Srinivas Devadas
2 papers · Latest:
Machine Learning
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
PACZero introduces a novel PAC-private zeroth-order method for fine-tuning LLMs, achieving strong privacy ($I=0$) with usable utility via sign quantization.
2605.06505
Enabling AI ASICs for Zero Knowledge Proof
MORPH is a framework that reformulates ZKP kernels for AI ASICs like TPUs, significantly boosting performance for MSM and NTT operations.
2604.17808
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.