Yiyuan Zhang

Native-Resolution Image Synthesis

Towards Continual Domain Adaptation of Vision-language Models

Debiasing Text-to-image Diffusion Models with Self-discovering Latent Directions

Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities

Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines

From Language to 3D Worlds: Adapting Language Models for Point Cloud Perception

Text-to-3D Generation with Bidirectional Diffusion using both 3D and 2D priors

Towards Unified and Effective Domain Generalization

Meta-Transformer: A Unified Framework for Multimodal Learning

Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities