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 (Language) 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/mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
amazon-science/patchcore-inspection
amazon-science/esci-data
Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search
amazon-science/glass-text-spotting
Official implementation for "GLASS: Global to Local Attention for Scene-Text Spotting" (ECCV'22)
amazon-science/CodeSage
CodeSage: Code Representation Learning At Scale (ICLR 2024)
amazon-science/auto-rag-eval
Code repo for the ICML 2024 paper "Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation"
amazon-science/probconserv
Datasets and code for results presented in the ProbConserv paper
amazon-science/Repoformer
Repoformer: Selective Retrieval for Repository-Level Code Completion (ICML 2024)
amazon-science/tofueval
amazon-science/page-link-path-based-gnn-explanation
amazon-science/graph-lm-ensemble
amazon-science/adaptive-feature-transfer
Official implementation of Adaptive Feature Transfer (AFT)
amazon-science/camml
CaMML:Context-Aware MultiModal Learner for Large Models (ACL 2024)
amazon-science/controllable-readability-summarization
Generating Summaries with Controllable Readability Levels (EMNLP 2023)
amazon-science/piperag
PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
amazon-science/factual-confidence-of-llms
Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"
amazon-science/steerfair
Discovering Bias in Latent Space: An Unsupervised Debiasing Approach (ICML 2024)
amazon-science/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.
amazon-science/mezo_svrg
Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"
amazon-science/CERET-LLM-refine
This is the code repository for paper CERET: Cost-Effective Extrinsic Refinement for Text Generation (NAACL 2024).
amazon-science/explaining-probabilistic-models-with-distributinal-values
Distributional values for XAI
amazon-science/xstreet
amazon-science/ccsum
amazon-science/mada_optimizer_search
Code the ICML 2024 paper: "MADA: Meta-Adaptive Optimizers through hyper-gradient Descent"
amazon-science/preference-driven-mt
amazon-science/m3t-multi-modal-translation-bench
amazon-science/contrastive_emc2
Code the ICML 2024 paper: "EMC^2: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence"
amazon-science/krylov-cubic-regularized-newton
Code for the AISTATS 2024 paper: "Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate".
amazon-science/prism-finetuned
amazon-science/Quivela4