Skip to content

@amazon-science Amazon Science

All

    Repositories list

    510 repositories

    • attune

      Public
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Oct 15, 2026Oct 15, 2026

    • ListQA-Eval

      Public
      Python
      •
      Other
      •0•2•0•0•Updated Oct 15, 2026Oct 15, 2026

    • MigrationBench

      Public
      Python
      •
      Apache License 2.0
      •11•18•0•5•Updated Oct 15, 2026Oct 15, 2026

    • LLMZero

      Public
      Python
      •
      Other
      •0•1•0•1•Updated Oct 15, 2026Oct 15, 2026

    • reskill

      Public
      An easy-to-configure and extensible veRL extension for agent RL training with skill co-evolution.
      Python
      •
      Apache License 2.0
      •2•26•1•4•Updated Oct 15, 2026Oct 15, 2026

    • dlm-scaling

      Public
      Code release for the paper Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models
      Python
      •
      Other
      •0•2•0•0•Updated Oct 14, 2026Oct 14, 2026

    • JAWS-Bench

      Public
      TypeScript
      •
      Other
      •0•4•0•27•Updated Oct 13, 2026Oct 13, 2026

    • evolveQA

      Public
      Other
      •0•0•0•0•Updated Oct 13, 2026Oct 13, 2026

    • hallucination-benchmark-trivialplus

      Public
      [ACL 2026 main] Long-Context Hallucination Detection Benchmark: Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, …
      Python
      •
      Other
      •1•4•0•0•Updated Oct 13, 2026Oct 13, 2026

    • PatientAgentBench

      Public
      PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents
      benchmarkevaluationagents
      benchmarkevaluationagentshealthcare-ai
      Python
      •
      Other
      •8•32•0•4•Updated Oct 13, 2026Oct 13, 2026

    • ATOD

      Public
      Python
      •
      Other
      •0•0•1•0•Updated Oct 13, 2026Oct 13, 2026

    • QASP

      Public
      0•0•0•0•Updated Oct 12, 2026Oct 12, 2026

    • NLPActiveTesting

      Public
      Repository containing the results of the paper: Select, Label, Evaluate: Active Testing in NLP, accepted at EMNLP 2026 Main Conference.
      nlpactive-testing
      nlpactive-testing
      Python
      •
      Other
      •0•0•0•2•Updated Oct 10, 2026Oct 10, 2026

    • barrier-free-synch-proof

      Public
      Lean
      •
      Other
      •1•0•0•0•Updated Oct 10, 2026Oct 10, 2026

    • Personalized-chat-interaction-autocomplete

      Public
      Python
      •
      Other
      •1•0•0•1•Updated Oct 10, 2026Oct 10, 2026

    • webie

      Public
      Dataset for web-scaled information extraction.
      nlpinformation-extractionrelation-extraction
      nlpinformation-extractionrelation-extractionentity-extractionnlp-dataset
      Python
      •
      Other
      •2•8•0•1•Updated Oct 9, 2026Oct 9, 2026

    • SpeechworthyLLMs

      Public
      HTML
      •2•4•1•5•Updated Oct 9, 2026Oct 9, 2026

    • whatfits

      Public
      Python
      •
      Other
      •0•0•0•0•Updated Oct 9, 2026Oct 9, 2026

    • ALoDLM

      Public
      Research code and optimized inference for ALoDLM: Adaptively Looped Diffusion Language Models.
      Python
      •
      Other
      •5•43•0•3•Updated Oct 8, 2026Oct 8, 2026

    • SpIDER

      Public
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Oct 8, 2026Oct 8, 2026

    • gpbm

      Public
      Python
      •
      Other
      •2•1•0•2•Updated Oct 8, 2026Oct 8, 2026

    • carbon-assessment-with-ml

      Public
      CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
      Jupyter Notebook
      •
      Apache License 2.0
      •13•59•0•5•Updated Oct 6, 2026Oct 6, 2026

    • dstc11-track2-intent-induction

      Public
      DSTC 11 Track 2: Intent Induction from Conversations for Task-Oriented Dialogue
      Python
      •
      Apache License 2.0
      •9•49•0•1•Updated Oct 6, 2026Oct 6, 2026

    • chronos-forecasting

      Public
      Chronos: Pretrained Models for Time Series Forecasting
      machine-learningtimeseriestime-series
      machine-learningtimeseriestime-seriestransformersartificial-intelligenceforecastingpretrained-modelstime-series-forecastinghuggingfacehuggingface-transformers
      Python
      •
      Apache License 2.0
      •747•6.1k•22•18•Updated Oct 5, 2026Oct 5, 2026

    • JavaMigration

      Public
      Python
      •
      Apache License 2.0
      •2•9•0•0•Updated Sep 30, 2026Sep 30, 2026

    • StructRL

      Public
      Official implementation of "StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks "
      Python
      •
      Other
      •0•5•1•0•Updated Sep 30, 2026Sep 30, 2026

    • uniqsketch

      Public
      UniqSketch: sensitive and resource-efficient strain-level detection in metagenomes
      C++
      •
      MIT License
      •2•2•0•0•Updated Sep 29, 2026Sep 29, 2026

    • SynthAVE

      Public archive
      SynthAVE: multilingual benchmark for attribute-value verification with LLM-arena validation (EMNLP 2026 Industry Track)
      multilingualnlpbenchmark
      multilingualnlpbenchmarkdatasetllm-as-judge
      Other
      •0•0•0•0•Updated Sep 29, 2026Sep 29, 2026

    • operator-probconserv

      Public
      Official implementation of Operator-ProbConserv: OOD UQ for Neural Operators
      partial-differential-equationsconservation-lawsuncertainty-quantification
      partial-differential-equationsconservation-lawsuncertainty-quantificationshock-capturingout-of-domainneural-operators
      Python
      •
      Apache License 2.0
      •1•6•0•0•Updated Sep 28, 2026Sep 28, 2026

    • ExTS

      Public
      Python
      •
      Other
      •0•1•0•0•Updated Sep 16, 2026Sep 16, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.