The battery systems of electric vehicles (EVs) are directly impacted by battery temperature in terms of thermal runaway and failure. However, uncertainty about thermal runaway, dynamic conditions, and a dearth of high-quality data sets make modeling and predicting nonlinear multiscale electrochemical systems challenging. In this work, a novel Mamba network architecture called BMPTtery (Bidirectional Mamba Predictive Battery Temperature Representation) is proposed to overcome these challenges. First, a two-step hybrid model of trajectory piecewise–polynomial regression and exponentially weighted moving average is created and used to an operational dataset of EVs in order to handle the problem of noisy and incomplete time-series data. Each time series is then individually labeled to learn the representation and adaptive correlation of the multivariate series to capture battery performance variations in complex dynamic operating environments. Next, a prediction method with multiple steps based on the bidirectional Mamba is suggested. When combined with a failure diagnosis approach, this scheme can accurately detect heat failures due to excessive temperature, rapid temperature rise, and significant temperature differences. The experimental results demonstrate that the technique can accurately detect battery failures on a dataset of real operational EVs and predict the battery temperature one minute ahead of time with an MRE of 0.273%.
Text recognition is a rapidly evolving task with broad practical applications across multiple industries. However, due to the arbitrary-shape text arrangement, irregular text font, and unintended occlusion of font, this remains a challenging task. To handle images with arbitrary-shape text arrangement and irregular text font, we designed the Discriminative Standard Text Font (DSTF) and the Feature Alignment and Complementary Fusion (FACF). To address the unintended occlusion of font, we propose a Dual Attention Serial Module (DASM), which is integrated between residual modules to enhance the focus on text texture. These components improve text recognition by correcting irregular text and aligning it with the original feature extraction, thus complementing the overall recognition process. Additionally, to enhance the study of text recognition in natural scenes, we developed the VBC Chinese dataset under varying lighting conditions, including strong light, weak light, darkness, and other natural environments. Experimental results show that our method achieves competitive performance on the VBC dataset with an accuracy of 90.8% and an overall average accuracy of 93.8%.
Recent diffusion-based Multimodal Large Language Models (dMLLMs) suffer from high inference latency and therefore rely on caching techniques to accelerate decoding. However, the application of cache mechanisms often introduces undesirable repetitive text generation, a phenomenon we term the \textbf{Repeat Curse}. To better investigate underlying mechanism behind this issue, we analyze repetition generation through the lens of information flow. Our work reveals three key findings: (1) context tokens aggregate semantic information as anchors and guide the final predictions; (2) as information propagates across layers, the entropy of context tokens converges in deeper layers, reflecting the model's growing prediction certainty; (3) Repetition is typically linked to disruptions in the information flow of context tokens and to the inability of their entropy to converge in deeper layers. Based on these insights, we present \textbf{CoTA}, a plug-and-play method for mitigating repetition. CoTA enhances the attention of context tokens to preserve intrinsic information flow patterns, while introducing a penalty term to the confidence score during decoding to avoid outputs driven by uncertain context tokens. With extensive experiments, CoTA demonstrates significant effectiveness in alleviating repetition and achieves consistent performance improvements on general tasks. Code is available at https://github.com/ErikZ719/CoTA
In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers as encoders without evaluating their cross-domain limitations and inherent shortcomings: forgetting important information or focusing on irrelevant representations when modeling long-range dependencies for text detection. The recently proposed state space model Mamba has demonstrated better long-range dependencies modeling through a linear complexity selection mechanism. Therefore, we propose a novel scene text detector based on Mamba that integrates the selection mechanism with attention layers, enhancing the encoder's ability to extract relevant information from long sequences. We adopt the Top\_k algorithm to explicitly select key information and reduce the interference of irrelevant information in Mamba modeling. Additionally, we design a dual-scale feed-forward network and an embedding pyramid enhancement module to facilitate high-dimensional hidden state interactions and multi-scale feature fusion. Our method achieves state-of-the-art or competitive performance on various benchmarks, with F-measures of 89.7\%, 89.2\%, and 78.5\% on CTW1500, TotalText, and ICDAR19ArT, respectively. Codes will be available.