2 papers
cs.CV2025
From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs
Mingxiao Li, Fang Qu, Zhanpeng Chen +5
While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pr…
cs.CV2025
Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding
Zhanpeng Chen, Mingxiao Li, Ziyang Chen +3
Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibitin…