Yifan Tang

Yifan Tang, Qiquan Wang, Inés García-Redondo et al.

We study the grokking phenomenon through the lens of topology. Using persistent homology on point clouds derived from the embedding matrices of a range of models trained on modular arithmetic with varying primes, we identify a clear and consistent topological signature of grokking: a sharp increase in both the maximum and total persistence of first homology ($H_1$). Persistence diagrams reveal the emergence of a dominant long-lived topological feature together with increasingly structured secondary features, reflecting the underlying cyclic structure of the task. Compared to existing spectral and geometric diagnostics -- specifically, Fourier analysis and local intrinsic dimension -- persistent homology provides a unified geometric and topological characterization of representation learning, capturing both local and global multi-scale structure. Ablations across data regimes and control settings show that these topological transitions are tied to generalization rather than memorization. Our results suggest that persistent homology offers a principled and interpretable framework for analyzing how neural networks internalize latent structure during training.

Yihao Wang, Ru Zhang, Yifan Tang et al.

With the evolution of generative linguistic steganography techniques, conventional steganalysis falls short in robustly quantifying the alterations induced by steganography, thereby complicating detection. Consequently, the research paradigm has pivoted towards deep-learning-based linguistic steganalysis. This study offers a comprehensive review of existing contributions and evaluates prevailing developmental trajectories. Specifically, we first provided a formalized exposition of the general formulas for linguistic steganalysis, while comparing the differences between this field and the domain of text classification. Subsequently, we classified the existing work into two levels based on vector space mapping and feature extraction models, thereby comparing the research motivations, model advantages, and other details. A comparative analysis of the experiments is conducted to assess the performances. Finally, the challenges faced by this field are discussed, and several directions for future development and key issues that urgently need to be addressed are proposed.

Yifan Tang, M. Rahmani Dehaghani, Pouyan Sajadi et al.

This paper aims to propose an online two-stage thermal history prediction method, which could be integrated into a metal AM process for performance control. Based on the similarity of temperature curves (curve segments of a temperature profile of one point) between any two successive layers, the first stage of the proposed method designs a layer-to-layer prediction model to estimate the temperature curves of the yet-to-print layer from measured temperatures of certain points on the previously printed layer. With measured/predicted temperature profiles of several points on the same layer, the second stage proposes a reduced order model (ROM) (intra-layer prediction model) to decompose and construct the temperature profiles of all points on the same layer, which could be used to build the temperature field of the entire layer. The training of ROM is performed with an extreme learning machine (ELM) for computational efficiency. Fifteen wire arc AM experiments and nine simulations are designed for thin walls with a fixed length and unidirectional printing of each layer. The test results indicate that the proposed prediction method could construct the thermal history of a yet-to-print layer within 0.1 seconds on a low-cost desktop computer. Meanwhile, the method has acceptable generalization capability in most cases from lower layers to higher layers in the same simulation, as well as from one simulation to a new simulation on different AM process parameters. More importantly, after fine-tuning the proposed method with limited experimental data, the relative errors of all predicted temperature profiles on a new experiment are smaller than 0.09, which demonstrates the applicability and generalization of the proposed two-stage thermal history prediction method in online applications for metal AM.

Yifan Tang, M. Rahmani Dehaghani, G. Gary Wang

Transfer learning (TL) based additive manufacturing (AM) modeling is an emerging field to reuse the data from historical products and mitigate the data insufficiency in modeling new products. Although some trials have been conducted recently, the inherent challenges of applying TL in AM modeling are seldom discussed, e.g., which source domain to use, how much target data is needed, and whether to apply data preprocessing techniques. This paper aims to answer those questions through a case study defined based on an open-source dataset about metal AM products. In the case study, five TL methods are integrated with decision tree regression (DTR) and artificial neural network (ANN) to construct six TL-based models, whose performances are then compared with the baseline DTR and ANN in a proposed validation framework. The comparisons are used to quantify the performance of applied TL methods and are discussed from the perspective of similarity, training data size, and data preprocessing. Finally, the source AM domain with larger qualitative similarity and a certain range of target-to-source training data size ratio are recommended. Besides, the data preprocessing should be performed carefully to balance the modeling performance and the performance improvement due to TL.

Pouyan Sajadi, Mostafa Rahmani Dehaghani, Yifan Tang et al.

