SigLIP-HD by Fine-to-Coarse Supervision
High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-grained visual tokens. However, it introduces additional computational and design complexity, due to multiple forward passes and post-processing of increased tokens. Before simply adopting a higher resolution, have we truly unlocked the model's full perception capability at a standard resolution? Therefore, we study an interesting problem: how to achieve fine visual perception under lower cost without larger images.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%New Server Hopes to Break Through AI’s “Memory Wall” →
- PossiblePossibly related (embedding) · 49%Would having a dedicated programming language specifically for LLMs be a viable solution? [D] →
- PossiblePossibly related (embedding) · 48%voxel51/fiftyone →
- PossiblePossibly related (embedding) · 47%Atomic-man007/Awesome_Multimodel_LLM →
- PossiblePossibly related (embedding) · 47%Introducing Gemma 4 12B: a unified, encoder-free multimodal model →
- LinkedLinked via arxiv author · 85%Lihe Yang →
“SigLIP-HD by Fine-to-Coarse Supervision”
- LinkedLinked via arxiv author · 85%Zhen Zhao →
“SigLIP-HD by Fine-to-Coarse Supervision”
- LinkedLinked via arxiv author · 85%Hengshuang Zhao →
“SigLIP-HD by Fine-to-Coarse Supervision”