3 papers
cs.CL2026
Continuous Language Diffusion as a Decoder-Interface Problem
Zhicheng Du, Lan Ma
Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diffusion language models can generate fluent text from them. We study this puzzle t…
cs.CV2025
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
Muyao Yuan, Yuanhong Zhang, Weizhan Zhang +4
Recently, the strong generalization ability of CLIP has facilitated open-vocabulary semantic segmentation, which labels pixels using arbitrary text. However, existing methods that…
cs.CV2025
LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
Tao Sun, Oliver Liu, JinJin Li +1
Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring res…