Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders Paper β’ 2412.09586 β’ Published 27 days ago β’ 5 β’ 2
OLA-VLM: Elevating Visual Perception in Multimodal LLMs with Auxiliary Embedding Distillation Paper β’ 2412.09585 β’ Published 27 days ago β’ 10 β’ 2