AsyMoE adds hyperbolic geometry for cross-modal hierarchies and evidence-priority experts to address vision-language asymmetry in LVLMs, reporting 1.5% average gains and 25.45% fewer active parameters.
arXiv:2401.17221
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
EchoVLM applies a Mixture-of-Experts vision-language model to ultrasound imaging across seven body regions, reporting gains of 10.15 BLEU-1 and 4.77 ROUGE-1 over Qwen2-VL on report generation.
citing papers explorer
-
Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models
AsyMoE adds hyperbolic geometry for cross-modal hierarchies and evidence-priority experts to address vision-language asymmetry in LVLMs, reporting 1.5% average gains and 25.45% fewer active parameters.
-
EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
EchoVLM applies a Mixture-of-Experts vision-language model to ultrasound imaging across seven body regions, reporting gains of 10.15 BLEU-1 and 4.77 ROUGE-1 over Qwen2-VL on report generation.