← Search

Qian Fu

2 accepted papers

2026

EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question Answering

ICML 2026poster

Knowledge-based Visual Question Answering (KB-VQA) remains a challenging task, particularly when queries require precise identification and grounding of fine-grained entities within large-scale knowledge base. Existing methods often treat visual and textual signals in isolation and rely heavily on i…

Cited by 0SourceScholar
2025

MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs

EMNLP 2025

Multimodal Multi-hop question answering requires integrating information from diverse sources, such as images and texts, to derive answers. Existing methods typically rely on sequential retrieval and reasoning, where each step builds on the previous output. However, this single-path paradigm makes t

Cited by 0SourcePDFScholar