Author

Yang Liu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space

Autoregressive Thought Flow is introduced, which models the next continuous thought as a multimodal distribution, and suggests that continuous reasoning is more effective when multiple possible next thoughts remain available rather than being collapsed into a single prediction.

Yang Li, Yi Wang, Shinda Huang et al. · 0 citations

#machine learning Mar 2026

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics

SaFeR-Steer, a progressive multi-turn alignment framework that combines staged synthetic bootstrapping with tutor-in-the-loop GRPO to train a single student under adaptive, on-policy attacks, is proposed and released.

Haolong Hu, Hanyu Li, Tian-Cheng He et al. · arXiv.org · 0 citations