HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MFMDQwen is the first open-source LLM for multilingual financial misinformation detection, backed by a new instruction dataset and benchmark on which it outperforms other open-source models.
citing papers explorer
-
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
-
MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model
MFMDQwen is the first open-source LLM for multilingual financial misinformation detection, backed by a new instruction dataset and benchmark on which it outperforms other open-source models.