arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. […]

[Submitted on 10 Jan 2025 (v1), last revised 22 Jul 2025 (this version, v2)] View a PDF of the paper titled EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model, by Shengqi Dang and 5 other authors View PDF HTML (experimental) Abstract:Recent research shows that emotions can enhance users’ cognition and influence information communication. While research on

[Submitted on 10 Jul 2025 (v1), last revised 22 Jul 2025 (this version, v2)] View a PDF of the paper titled IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning, by Jaeheun Jung and 3 other authors View PDF HTML (experimental) Abstract:With the growth of demand on neural network compression methods, the structured pruning

arXiv:2507.16695v1 Announce Type: cross Abstract: The DEDICOM algorithm provides a uniquely interpretable matrix factorization method for symmetric and asymmetric square matrices. We employ a new row-stochastic variation of DEDICOM on the pointwise mutual information matrices of text corpora to identify latent topic clusters within the vocabulary and simultaneously learn interpretable word embeddings. We introduce a

[Submitted on 30 Dec 2022 (v1), last revised 22 Jul 2025 (this version, v3)] View a PDF of the paper titled Learning from Data Streams: An Overview and Update, by Jesse Read and Indr\.e \v{Z}liobait\.e View PDF HTML (experimental) Abstract:The literature on machine learning in the context of data streams is vast and growing. However,

arXiv:2507.16746v1 Announce Type: cross Abstract: Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual CoT), is challenging due to: (1) poor off-the-shelf visual CoT performance, which hinders reinforcement learning, and (2) the lack of high-quality visual

[Submitted on 2 Aug 2024 (v1), last revised 22 Jul 2025 (this version, v4)] View a PDF of the paper titled FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation, by Xiang Gao and 1 other authors View PDF Abstract:Large-scale text-to-image diffusion models have been a revolutionary milestone in the

[Submitted on 25 Apr 2025 (v1), last revised 22 Jul 2025 (this version, v2)] View a PDF of the paper titled A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1, by Mingda Zhang and 1 other authors View PDF HTML (experimental) Abstract:Despite significant advances in foundation models like

[Submitted on 22 May 2025 (v1), last revised 22 Jul 2025 (this version, v2)] View a PDF of the paper titled Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models, by Yue Li and 5 other authors View PDF HTML (experimental) Abstract:With the increasing size of Large Vision-Language Models (LVLMs), network pruning

[Submitted on 19 Jul 2025 (v1), last revised 22 Jul 2025 (this version, v2)] Authors:Xiaolin Yan, Yangxing Liu, Jiazhang Zheng, Chi Liu, Mingyu Du, Caisheng Chen, Haoyang Liu, Ming Ding, Yuan Li, Qiuping Liao, Linfeng Li, Zhili Mei, Siyu Wan, Li Li, Ruyi Zhong, Jiangling Yu, Xule Liu, Huihui Hu, Jiameng Yue, Ruohui Cheng, Qi