Author

Jiahang Xie

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.

Preprint Aug 2026

Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning

Step-Level On-Policy Distillation is proposed, which combines the long-horizon correction of supervised fine-tuning (SFT) with the on-policy advantage of OPD to provide step-level supervision over complete student-generated trajectories and substantially outperforms conventional SFT and OPD.

Changhui Sun, Lan-Bo Liu, Hang Lei et al. · 2 citations

Preprint Aug 2026

MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models

MDLMPE is the first method to make positional representations explicitly aware of the changing revealed/masked configuration, and the complete combination of availability state, Gaussian locality, spectral basis, and embedding injection yields the strongest result.

Tong-Tong Ling, Hang Lei, Feng Xiao et al. · 0 citations