BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.25891v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may only appear in local regions. On-policy self-distillation (OPD) enables transferring privileged…

aiscience

Sources

• T1BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal PerceptionarXiv24 Sept, 04:00