GRIP uses contrastive training on LMM feedback to retrieve beneficial in-context examples for multimodal tasks, outperforming similarity-based methods and transferring across models including GPT-4o.
Demonstration selection for in-context learning via reinforcement learning.arXiv preprint arXiv:2412.03966,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models
GRIP uses contrastive training on LMM feedback to retrieve beneficial in-context examples for multimodal tasks, outperforming similarity-based methods and transferring across models including GPT-4o.