2024.07.26 [24’ ICLR] Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models Language Hallucination Interpretability
2024.07.10 [22’ ECCV] MaskCLIP: Extract Free Dense Labels from CLIP Multimodal Contrastive Learning Zero-shot Segmentation
2024.07.09 [24’ ICML] Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation Multimodal Contrastive Learning Zero-shot Segmentation
2024.07.08 [23’ CVPR] Teaching Matters: Investigating the Role of Supervision in Vision Transformers Vision Analysis ViT
2024.07.08 [22’ CVPR] Splicing ViT Features for Semantic Appearance Transfer Vision Analysis Self-supervised Learning Style Transfer