3 papers
cs.LG2025
One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
Amrit Diggavi Seshadri
To reduce the time and computational costs of inference of large language models, there has been interest in parameter-efficient low-rank early-exit casting of transformer hidden-r…
cs.AI2024
Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction
Amrit Diggavi Seshadri
With the size and cost of large transformer-based language models growing, recently, there has been interest in shortcut casting of early transformer hidden-representations to fina…
cs.CV2021
Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis
Amrit Diggavi Seshadri, Balaraman Ravindran
Synthesizing high-quality, realistic images from text-descriptions is a challenging task, and current methods synthesize images from text in a multi-stage manner, typically by firs…