1 citations · 1 across the 5 of their papers we have counts for
7 papers
SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption
Wentao Zhang, Yifan Zhu, Yutong Zhang +1
Multimodal gradient balancing methods modulate encoder gradients with a shared scalar per modality, implicitly assuming that corruption is uniform across the training batch. In pra…
Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning
Wentao Zhang, Wentao Mo
Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbrev…
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…
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…
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…
Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
Naifu Zhang, Wei Tao, Xi Xiao +5
In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end trainin…
Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
Linhao Huang, Xue Jiang, Zhiqiang Wang +5
Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial…