Author

V. Sharan

h-index 17 View on Semantic Scholar

We have 2 of 73 papers

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.

Preprint Oct 2026

Does Random Search Discover Task Experts? Revisiting Neural Thickets

Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise. Gan&Isola (2026) recently proposed a striking alternative: that pretrained models lie in a dense neural thicket of task specialists, which can be surfaced with simple Gaussian weight perturbations....

Julian Asilis, Guan-Zhe Hong, Vatsal Sharan · 0 citations

#artificial intelligence Apr 2026

Convergent Evolution: How Different Language Models Learn Similar Number Representations

This paper identifies two different routes through which models can acquire geometrically separable features: they can learn them from complementary co-occurrence signals in general language data, including text-number co-occurrence and cross-number interaction, or from multi-token addition problems.

Deqing Fu, Tianyi Zhou, Mikhail Belkin et al. · arXiv.org · 3 citations