Accurately predicting the temperature field in metal additive manufacturing (AM) processes is critical to preventing overheating, adjusting process parameters, and ensuring process stability. While physics-based computational models offer precision, they are often time-consuming and unsuitable for real-time predictions and online control in iterative design scenarios. Conversely, machine learning models rely heavily on high-quality datasets, which can be costly and challenging to obtain within the metal AM domain. Our work addresses this by introducing a physics-informed neural network framework specifically designed for temperature field prediction in metal AM. This framework incorporates a physics-informed input, physics-informed loss function, and a Convolutional Long Short-Term Memory (ConvLSTM) architecture. Utilizing real-time temperature data from the process, our model predicts 2D temperature fields for future timestamps across diverse geometries, deposition patterns, and process parameters. We validate the proposed framework in two scenarios: full-field temperature prediction for a thin wall and 2D temperature field prediction for cylinder and cubic parts, demonstrating errors below 3% and 1%, respectively. Our proposed framework exhibits the flexibility to be applied across diverse scenarios with varying process parameters, geometries, and deposition patterns.

Jiaxin Song, Xinyu Wang, Yihao Wang et al.

With the widespread use of social media, user-generated content has surged on online platforms. When such content includes hateful, abusive, offensive, or cyberbullying behavior, it is classified as toxic speech, posing a significant threat to the online ecosystem's integrity and safety. While manual content moderation is still prevalent, the overwhelming volume of content and the psychological strain on human moderators underscore the need for automated toxic speech detection. Previously proposed detection methods often rely on large annotated datasets; however, acquiring such datasets is both costly and challenging in practice. To address this issue, we propose an uncertainty-guided firewall for toxic speech in few-shot scenarios, U-GIFT, that utilizes self-training to enhance detection performance even when labeled data is limited. Specifically, U-GIFT combines active learning with Bayesian Neural Networks (BNNs) to automatically identify high-quality samples from unlabeled data, prioritizing the selection of pseudo-labels with higher confidence for training based on uncertainty estimates derived from model predictions. Extensive experiments demonstrate that U-GIFT significantly outperforms competitive baselines in few-shot detection scenarios. In the 5-shot setting, it achieves a 14.92\% performance improvement over the basic model. Importantly, U-GIFT is user-friendly and adaptable to various pre-trained language models (PLMs). It also exhibits robust performance in scenarios with sample imbalance and cross-domain settings, while showcasing strong generalization across various language applications. We believe that U-GIFT provides an efficient solution for few-shot toxic speech detection, offering substantial support for automated content moderation in cyberspace, thereby acting as a firewall to promote advancements in cybersecurity.

Yifan Tang, Yihao Wang, Ru Zhang et al.

To detect stego (steganographic text) in complex scenarios, linguistic steganalysis (LS) with various motivations has been proposed and achieved excellent performance. However, with the development of generative steganography, some stegos have strong concealment, especially after the emergence of LLMs-based steganography, the existing LS has low detection or cannot detect them. We designed a novel LS with two modes called LSGC. In the generation mode, we created an LS-task "description" and used the generation ability of LLM to explain whether texts to be detected are stegos. On this basis, we rethought the principle of LS and LLMs, and proposed the classification mode. In this mode, LSGC deleted the LS-task "description" and used the "causalLM" LLMs to extract steganographic features. The LS features can be extracted by only one pass of the model, and a linear layer with initialization weights is added to obtain the classification probability. Experiments on strongly concealed stegos show that LSGC significantly improves detection and reaches SOTA performance. Additionally, LSGC in classification mode greatly reduces training time while maintaining high performance.

Yifan Tang, M. Rahmani Dehaghani, Pouyan Sajadi et al.

Considering data insufficiency in metal additive manufacturing (AM), transfer learning (TL) has been adopted to extract knowledge from source domains (e.g., completed printings) to improve the modeling performance in target domains (e.g., new printings). Current applications use all accessible source data directly in TL with no regard to the similarity between source and target data. This paper proposes a systematic method to find appropriate subsets of source data based on similarities between the source and target datasets for a given set of limited target domain data. Such similarity is characterized by the spatial and model distance metrics. A Pareto frontier-based source data selection method is developed, where the source data located on the Pareto frontier defined by two similarity distance metrics are selected iteratively. The method is integrated into an instance-based TL method (decision tree regression model) and a model-based TL method (fine-tuned artificial neural network). Both models are then tested on several regression tasks in metal AM. Comparison results demonstrate that 1) the source data selection method is general and supports integration with various TL methods and distance metrics, 2) compared with using all source data, the proposed method can find a small subset of source data from the same domain with better TL performance in metal AM regression tasks involving different processes and machines, and 3) when multiple source domains exist, the source data selection method could find the subset from one source domain to obtain comparable or better TL performance than the model constructed using data from all source domains.