← Search

Nihal V. Nayak

2 accepted papers

2026

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

ICLR 2026poster

Large language models (LLMs) are typically deployed under diverse memory and compute constraints. Existing approaches build model families by training each size independently, which is prohibitively expensive and provides only coarse-grained size options. In this work, we identify a novel phenomenon…

Cited by 0SourcecodeScholar
2023

Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

ICLR 2023poster

We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models (VLMs) like CLIP. We develop CSP for compositional zero-shot learning, the task of predicting unseen attribute-object c…