Skip to content
arXiv cs.CV · Papers

From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering

arXiv:2511.11132v3 Announce Type: replace Abstract: Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit k