Author

Xiangtian Li

h-index 2 View on Semantic Scholar

We have 3 of 8 papers

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

Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable

Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and ne...

Zhichen Dong, Zhi-Xuan Liu, Yuanjiu Fan, et al. · 1 citation

Preprint Aug 2026

Certified Learning and Equilibrium Implementation under Opaque Partial Commitment

The original robust value frontier, support-wise linear-programming algorithm, and binary-action fractional-knapsack specialization are embedded into this implementation framework and embeds the original robust value frontier, support-wise linear-programming algorithm, and binary-action fractional-knapsack specializati...

Shuyan Zhang, Xiangtian Li · 0 citations

#machine learning Preprint Sep 2026

Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation

Trait-direction drift is proposed and validated as a mechanism for subliminal learning: biased generation creates measurable preference gaps in teacher data, and student-recognizable gaps induce trait-aligned updates during supervised fine-tuning that accumulate into behavioral transfer.

Zhi-Xuan Liu, Zhichen Dong, Yuanjiu Fan, et al. · 1 citation