4 papers
GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
Lingxiao Li, Max Whitton, Ledell Wu +1
Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure thi…
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Lingxiao Li, Yifan Wang, Xinyan Gao +3
Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language mo…
HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation
Lingxiao Li, Kaixuan Fan, Boqing Gong +1
Few-shot image generation aims to generate diverse and high-quality images for an unseen class given only a few examples in that class. A key challenge in this task is balancing ca…
BIFRÖST: 3D-Aware Image compositing with Language Instructions
Lingxiao Li, Kaixiong Gong, Weihong Li +4
This paper introduces Bifröst, a novel 3D-aware framework that is built upon diffusion models to perform instruction-based image composition. Previous methods concentrate on image…