GitHub - 52CV CVPR-2025-Papers When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach Domain Generalization in CLIP via Learning with Diverse Text Prompts
CVPR 2025 Accepted Papers Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning Poster Session 3
A Common Pitfall of Margin-based Language Model Alignment: Gradient . . . Formally, we derive conditions for general margin-based alignment objectives under which gradient entanglement becomes concerning: the inner product between the gradient of preferred log-probability and the gradient of dispreferred log-probability is large relative to the individual gradient norms
CVPR2025 Accepted Papers - CSDN博客 A Deep-Dive into the Vision of Vision Language Models Stop learning it all to mitigate visual hallucination, Focus on the hallucination target Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing Do We Always Need the Simplicity Bias?
Accepted Regular Papers | 2025 ACM Multimedia Accepted Papers 3783 CrossMind-VL: Multi-Subject Mind-to-Video Decoding with Multimodal LLM Semantic Grounding Xuanliu Zhu, Yiqiao Chai, Runnan Li, Mingying Lan, Li Gao 2254 HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection Jialei Cui, JianweiDu JianweiDu, Yanzhe Li, Lei Gao, Jiang Hui, Chenfu Bao 1458 Towards Generalized Physical
【CVPR 2025】 域适应 域泛化汇总 - 知乎 The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
[分享] [每日更新] [2025. 03. 03] [ArXiv CV Paper] - 知乎 On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models 警惕你的相册！ 关于多模态大型语言模型中的无意隐私记忆 https: github com hzphzp WeGen https: github com Lan1eve SVDC Pooya Mohammadi Kazaj, Giovanni Baj, Yazdan Salimi, Anselm W Stark, Waldo Valenzuela, George CM Siontis, Habib Zaidi, Mauricio Reyes etc
[分享] [每日更新] [2025. 03. 21] [ArXiv CV Paper] - 知乎 Beyond Accuracy: What Matters in Designing Well-Behaved Models? 超越准确性：设计良好行为模型的关键因素是什么？ OpenCity3D: What do Vision-Language Models know about Urban Environments? OpenCity3D：视觉-语言模型了解多少关于城市环境的信息？ Does a Rising Tide Lift All Boats? Bias Mitigation for AI-based CMR Segmentation 《涨潮是否都能扬帆？ 基于AI的CMR分割的偏差缓解》