Guangcan Mai — accepted AI-conference papers

2026

Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation

Junjie Wang, 星华娄, Xiangtai Li, Ye Tian, Keyu Chen, Yulin Li +5

ICML 2026poster

Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual …

Cited by 0 Source ↗Scholar ↗

2026

Grasp Any Region: Prompting MLLM to Understand the Dense World

Haochen Wang, Yuhao Wang, Tao Zhang, Yikang Zhou, Yanwei Li, Jiacong Wang +10

ICLR 2026poster

While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle with the dense world, i.e., complex scenes requiring fine-grained analysis of intricate details and object inter-relationships. Region-level MLLMs have been a promising step. However, previous attempts are…

Cited by 0 Source ↗code ↗Scholar ↗