Ada Chen, Yongjiang Wu, Junyuan Zhang, Jingyu Xiao, Shu Yang, Jen-tse Huang, Kun Wang, Wenxuan Wang, Shuai Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Two families of sets F and G are said to be cross s -union if for any F ∈ F and G ∈ G , | F ∪ G | ≤ s . In 2021, Frankl and Wong proved that if F , G ⊆ 2 [ n ] are non-empty cross s -union, then | F | + | G | ≤ ∑ i = 0 s n i + 1 . Moreover, for s < n − 1 , equality holds if and only if F , G = { 0̸ } , { G ⊆ [ n ] : | G | ≤ s } . In this paper, we give a new method to prove this result. Our method also allows us to establish a vector space version and a hereditary family extension. As a byproduct, we revisit the vector space version of the Katona s -union theorem due to Frankl and Tokushige, and characterize the extremal families for the case s = n − 1 .

The rapid growth of audio-centric platforms and applications such as Whatsapp and Twitter has transformed the way people communicate and share audio content in modern society. However, these platforms are increasingly misused to disseminate harmful audio content, such as hate speech, deceptive advertisements, and explicit material, which can have significant negative consequences (e.g., detrimental effects on mental health). In response, researchers and practitioners have been actively developing and deploying audio content moderation tools to tackle this issue. Despite these efforts, malicious actors can bypass moderation systems by making subtle alterations to audio content, such as modifying pitch or inserting noise. Moreover, the effectiveness of modern audio moderation tools against such adversarial inputs remains insufficiently studied. To address these challenges, we propose MTAM, a Metamorphic Testing framework for Audio content Moderation software. Specifically, we conduct a pilot study on 2000 audio clips and define 14 metamorphic relations across two perturbation categories: Audio Features-Based and Heuristic perturbations. MTAM applies these metamorphic relations to toxic audio content to generate test cases that remain harmful while being more likely to evade detection. In our evaluation, we employ MTAM to test five commercial textual content moderation software and an academic model against three kinds of toxic content. The results show that MTAM achieves up to 38.6%, 18.3%, 35.1%, 16.7%, and 51.1% error finding rates (EFR) when testing commercial moderation software provided by Gladia, Assembly AI, Baidu, Nextdata, and Tencent respectively, and it obtains up to 45.7% EFR when testing the state-of-the-art algorithms from the academy. In addition, we leverage the test cases generated by MTAM to retrain the model we explored, which largely improves model robustness (nearly 0% EFR) while maintaining the accuracy on the original test set. We release the code and experiment data to facilitate future research1.

This paper presents a novel and robust descriptor, depth-projection-map-based bag of contour fragments, which is applied to extraction of hand shape and structure information from depth maps. Our method projects depth maps onto three orthogonal planes to generate the depth projection maps. Then, the bag of contour fragment descriptors are extracted from the three depth projection maps and concatenated as a final shape representation of the original depth data. A support vector machine with a linear kernel is used as a shape classifier. The proposed description method is evaluated on three public datasets, as well as a new and more challenging dataset for hand gesture recognition. Results demonstrate that the proposed method significantly outperforms the previous methods on all tested datasets for both static digit recognition and letter gesture recognition. For the challenging HUST-ASL dataset, in particular, the proposed method improves on the previous state-of-the-art methods from 40.1% to 64.6%.