Yingjin Song — accepted AI-conference papers

2025

Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?

Yingjin Song, Yupei Du, Denis Paperno, Albert Gatt

ACL 2025finding

This paper introduces the TempVS benchmark, which focuses on temporal grounding and reasoning capabilities of Multimodal Large Language Models (MLLMs) in image sequences. TempVS consists of three main tests (i.e., event relation inference, sentence ordering and image ordering), each accompanied with…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Disentangling the Roles of Representation and Selection in Data Pruning

Yupei Du, Yingjin Song, Hugh Mee Wong, Daniil Ignatev, Albert Gatt, Dong Nguyen

ACL 2025long

Data pruning—selecting small but impactful subsets—offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This limits future developments. In this work, we decompose data pruni…

Cited by 0 Source ↗PDF ↗Scholar ↗