Architecture researcher
Luke Zettlemoyer
Co-created BART, a denoising encoder-decoder pretraining objective effective for text generation and comprehension.
Works in the archive (3)
- BART: Denoising Seq2Seq Pre-training · 2020
- Inference Quantization (GPTQ/AWQ/SmoothQuant/bitsandbytes) · 2022
- LoRA / QLoRA (parameter-efficient fine-tuning) · 2022
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (17 people)
Loading graph…