Tag
This paper introduces Evidence-Backed Video Question Answering (E-VQA), a new task requiring models to output both semantic answers and precise spatio-temporal evidence like tracked object segmentation masklets. The authors create a human-verified benchmark and a scalable training dataset, showing significant improvements over baselines.
VisualClaw is a self-evolving multimodal agent that reduces deployment costs through hybrid encoding and skill evolution, while improving video-QA accuracy across multiple benchmarks.