Rethinking Projector Training in Multimodal LLMs
PORTAL initializes multimodal projectors from summary statistics and matches caption-trained alignment without paired data.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #projector
Selective Channel Restoration for Backdoored Vision-Language Models
Post-training defense restores fragile VLM projector channels, driving backdoor success near zero without inference overhead.