Akshay Jajoo — accepted AI-conference papers

2026

KLAS: Using Similarity to Stitch Neural Networks for an Improved Accuracy-Efficiency Tradeoff

Debopam Sanyal, Anantharaman S. Iyer, Alind Khare, Trisha Jain, Akshay Jajoo, Myungjin Lee +2

ICLR 2026poster

Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work demonstrates that stitching pretrained models within a model family enables cost-effective interpolation of the accuracy-efficiency tradeoff space.…

Cited by 0 Source ↗Scholar ↗

2025

StitchLLM: Serving LLMs, One Block at a Time

Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li +6

ACL 2025long

The rapid evolution of large language models (LLMs) has revolutionized natural language processing (NLP) tasks such as text generation, translation, and comprehension. However, the increasing computational demands and inference costs of these models present significant challenges. This study investi…

Cited by 0 Source ↗PDF ↗Scholar ↗