Firebolt-VL introduces an LFM-based decoder and token-grid correlation to achieve linear-time vision-language inference with improved fine-grained grounding.
Align-kd: Distilling cross-modal alignment knowledge for mobile vision-language large model enhancement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
Firebolt-VL introduces an LFM-based decoder and token-grid correlation to achieve linear-time vision-language inference with improved fine-grained grounding.