2.1k citations · 8.9k across the 84 of their papers we have counts for
18 papers · 1 filter
PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski +4
Can we train a single transformer model capable of processing multiple modalities and datasets, whilst sharing almost all of its learnable parameters? We present PolyViT, a model t…
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
Vamsi Aribandi, Yi Tay, Tal Schuster +11
Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the nu…
The Efficiency Misnomer
Mostafa Dehghani, Anurag Arnab, Lucas Beyer +2
Model efficiency is a critical aspect of developing and deploying machine learning models. Inference time and latency directly affect the user experience, and some applications hav…
Sharpness-Aware Minimization Improves Language Model Generalization
Dara Bahri, Hossein Mobahi, Yi Tay
The allure of superhuman-level capabilities has led to considerable interest in language models like GPT-3 and T5, wherein the research has, by and large, revolved around new model…
Improving Compositional Generalization with Self-Training for Data-to-Text Generation
Sanket Vaibhav Mehta, Jinfeng Rao, Yi Tay +3
Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is cost…
Improving Neural Ranking via Lossless Knowledge Distillation
Zhen Qin, Le Yan, Yi Tay +4
We explore a novel perspective of knowledge distillation (KD) for learning to rank (LTR), and introduce Self-Distilled neural Rankers (SDR), where student rankers are parameterized…