2 papers
cs.LG2025
DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities
Jueqing Lu, Yuanyuan Qi, Xiaohao Yang +8
The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete infor…
cs.CL2024
How Can I Improve? Using GPT to Highlight the Desired and Undesired Parts of Open-ended Responses
Jionghao Lin, Eason Chen, Zeifei Han +5
Automated explanatory feedback systems play a crucial role in facilitating learning for a large cohort of learners by offering feedback that incorporates explanations, significantl…