MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models
arXiv:2610.08830v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across vision and language tasks. However, their massive computational and memory demands hinder real-world deployment. While recent efforts reduce costs by e…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-08 04:00 · arXiv cs.CV
MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models