-modal ai-research foundation-models genai
Python
•
Apache License 2.0
•1•6•5•3•Updated Jul 11, 2025Jul 11, 2025