Jin Xu

Researcher@Microsoft·英国·OpenReview

研究方向

Deep Generative Models · large language model pretraining · group equivariance · neural networks · representation learning · meta-learning · few-shot learning · deep generative models · variational autoencoders · disentangling

发表论文（5 篇）

5.5

ICLR 2026desk_rejected

$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling

NeurIPS 2024Poster

二作

合作者 (20)

Leena Chennuru Vankadara