6 accepted papers
The discovery of the *lazy neuron phenomenon* (Li et al., 2022), where fewer than 10% of the feedforward networks (FFN) parameters in trained Transformers are activated per token, has spurred significant interests in *activation sparsity* for enhancing large model efficiency. While notable progress…
Understanding long real-world videos requires modeling of long-range visual dependencies. To this end we explore video-first architectures building on the common paradigm of transferring large-scale image--text models to video via shallow temporal fusion. However we expose two limitations to the app…
"Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these methods have yet to be widely adopted since no one algorithm…
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL). In this work, we demonstrate that training an RL agent at scale leads to a general in-context l…
Pretrained models are a mainstay in modern NLP applications. Pretraining requires access to large volumes of unlabeled text. While monolingual text is readily available for many of the world’s languages, access to large quantities of code-switched text (i.e., text with tokens of multiple languages i…
Code-switching has seen growing interest in recent years as an important multilingual NLP phenomenon. Generating code-switched text for data augmentation has been sufficiently well-explored. However, there is no prior work on generating code-switched text with fine-grained control on the degree of c…