Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Molino, Piero"'
Autor:
Zhao, Justin, Wang, Timothy, Abid, Wael, Angus, Geoffrey, Garg, Arnav, Kinnison, Jeffery, Sherstinsky, Alex, Molino, Piero, Addair, Travis, Rishi, Devvret
Low Rank Adaptation (LoRA) has emerged as one of the most widely adopted methods for Parameter Efficient Fine-Tuning (PEFT) of Large Language Models (LLMs). LoRA reduces the number of trainable parameters and memory usage while achieving comparable p
Externí odkaz:
http://arxiv.org/abs/2405.00732
Autor:
Molino, Piero, Tagliabue, Jacopo
We examine how much of the contemporary progress in artificial intelligence (and, specifically, in natural language processing), can be, more or less directly, traced back to the seminal work and ideas of the Austrian-British philosopher Ludwig Wittg
Externí odkaz:
http://arxiv.org/abs/2302.01570
The rapid proliferation of machine learning models across domains and deployment settings has given rise to various communities (e.g. industry practitioners) which seek to benchmark models across tasks and objectives of personal value. Unfortunately,
Externí odkaz:
http://arxiv.org/abs/2111.04260
Autor:
Molino, Piero, Ré, Christopher
In the last years machine learning (ML) has moved from a academic endeavor to a pervasive technology adopted in almost every aspect of computing. ML-powered products are now embedded in our digital lives: from recommendations of what to watch, to div
Externí odkaz:
http://arxiv.org/abs/2107.08148
Autor:
Shu, Lei, Papangelis, Alexandros, Wang, Yi-Chia, Tur, Gokhan, Xu, Hu, Feizollahi, Zhaleh, Liu, Bing, Molino, Piero
This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to
Externí odkaz:
http://arxiv.org/abs/2009.12046
Autor:
Weng, Yue, Miryala, Sai Sumanth, Khatri, Chandra, Wang, Runze, Zheng, Huaixiu, Molino, Piero, Namazifar, Mahdi, Papangelis, Alexandros, Williams, Hugh, Bell, Franziska, Tur, Gokhan
The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to perform c
Externí odkaz:
http://arxiv.org/abs/2002.00750
Autor:
Madotto, Andrea, Namazifar, Mahdi, Huizinga, Joost, Molino, Piero, Ecoffet, Adrien, Zheng, Huaixiu, Papangelis, Alexandros, Yu, Dian, Khatri, Chandra, Tur, Gokhan
This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the pl
Externí odkaz:
http://arxiv.org/abs/2001.08868
Autor:
Papangelis, Alexandros, Namazifar, Mahdi, Khatri, Chandra, Wang, Yi-Chia, Molino, Piero, Tur, Gokhan
As the field of Spoken Dialogue Systems and Conversational AI grows, so does the need for tools and environments that abstract away implementation details in order to expedite the development process, lower the barrier of entry to the field, and offe
Externí odkaz:
http://arxiv.org/abs/2001.06463
We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link predict
Externí odkaz:
http://arxiv.org/abs/1912.09867
Autor:
Dathathri, Sumanth, Madotto, Andrea, Lan, Janice, Hung, Jane, Frank, Eric, Molino, Piero, Yosinski, Jason, Liu, Rosanne
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying t
Externí odkaz:
http://arxiv.org/abs/1912.02164