Yapeng Mi — accepted AI-conference papers

2026

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

Yapeng Mi, Yanpeng Zhao, Hengli Li, Chenxi Li, Huimin Wu, Xiaojian Ma +3

ICLR 2026poster

Reasoning-augmented machine learning systems have shown improved performance in various domains, including image generation. However, existing reasoning-based methods for image generation either restrict reasoning to a single modality (image or text) or rely on high-quality reasoning data for fine-t…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Pengxiang Li, Zhi Gao, Bofei Zhang, Yapeng Mi, Xiaojian Ma, Chenrui Shi +5

NeurIPS 2025poster

Multimodal agents, which integrate a controller (e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extens…

Cited by 0 Source ↗Scholar ↗