Stefan Lee

5

Papers

16

Total Citations

Papers (5)

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

Do Visual Imaginations Improve Vision-and-Language Navigation Agents?

Harnessing Input-Adaptive Inference for Efficient VLN

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles

Viewpoint-Aware Visual Grounding in 3D Scenes