Jiaoyang Ruan — accepted AI-conference papers

2026

MacTok: Robust Continuous Tokenization for Image Generation

Hengyu Zeng, Xin Gao, Guanghao Li, Yuxiang Yan, Jiaoyang Ruan, Junpeng Ma +2

CVPR 2026

Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using fewer tokens, where the encoder fails to encode informative f

Cited by 0 Source ↗Scholar ↗

2026

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

Jiaoyang Ruan, Xin Gao, Yinda Chen, Hengyu Zeng, Liang Du, Guanghao Li +2

ICML 2026poster

While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geometric perspective: Reasoning on the Manifold. We hypothesiz…

Cited by 0 Source ↗Scholar ↗