Luke Zettlemoyer

17

Papers

112

Total Citations

2

Affiliations

Affiliations

University of WashingtonFacebook

Papers (17)

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

MoDE: CLIP Data Experts via Clustering

Situation Recognition: Visual Semantic Role Labeling for Image Understanding

Commonly Uncommon: Semantic Sparsity in Situation Recognition

ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

CiT: Curation in Training for Effective Vision-Language Data

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

QLoRA: Efficient Finetuning of Quantized LLMs

Stable and low-precision training for large-scale vision-language models

LIMA: Less Is More for Alignment

Toolformer: Language Models Can Teach Themselves to Use Tools

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Pre-training via Paraphrasing

Luna: Linear Unified Nested Attention

SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark

Improving Policy Learning via Language Dynamics Distillation

GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale