3 papers
cs.CV2026
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs
Ruichuan An, Kai Zeng, Ming Lu +5
Vision-Language Models (VLMs) have demonstrated exceptional performance in various multi-modal tasks. Recently, there has been an increasing interest in improving the personalizati…
cs.CV2026
PEARL: Personalized Streaming Video Understanding Model
Yuanhong Zheng, Ruichuan An, Xiaopeng Lin +10
Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimoda…
cs.CV2025
VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging
Ming Zhong, Yuanlei Wang, Liuzhou Zhang +7
While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who natu…