Tag
This paper presents AREA, a training-free inference-time method that adaptively allocates evidence highlighting in multimodal large language models, improving performance on knowledge-based visual question answering and standard multimodal benchmarks.
KBMR is an MLLM-based retriever for knowledge-based visual question answering that uses semantic alignment to improve retrieval and VQA accuracy, showing significant gains over CLIP baselines.
This paper introduces Bayesian Data Reweighting, a probabilistic framework that adaptively weights query-document pairs to mitigate false negatives in contrastive training, improving multimodal retrieval across multiple knowledge-based VQA benchmarks.
This paper proposes a training-free 'identify-before-answer' (IBA) framework for Knowledge-Based Visual Question Answering (KB-VQA) that decouples entity identification from evidence ranking, outperforming fine-tuned multi-modal retrieval-augmented generation baselines while reducing complexity.