4 papers · 1 filter
ELT: Elastic Looped Transformers for Visual Generation
Sahil Goyal, Swayam Agrawal, Gautham Govind Anil +3
We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architecture. While conventional gen…
Masked Generative Nested Transformers with Decode Time Scaling
Sahil Goyal, Debapriya Tula, Gagan Jain +3
Recent advances in visual generation have made significant strides in producing content of exceptional quality. However, most methods suffer from a fundamental problem - a bottlene…
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Gagan Jain, Nidhi Hegde, Aditya Kusupati +5
The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. Wh…
LookupViT: Compressing visual information to a limited number of tokens
Rajat Koner, Gagan Jain, Prateek Jain +2
Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they c…