AI RESEARCH
Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM
arXiv CS.CV
•
ArXi:2603.08800v1 Announce Type: new Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon