self-reward

Tag

Cards List
#self-reward

Mitigating Multimodal Hallucination via Phase-wise Self-reward

Hugging Face Daily Papers · 2026-04-20 Cached

PSRD framework halves multimodal hallucination in LVLMs by using phase-wise self-reward decoding and a distilled lightweight reward model without extra supervision.

0 favorites 0 likes
← Back to home

Submit Feedback