01 arXiv · 2021
SilkTrain / R&D
From research paper to tested prototype
Find the authors’ code and relevant models or datasets. Ask a specialist to reproduce one result using data you have permission to use.
Selected papers
No selected paper matches. Search the public index or enter an arXiv identifier to request a review.
02 arXiv · 2022
Robust Speech Recognition via Large-Scale Weak Supervision
Read the paper · 2212.04356 ↗03 arXiv · 2023
Segment Anything
Read the paper · 2304.02643 ↗04 arXiv · 2020
Dense Passage Retrieval for Open-Domain Question Answering
Read the paper · 2004.04906 ↗05 arXiv · 2023
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Read the paper · 2305.18290 ↗06 arXiv · 2021
LoRA: Low-Rank Adaptation of Large Language Models
Read the paper · 2106.09685 ↗07 arXiv · 2020
Measuring Massive Multitask Language Understanding
Read the paper · 2009.03300 ↗08 arXiv · 2021
The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation
Read the paper · 2106.03193 ↗Linked datasets and software have their own terms. The pilot uses approved or synthetic data.