2.7k citations · 3.3k across the 22 of their papers we have counts for
8 papers · 1 filter
RouteLLM: Learning to Route LLMs with Preference Data
Isaac Ong, Amjad Almahairi, Vincent Wu +5
Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and c…
Uniform Masking Prevails in Vision-Language Pretraining
Siddharth Verma, Yuchen Lu, Rui Hou +4
Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining. To implement MLM, the researcher must make two design choices: the maski…
Adversarial Computation of Optimal Transport Maps
Jacob Leygonie, Jennifer She, Amjad Almahairi +2
Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) ar…
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Hugo Berard, Gauthier Gidel, Amjad Almahairi +2
Generative adversarial networks have been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks. In…
Learning Distributed Representations from Reviews for Collaborative Filtering
Amjad Almahairi, Kyle Kastner, Kyunghyun Cho +1
Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regulariz…
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni +2
Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN…
Calibrating Energy-based Generative Adversarial Networks
Zihang Dai, Amjad Almahairi, Philip Bachman +2
In this paper, we propose to equip Generative Adversarial Networks with the ability to produce direct energy estimates for samples.Specifically, we propose a flexible adversarial t…
Dynamic Capacity Networks
Amjad Almahairi, Nicolas Ballas, Tim Cooijmans +3
We introduce the Dynamic Capacity Network (DCN), a neural network that can adaptively assign its capacity across different portions of the input data. This is achieved by combining…