2 papers
cs.CV2025
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Bowen Chen, Mengyi Zhao, Haomiao Sun +4
Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermin…
cs.CV2025
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding
Liping Yuan, Jiawei Wang, Haomiao Sun +2
We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior genera…