✨LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

📝 Summary:
LumosX enhances text-to-video generation by improving face-attribute alignment and subject consistency. It uses a new data pipeline to infer subject dependencies and Relational Attention mechanisms to explicitly link subjects with attributes, achieving state-of-the-art personalized multi-subject ...

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.20192
• PDF: https://arxiv.org/pdf/2603.20192
• Project Page: https://jiazheng-xing.github.io/lumosx-home/
• Github: https://github.com/alibaba-damo-academy/Lumos-Custom

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#TextToVideo #VideoGeneration #PersonalizedAI #ComputerVision #DeepLearning

✨PersonaVLM: Long-Term Personalized Multimodal LLMs

📝 Summary:
PersonaVLM introduces a framework for long-term personalized multimodal LLMs. It remembers interactions, reasons multi-turn using retrieved memories, and aligns responses with evolving user personality. This novel method significantly outperforms baselines and GPT-4o on a new evaluation benchmark.

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: http://arxiv.org/abs/2604.13074
• PDF: https://arxiv.org/pdf/2604.13074
• Project Page: https://personavlm.github.io/
• Github: https://github.com/MiG-NJU/PersonaVLM

🔹 Models citing this paper:
• https://huggingface.co/ClareNie/PersonaVLM

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ClareNie/Persona-MME
• https://huggingface.co/datasets/ClareNie/PersonaVLM-Dataset

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #MultimodalAI #PersonalizedAI #AIResearch #MemoryAI