Tianshi Wang

Drift-Aware System Assurance for Wind-Turbine SCADA Condition Monitoring

Tianshi Wang, Tianlin Li

cn (code pays fourni par la source)

Prior-informed generative hashing under non-ideal semantic manifolds for cross-modal retrieval

Zi Wang, Fengling Li, Tianshi Wang, Guohua Dong et autres

cn, au (code pays fourni par la source)

Engineering Spatiotemporally‐Resolved Hydrogen‐Bond Networks for Decoupled H + /Zn 2+ Transport Toward Durable Low‐Temperature Aqueous Zinc‐Ion Batteries

Xin Tang, Tianshi Wang, Guolang Zhou, Chong Zhao et autres

ABSTRACT The performance of aqueous zinc‐ion batteries is limited by the coupled transport of protons (H + ) and Zn 2+ due to extensive hydrogen‐bond (H‐bond) networks in conventional electrolytes. To achieve the decoupling of this detrimental interplay, we establish a spatiotemporal …

cn (code pays fourni par la source)

Priority-Driven Flow Scheduling for Distributed Large Language Model Training

Tianshi Wang, Yiran Zhang, Zhang Yiao, Qiyang Zhang et autres

cn (code pays fourni par la source)

Mistake Detection in Egocentric Procedural Videos Via CoT-Based Action Anticipation

Yishan Zou, Chris Nugent, Matthew Burns, Shengli Wu et autres

Mistake detection aims to identify deviations from expected action sequences during task execution, a process particularly crucial in egocentric procedural videos to enable reliable task monitoring and the development of intelligent assistive systems. However, existing approaches often depend on preconceived mistake scenarios …

cn, gb (code pays fourni par la source)

Beyond Fixed-Length Constraints: Variable-length Hashing via Adaptive Bit-importance Learning for Multi-modal Retrieval

Ruifan Zuo, C. Zheng, Fengling Li, Tianshi Wang et autres

cn, au (code pays fourni par la source)

Do More With Less: Capacity-Aware Selective Hashing for Continual Cross-Modal Retrieval

Wenhao Liu, Tianshi Wang, Fengling Li, Jingjing Li et autres

Although cross-modal hashing enables efficient large-scale retrieval by encoding multimodal data into compact binary representations, its fixed code length and binary nature impose a fundamental capacity constraint that hinders continual adaptation to growing data streams and emerging semantic concepts. Existing continual cross-modal …

cn, ae (code pays fourni par la source)

Prompt-Driven Bit Extension Hashing for Continual Cross-Modal Retrieval

Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu

Continual cross-modal hashing is critical for efficient retrieval across heterogeneous modalities in dynamic environments. Yet, existing approaches primarily focus on mitigating catastrophic forgetting, while overlooking two key challenges: 1) the hash collision arising from the excessive utilization of the Hamming space across …

cn, au (code pays fourni par la source)

Noise-Robust Generative Hashing for Cross-Modal Retrieval

Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu

Deep hashing has proven remarkable effectiveness for large-scale cross-modal retrieval, yet its performance is highly vulnerable to supervisory noise, such as mismatched cross-modal correspondences and incorrect category labels. Such noise is prevalent in real-world scenarios, where correspondence mismatches and label inaccuracies often …

cn, au (code pays fourni par la source)

Decoupling the Interfacial Failure Mechanisms of Zn Anodes via Functional Zoning Strategy

Guolang Zhou, Chao Tang, Xin Tang, Tianshi Wang et autres

Abstract The commercialization of aqueous zinc‐ion batteries is impeded by the dynamic interfacial instability of zinc anodes, stemming from the intertwined issues of dendritic growth, hydrogen evolution corrosion, and sluggish ion transport. Conventional homogeneous interfacial layers fail to decouple these conflicting requirements. …

cn (code pays fourni par la source)

Robust Onboard DNNs under Single Event Upsets

Hao Zhao, Tianshi Wang, Chen Yang, Fei Teng

The deployment of Deep Neural Networks (DNNs) for onboard satellite applications, such as raw data processing and Earth observation, is rapidly expanding. However, Single Event Upsets (SEUs) caused by high-energy particles induce bit flips in memory-stored model parameters, compromising system reliability. Hardware …

cn (code pays fourni par la source)

Author response: Action mechanism of a novel agrichemical quinofumelin against Fusarium graminearum

Qian Xiu, Xiaoru Yin, Yuanyuan Chen, Z. Zhang et autres

cn (code pays fourni par la source)