Constructive Apraxia: An Unexpected Limit of Instructible Vision-Language Models and Analog for Human Cognitive Disordersby…
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decodingby Doohyuk Jang, Sihwan Park, June Yong…
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Featuresby Benyuan Meng, Qianqian Xu,…
SteerDiff: Steering towards Safe Text-to-Image Diffusion Modelsby Hongxiang Zhang, Yifeng He, Hao ChenFirst submitted to…
Grounded Answers for Multi-agent Decision-making Problem through Generative World Modelby Zeyang Liu, Xinrui Yang, Shiguang…
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generationby Liang Chen,…
Data Extrapolation for Text-to-image Generation on Small Datasetsby Senmao Ye, Fei LiuFirst submitted to arxiv…
KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Modelsby Pouyan Navard, Amin Karimi Monsefi,…
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterionby…
GeoBiked: A Dataset with Geometric Features and Automated Labeling Techniques to Enable Deep Generative Models…