🏢 University of Waterloo

LOCATEdit refines cross-attention maps with graph Laplacian regularization, achieving precise & localized text-guided image editing without artifacts.

VisualWebInstruct: Scales up multimodal instruction data via web search, enhancing VLMs’ reasoning for complex tasks.

AceCoder uses automated test-case synthesis to create a large-scale dataset for training reward models, enabling effective reinforcement learning to significantly boost code generation model performan…

VISTA synthesizes long-duration, high-resolution video instruction data, creating VISTA-400K and HRVideoBench to significantly boost video LMM performance.

OmniEdit, a novel instruction-based image editing model, surpasses existing methods by leveraging specialist supervision and high-quality data, achieving superior performance across diverse editing ta…