English(EN) From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme

新框架HUMOR通过分层推理增强VLM表情包生成

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了一个名为HUMOR的新颖框架，以增强视觉语言模型（VLM）生成幽默表情包的能力。该框架采用分层、多路径的思维链（CoT）方法，允许模型根据上下文探索不同的推理路径并识别模板级意图。此外，HUMOR还包含一个基于具有相似模板的表情包组进行训练的成对奖励模型，以使VLM的输出与主观人类偏好保持一致，从而提高推理多样性和表情包质量。 AI

影响这项研究引入了一种新颖的多模态生成方法，有望提高AI理解和创作幽默等主观内容的能力。

排序理由该集群包含一篇学术论文，详细介绍了一种用于VLM表情包生成的新框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种用于VLM表情包生成的新框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Xueyan Li, Yingyi Xue, Mengjie Jiang, Qingzi Zhu, Yazhe Niu · 2026-10-28 04:00

从感知到笑点：用野外表情包的艺术赋能VLM

arXiv:2512.24555v4 Announce Type: replace Abstract: Generating humorous memes is a challenging multimodal task that moves beyond direct image-to-caption supervision. It requires a nuanced reasoning over visual content, contextual cues, and subjective humor. To bridge this gap bet…

本文如何被排名

报道来源 [1]

从感知到笑点：用野外表情包的艺术赋能VLM

相关实体

相关话题