ID-Align improves high-resolution VLM performance by reusing thumbnail position IDs for high-resolution image tokens, yielding small but positive gains on several benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models
ID-Align improves high-resolution VLM performance by reusing thumbnail position IDs for high-resolution image tokens, yielding small but positive gains on several benchmarks.