Yang Yang

Hoang Le, Liang Zhang, Amir Said et al.

Realizing the potential of neural video codecs on mobile devices is a big technological challenge due to the computational complexity of deep networks and the power-constrained mobile hardware. We demonstrate practical feasibility by leveraging Qualcomm's technology and innovation, bridging the gap from neural network-based codec simulations running on wall-powered workstations, to real-time operation on a mobile device powered by Snapdragon technology. We show the first-ever inter-frame neural video decoder running on a commercial mobile phone, decoding high-definition videos in real-time while maintaining a low bitrate and high visual quality.

Xuguang Li, Zhonglin Zuo, Zheng Dong et al.

Natural gas pipeline leaks pose severe risks, leading to substantial economic losses and potential hazards to human safety. In this study, we develop an accurate model for the early prediction of pipeline leaks. To the best of our knowledge, unlike previous anomaly detection, this is the first application to use internal pipeline data for early prediction of leaks. The modeling process addresses two main challenges: long-term dependencies and sample imbalance. First, we introduce a dilated convolution-based prediction model to capture long-term dependencies, as dilated convolution expands the model's receptive field without added computational cost. Second, to mitigate sample imbalance, we propose the MKTCN model, which incorporates the Kolmogorov-Arnold Network as the fully connected layer in a dilated convolution model, enhancing network generalization. Finally, we validate the MKTCN model through extensive experiments on two real-world datasets. Results demonstrate that MKTCN outperforms in generalization and classification, particularly under severe data imbalance, and effectively predicts leaks up to 5000 seconds in advance. Overall, the MKTCN model represents a significant advancement in early pipeline leak prediction, providing robust generalization and improved modeling of the long-term dependencies inherent in multi-dimensional time-series data.

Jun Ling, Yao Qi, Tao Huang et al.

In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs. A central challenge of this task lies in accurately handling complex tables -- those with large sizes, deeply nested structures, and semantically rich or irregular cell content -- where existing methods often fail. We begin with a comprehensive analysis, identifying key challenges and highlighting the limitations of current evaluation protocols. To overcome these issues, we propose a reinforced multimodal large language model (MLLM) framework, where a pre-trained MLLM is fine-tuned on a large-scale table-to-LaTeX dataset. To further improve generation quality, we introduce a dual-reward reinforcement learning strategy based on Group Relative Policy Optimization (GRPO). Unlike standard approaches that optimize purely over text outputs, our method incorporates both a structure-level reward on LaTeX code and a visual fidelity reward computed from rendered outputs, enabling direct optimization of the visual output quality. We adopt a hybrid evaluation protocol combining TEDS-Structure and CW-SSIM, and show that our method achieves state-of-the-art performance, particularly on structurally complex tables, demonstrating the effectiveness and robustness of our approach.