4 papers
What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
Jiachen Zhang, Junnan Nie, Junyi Lao +4
Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Their frozen representations nev…
Mirror Descent on Riemannian Manifolds
Jiaxin Jiang, Lei Shi, Jiyuan Tan
Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network trainin…
Revisit First-order Methods for Geodesically Convex Optimization
Yunlu Shu, Jiaxin Jiang, Lei Shi +1
In a seminal work of Zhang and Sra, gradient descent methods for geodesically convex optimization were comprehensively studied. In particular, Zhang and Sra derived a comparison in…
Diffusion-based Semi-supervised Spectral Algorithm for Regression on Manifolds
Weichun Xia, Jiaxin Jiang, Lei Shi
We introduce a novel diffusion-based spectral algorithm to tackle regression analysis on high-dimensional data, particularly data embedded within lower-dimensional manifolds. Tradi…