research
∙
07/04/2023
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
Connectionist Temporal Classification (CTC) is a widely used criterion f...
share
research
∙
04/19/2023
Fundamental Limitations of Alignment in Large Language Models
An important aspect in developing language models that interact with hum...
research
∙
03/14/2023
The Learnability of In-Context Learning
In-context learning is a surprising and important phenomenon that emerge...
research
∙
04/06/2022
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
The field of Natural Language Processing (NLP) has experienced a dramati...
research
∙
10/09/2021
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design
Pretraining Neural Language Models (NLMs) over a large corpus involves c...
research
∙
05/09/2021
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
After their successful debut in natural language processing, Transformer...
research
∙
06/22/2020
Limits to Depth Efficiencies of Self-Attention
Self-attention architectures, which are rapidly pushing the frontier in ...
research
∙
02/11/2019