Yue Zhang

An Integrated Model for Tropical Cyclone Track Forecasting Based on Deep Learning Techniques

Yue Zhang, Yuhang Zhu, Mengqi Yang, Lichun Tang et autres

Abstract An accurate track forecast for tropical cyclones (TCs) is critical for disaster prevention and mitigation. Although various models, including statistical, numerical, and artificial intelligence (AI) based, have demonstrated good skill in TC track forecasting, they have not ever been (and will …

cn (code pays fourni par la source)

Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents

Tianyi Ma, Yue Zhang, Zehao Wang, Parisa Kordjamshidi

Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments.While recent progress has been driven by large-scale pre-training and data augmentation, current methods still struggle to generalize to unseen scenarios, particularly when complex spatial …

us, be (code pays fourni par la source)

Ultrasonic lithotripsy-inspired acousto-optic dual-responsive nano-enzymatic hollow spheres for precise, rapid and long-acting clearance of deep vein thrombosis

Yue Zhang, Xinyang Yin, Lina Chen, Zhenzhen Weng et autres

cn (code pays fourni par la source)

Select High-Quality Stock with Random Forest Classifier

Chang Liu, Yue Zhang, Yuqi Cai

This study explores the application of a Random Forest Classifier to predict stock performance among S&P 500 companies based on financial and stock performance data. Financial indicators such as Return on Equity (ROE), Return on Assets (ROA), Market Value (MV), Price-to-Book Ratio …

cn, ca (code pays fourni par la source)

Cloud-assisted updatable private set intersection cardinality

Yue Zhang, Wei Liu, Jiayi Song, Ke Chen et autres

cn (code pays fourni par la source)

Quantized Channels and Instability Modulation Strategy in Au/PDMS Single-Crack Evolution

Yongqiang Yang, Yue Zhang, Yujie Wei, Manasa Pantrangi et autres

Controllable conductive channels in crack-based sensors are crucial for stable microdeformation detection, yet the random formation of disordered crack networks in conventional sensors hinders the precise analysis of single-crack contributions to sensing performance. We propose a stress-engineered single-crack architecture in Au/PDMS films, …

cn, it (code pays fourni par la source)

Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment

Yue Zhang, Jilei Sun, Yunhui Guo, Vibhav Gogate

Video Large Multimodal Models (VLMMs) have made impressive strides in understanding video content, but they often struggle with abstract and adaptive reasoning-the ability to revise their interpretations when new information emerges. In reality, conclusions are rarely set in stone; additional context can …

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu et autres

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching …

Research on the diagnosis and evaluation technology of the whole life cycle cost of power grid transformer equipment

Mengzhe Liu, Ying Wang, Yue Zhang, Zhiyuan Zhang

With the continuous development of grid equipment, how to achieve refined management of costs throughout the entire lifecycle has become a significant challenge for power grid enterprises. The lifecycle cost of grid equipment involves multiple stages, including initial investment, maintenance, operations, fault …

Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization

Yue Zhang, Liqiang Jing, Vibhav Gogate

We introduce a new task called Defeasible Visual Entailment (DVE), where the goal is to allow the modification of the entailment relationship between an image premise and a text hypothesis based on an additional update. While this concept is well-established in Natural …

us (code pays fourni par la source)

Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation

Qiji Zhou, Yifan Gong, Guangsheng Bao, Hongjie Qiu et autres

Counterfactual reasoning is crucial for robust video understanding but remains underexplored in existing multimodal benchmarks. In this paper, we introduce \textbf{COVER} (\textbf{\underline{CO}}unterfactual \textbf{\underline{V}}id\textbf{\underline{E}}o \textbf{\underline{R}}easoning), a multidimensional multimodal benchmark that systematically evaluates MLLMs across the abstract-concrete and perception-cognition dimensions. Beyond prior multimodal benchmarks, …

Optical microfiber intelligent watchband for cuffless blood pressure monitoring

Jiaqi Chen, Yue Zhang, Bin Liu, Juan Liu et autres

cn, gb (code pays fourni par la source)