collaborators

7 papers

cs.LG2026

Terminal Symmetry as a Decision Resource: Statewise Refinement for Anytime Verified Construction

Yi Liu

Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent. We develop a decision-resource view of termina…

cs.AI2026

Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation

Yongkang Yang, Zhezheng Hao, Hong Zhang +8

On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation. Two recent research…

cs.LG2026

Learned, Relied Upon, or Necessary? Separating Checkpoint Dependence from Task-Level Value in Sheaf GNNs

Yi Liu

Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry. That conclusion does not follow from paramete…

cs.LG2026

Auditing Training Data in Generative Music Models via Black-Box Membership Inference

Yi Chen Liu, Jiawei Yu, Kexin Cao +3

Recent advances in text-to-music generation enable high-fidelity synthesis of structured musical audio, raising growing concerns about data provenance, consent, and training transp…

cs.LG2026

Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference

Yi Liu

Repeated sampling is a standard way to spend test-time compute, but its benefit is controlled by the latent distribution of correctness across examples, not by one-call accuracy al…

cs.PF2026

Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs

Yi Liu

Scaling laws relate model quality to compute budget (FLOPs), but practitioners face wall-clock time constraints, not compute budgets. We study optimal model sizing under fixed time…