RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
Visiongpt: Vision-language understand- ing agent using generalized multimodal framework
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Introduces ProcedureVQA benchmark and Chain-of-Procedure framework that improves VLM next-step prediction in procedures by up to 13% over baselines.
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
DREAM introduces a two-stage adaptive multi-modal fusion framework that reaches BLEU-4 of 0.241 on DeepEyeNet for retinal image report generation and generalizes to ROCO.
citing papers explorer
-
RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
-
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
Introduces ProcedureVQA benchmark and Chain-of-Procedure framework that improves VLM next-step prediction in procedures by up to 13% over baselines.
-
GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
-
DREAM: Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion for Expert Precision Medical Report Generation
DREAM introduces a two-stage adaptive multi-modal fusion framework that reaches BLEU-4 of 0.241 on DeepEyeNet for retinal image report generation and generalizes to ROCO.