Research

What I study

I work on making large AI models cheaper to adapt and faster to run: combining many trained adapters in one model, and compiler techniques for model code.

01 Publications

Papers

2026

NeurIPS 2026
Accepted
Lead author

LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition

Using many separately trained LoRA adapters in one model at the same time, without retraining them together, for diffusion models and large language models.

Thamirawaran Sathiyalogeswaran · full author list forthcoming

Main conference · Poster

Details

2027

CGO 2027
Accepted

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2

Source-level program transformations that remove graph breaks, so torch.compile captures one uninterrupted FX graph instead of falling back to Python.

Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran, Krisztian Flautner, Lingjia Tang, Jason Mars

Details
arXiv