Jiwen Zhang

Evaluating multimodal large language models (MLLMs) is becoming increasingly expensive as benchmarks grow in scale and cross-modality complexity. Inspired by structuralism in cognitive psychology, we tackle this difficulty with an adaptive evaluation framework for efficient benchmarking, namely A...

Mobile GUI agents powered by large foundation models enable autonomous task execution in applications, but frequent updates that alter UI appearance and reorganize workflows cause agents trained on historical data to fail. Despite these surface changes, we observe that functional semantics and ta...