Yaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan, Zhongyu Ouyang, Chiyu Ma, Soroush Vosoughi. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In advanced technology nodes, Current Source Models (CSMs) are widely adopted due to their high accuracy. However, IR-drop–induced supply voltage fluctuations increase the computational burden of CSM-based timing analysis. Existing machine-learning (ML) approaches accelerate CSM evaluation by assuming fixed receiver capacitance along the path, which contradicts the variable-load dependency inherent to CSM formulation. In this work, we propose GoG-Predict, a fast and accurate IR-aware path waveform prediction framework. GoG-Predict employs a Graph-of-Graphs (GoG) Neural Network to model the structured interactions among driver cells, load nets, and receiver cells. In addition, a Feature-wise Linear Modulation (FiLM) mechanism is incorporated to account for the impact of IR drop on output waveform. We evaluate GoG-Predict on open-source designs using a commercial 12nm technology. Experimental results show an average waveform error of 2.03% and a 1426 × runtime speedup over HSPICE, while achieving 1.63 × higher accuracy compared with state-of-the-art ML-based prediction methods.

Nüshu is an endangered language from Jiangyong County, China, and the world's only known writing system created and used exclusively by women.Recent Natural Language Processing (NLP) work has digitized small Nüshu-Chinese corpora, but the script remains computationally inaccessible due to its handwritten, mixedmedia form and dearth of multimodal resources.We address this gap with two novel datasets: NüshuVision, an image corpus of 500 rendered sentences in traditional vertical, right-to-left orthography, and NüshuStrokes, the first sequential handwriting recordings of all 397 Unicode Nüshu characters by an expert calligrapher.Evaluating five state-of-the-art Chinese Optical Character Recognition (OCR) systems on NüshuVision shows that all fail entirely, each yielding a Character Error Rate (CER) of 1.0.Fine-tuning Microsoft's TrOCR on NüshuVision lowers CER to 0.67, a modest yet meaningful improvement.These contributions establish the first multimodal foundation for Nüshu revitalization and offer a culturally grounded framework for language preservation.

In modern social media, recommender systems (RecSys) rely on the click-through rate (CTR) as the standard metric to evaluate user engagement. CTR prediction is traditionally framed as a binary classification task to predict whether a user will interact with a given item. However, this approach overlooks the complexity of real-world social modeling, where user, item, and their interactive features change dynamically in fast-paced online environments. This dynamic nature often leads to model instability, reflected in overfitting short-term fluctuations rather than higher-level interactive patterns. While overfitting calls for more scaled and refined supervisions, current solutions often rely on binary labels that overly simplify fine-grained user preferences through the thresholding process, which significantly reduces the richness of the supervision. Therefore, we aim to alleviate the overfitting problem by increasing the supervision bandwidth in CTR training. Specifically, (i) theoretically, we formulate the impact of fine-grained preferences on model stability as a Lipschitz constrain; (ii) empirically, we discover that scaling the supervision bandwidth can act as an implicit Lipschitz regularizer, stably optimizing existing CTR models to achieve better generalizability. Extensive experiments show that this scaled supervision significantly and consistently improves the optimization process and the performance of existing CTR models, even without the need for additional hyperparameter tuning.

Relational learning has gained significant attention, led by the expressiveness of Graph Neural Networks (GNNs) on graph data. While the inherent biases in common graph data are involved in GNN training, it poses a serious challenge to constraining the GNN output perturbations induced by input biases, thereby safeguarding fairness during training. The Lipschitz bound, a technique from robust statistics, can limit the maximum changes in the output concerning the input, taking into account associated irrelevant biased factors. It is an efficient and provable method to examine the output stability of machine learning models without incurring additional computational costs. Recently, its use in controlling the stability of Euclidean neural networks, the calculation of the precise Lipschitz bound remains elusive for non-Euclidean neural networks like GNNs, especially within fairness contexts. However, no existing research has investigated Lipschitz bounds to shed light on stabilizing the GNN outputs, especially when working on graph data with implicit biases. To narrow this gap, we begin with the general GNNs operating on relational data, and formulate a Lipschitz bound to limit the changes in the output regarding biases associated with the input. Additionally, we theoretically analyze how the Lipschitz bound of a GNN model could constrain the output perturbations induced by biases learned from data for fairness training. We experimentally validate the Lipschitz bound's effectiveness in limiting biases of the model output. Finally, from a training dynamics perspective, we demonstrate why the theoretical Lipschitz bound can effectively guide the GNN training to better trade-off between accuracy and fairness.

Graph neural networks (GNNs) have shown considerable promise for graph-structured data. However, they are also known to be unstable and vulnerable to perturbations and attacks. Recently, the Lipschitz constant has been adopted as a control on the stability of Euclidean neural networks, but calculating the exact constant is also known to be difficult even for very shallow networks. In this paper, we extend the Lipschitz analysis to graphs by providing a systematic scheme for estimating upper bounds of the Lipschitz constants of GNNs. We also derive concrete bounds for widely used GNN architectures including GCN, GraphSAGE and GAT. We then use these Lipschitz bounds for regularized GNN training for improved stability. Our numerical results on Lipschitz regularization of GNNs not only illustrate enhanced test accuracy under random noise, but also show consistent improvement for state-of-the-art defense methods against adversarial attacks.