Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task LearnersZitian ChenYikang Shenet al.2023CVPR 2023
Visual Dependency Transformers: Dependency Tree Emerges from Reversed AttentionMingyu DingYikang Shenet al.2023CVPR 2023
SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World KnowledgeAndong WangBo Wuet al.2024CVPR 2024
Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction FollowingMingyu DingYan Xuet al.2022CORL 2022
A UNIFIED FRAMEWORK FOR MASKED AND MASK-FREE FACE RECOGNITION VIA FEATURE RECTIFICATIONShaozhe HaoChaofeng Chenet al.2022ICIP 2022