Retrofitting Recurrent Vision-Language Models from Pretrained Backbones

Madhav Iyengar, Andreas Geiger, Hilde Kühne

Prunes layers from a pretrained vision-language model, then loops the remaining middle block with a learned adapter. Uses text training, projector realignment, and visual instruction tuning to recover performance; on TinyLLaVA, the resulting model improves reasoning benchmarks with fewer language-model parameters.

First public: October 15, 2026 · Added to this list: October 26, 2026