works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning

Wentao Zhang, Wentao Mo

The paper proposes an online convex optimization method (OCO-PAoI-Hard) that guarantees zero per-slot violations of hard peak Age of Information deadlines in safety‑critical IoT sy…

cs.LG2026

Data-Dependent Regret and Polyak Corrections for Constrained Online Convex Optimization

Wentao Zhang

Constrained online convex optimization requires minimizing regret against adversarial convex costs while satisfying a convex constraint at every round, as needed in safety-critical…

cs.LG2026

Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization

Wentao Zhang, Yutong Zhang, Wentao Mo

We study high-probability regret bounds for online convex optimization (OCO) with strongly convex losses and establish three results that resolve open questions at the intersection…

cs.AI2026

Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions

Wentao Zhang, Yutong Zhang, Yifan Zhu +1

The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions, yet existing approaches often struggle to balance optimization stability w…

cs.RO2026

From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models

Wentao Zhang, Aolan Sun, Wentao Mo +3

While vision-language-action (VLA) models for embodied agents integrate perception, reasoning, and control, they remain constrained by two critical weaknesses: first, during graspi…