Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Scaffolding Minds lifts latent multimodal reasoning by 5.6 points across nine visual benchmarks.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #vision-encoder
Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models
CIRA induces LVLM failures only after visual-token compression, with a 20.35% mean failure rate.