Author

Pratyusha Sharma

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time

OP-Mix (On-Policy Mix), a data mixing algorithm that operates across pretraining, midtraining, and instruction tuning, is introduced, suggesting a different view of language model training: not a sequence of distinct phases, but a single continuous process of learning from data.

Michael Y Hu, Apurva Gandhi, Kyunghyun Cho et al. · arXiv.org · 0 citations

#machine learning Preprint Sep 2026

Training Witnesses: Trusting the Training without Trusting the Trainer

The key insight is that fast behavioral fingerprints with occasional replay challenges are sufficient for auditing neural network training, and the method is applicable at scale with minimal overhead to the trainer, is cheap for the verifier, rejects bad training runs with amplifiable probability, and allows for exact...

Hou-Jun Liu, Pratyusha Sharma · 0 citations