arXiv subjects
Publications and source records attributed to Fangfang Chen.
Following B. Yu's work on Lyapunov graphs of non-singular Smale flows on $S^1\times S^2$, we characterize the Lyapunov graphs of non-singular Morse-Smale flows on $S^1 \times S^2$ by using filtrating neighborhoods as the local data attached to the vertices. More precisely, we determine which oriented graphs with vertices labeled by filtrating neighborhoods can be realized as such Lyapunov graphs.
Catastrophic forgetting remains a central challenge in continual learning (CL) with pre-trained models. While existing approaches typically freeze the backbone and fine-tune a small number of parameters to mitigate forgetting, they still rely on iterative error backpropagation and gradient-based optimization, which can be computationally intensive and less suitable for resource-constrained environments. To address this, we propose FoRo, a forward-only, gradient-free continual learning method. FoRo consists of a lightweight prompt tuning strategy and a novel knowledge encoding mechanism, both designed without modifying the pre-trained model. Specifically, prompt embeddings are inserted at the input layer and optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), which mitigates distribution shifts and extracts high-quality task representations. Subsequently, task-specific knowledge is encoded into a knowledge encoding matrix via nonlinear random projection and recursive least squares, enabling incremental updates to the classifier without revisiting prior data. Experiments show that FoRo significantly reduces average forgetting and improves accuracy. Thanks to forward-only learning, FoRo reduces memory usage and run time while maintaining high knowledge retention across long task sequences. These results suggest that FoRo could serve as a promising direction for exploring continual learning with pre-trained models, especially in real-world multimedia applications where both efficiency and effectiveness are critical.
Industrial AI is transitioning from traditional deep learning models to large-scale transformer-based architectures, with the Industrial Internet of Things (IIoT) playing a pivotal role. IIoT evolves from a simple data pipeline to an intelligent infrastructure, enabling and enhancing these advanced AI systems. This survey explores the integration of IIoT with large models (LMs) and their potential applications in industrial environments. We focus on four primary types of industrial LMs: language-based, vision-based, time-series, and multimodal models. The lifecycle of LMs is segmented into four critical phases: data foundation, model training, model connectivity, and continuous evolution. First, we analyze how IIoT provides abundant and diverse data resources, supporting the training and fine-tuning of LMs. Second, we discuss how IIoT offers an efficient training infrastructure in low-latency and bandwidth-optimized environments. Third, we highlight the deployment advantages of LMs within IIoT, emphasizing IIoT's role as a connectivity nexus fostering emergent intelligence through modular design, dynamic routing, and model merging to enhance system scalability and adaptability. Finally, we demonstrate how IIoT supports continual learning mechanisms, enabling LMs to adapt to dynamic industrial conditions and ensure long-term effectiveness. This paper underscores IIoT's critical role in the evolution of industrial intelligence with large models, offering a theoretical framework and actionable insights for future research.
Integrating large language models (LLMs) into autonomous driving enhances personalization and adaptability in open-world scenarios. However, traditional edge computing models still face significant challenges in processing complex driving data, particularly regarding real-time performance and system efficiency. To address these challenges, this study introduces EC-Drive, a novel edge-cloud collaborative autonomous driving system with data drift detection capabilities. EC-Drive utilizes drift detection algorithms to selectively upload critical data, including new obstacles and traffic pattern changes, to the cloud for processing by GPT-4, while routine data is efficiently managed by smaller LLMs on edge devices. This approach not only reduces inference latency but also improves system efficiency by optimizing communication resource use. Experimental validation confirms the system's robust processing capabilities and practical applicability in real-world driving conditions, demonstrating the effectiveness of this edge-cloud collaboration framework. Our data and system demonstration will be released at https://sites.google.com/view/ec-drive.
We classify the indexed links corresponding to the union of the closed orbits of non-singular Morse-Smale flows on most graph manifolds. We find that each of this kind of indexed links can be obtained by applying a finite steps of operations on a special indexed link, which consists of all of the singular Seifert fibers and some regular Seifert fibers with some precisely described conditions.
The internal structures of pulsating white dwarfs can be explored only with asteroseismology. Time series photometric observations were made for the pulsating DA white dwarf (ZZ Ceti star) WD~0246+326 during 9 nights in 2014 with a bi-site observation campaign. Eleven frequencies were detected including 1 triplet, 2 doublets, and 4 single modes, which are identified as either $l=1$ or $l=2$ modes with the complementarity of frequencies present in the literature. From the multiplets, the rotation period of \astrobj{WD~0246+326} is derived as $3.78\pm 0.11$ days. The average period spacing of the l=1 modes $ΔP=29.3\pm 0.2s$, implies that \astrobj{WD~0246+326} may be a massive ZZ Ceti star concerning the $ΔP-M_*$ relationship for the DAVs. Preliminary analysis derives the stellar parameters of $M_*=0.98\pm0.01$~${\rm M_\odot}$ and $T_{\rm eff}=11700\pm100$~K by fitting the theoretical frequencies of the eigen modes to the observed ones.
The spectroscopic sky survey carried out by the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) provides the largest stellar spectra library in the world until now. A large number of new DA white dwarfs had been identified based on the LAMOST spectra. The effective temperature ($T_{\rm eff}$) and surface gravity ($\log g$) of most DA white dwarfs were determined and published in the catalogs, e.g. Zhao et al. (2013), Rebassa-Mansergas et al. (2015), Gentile Fusillo et al. (2015) and Guo et al. (2015). We selected ZZ Ceti candidates from the published catalogs by considering whether their $T_{\rm eff}$ are situated in the ZZ Ceti instability strip. The follow-up time-series photometric observations for the candidates were performed in 2015 and 2016. Four stars: LAMOST J004628.31+343319.90, LAMOST J062159.49+252335.9, LAMOST J010302.46+433756.2 and LAMOST J013033.90+273757.9 are finally confirmed to be new ZZ Ceti stars. They show dominant peaks with amplitudes rising above the 99.9% confidence level in the amplitude spectra. As LAMOST J004628.31+343319.90 has an estimated mass of $\sim$ 0.40 $M_{\odot}$ and LAMOST J013033.90+273757.9 has a mass of $\sim$ 0.45 $M_{\odot}$ derived from their $\log g$ values, these two stars are inferred to be potential helium-core white dwarfs.