7 papers · 1 filter
Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
Zirui Zheng, Takashi Isobe, Tong Shen +12
Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the…
PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization
Ying Tang, Dong Li, Youjia Zhang +3
Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent i…
Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
Mengmeng Ge, Takashi Isobe, Xu Jia +7
Understanding physical transformation processes is crucial for both human cognition and artificial intelligence systems, particularly from an egocentric perspective, which serves a…
E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources
Tong Shen, Jingai Yu, Dong Zhou +2
Diffusion models have shown strong capabilities in generating high-quality images from text prompts. However, these models often require large-scale training data and significant c…
AMD-Hummingbird: Towards an Efficient Text-to-Video Model
Takashi Isobe, He Cui, Dong Zhou +3
Text-to-Video (T2V) generation has attracted significant attention for its ability to synthesize realistic videos from textual descriptions. However, existing models struggle to ba…
ReNeg: Learning Negative Embedding with Reward Guidance
Xiaomin Li, Yixuan Liu, Takashi Isobe +8
In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative em…