An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
In: Proceedings of the IEEE/cvf conference on computer vision and pattern recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Audit of KB-VQA benchmarks reveals systematic violations of answer derivability, question clarity, and visual disambiguation assumptions, with new repair and multi-entity augmentation protocols producing different model performance trends.
VLMs fine-tuned on a consistency-probed Visual-Idk dataset via SFT and preference optimization raise truthful rate from 57.9% to 67.3% and show internal evidence of genuine boundary recognition.
citing papers explorer
-
MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG
An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
-
Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
Audit of KB-VQA benchmarks reveals systematic violations of answer derivability, question clarity, and visual disambiguation assumptions, with new repair and multi-entity augmentation protocols producing different model performance trends.
-
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
VLMs fine-tuned on a consistency-probed Visual-Idk dataset via SFT and preference optimization raise truthful rate from 57.9% to 67.3% and show internal evidence of genuine boundary recognition.