6 papers
Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction
Yi Liu
Many sequential construction tasks have exact terminal symmetries even though execution is directed and depends on history. Process evidence supplies order. Terminal correspondence…
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…
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…
Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference
Yi Liu
Repeated sampling can improve LLM accuracy, and quantifying the gains from additional calls is essential for allocating test-time compute. We study binary decisions, a fundamental…
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…
P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis
Feifan Song, Bofei Gao, Yifan Song +6
Large Language Models (LLMs) are expected to produce safe, helpful, and honest content during interaction with human users, but they frequently fail to align with such values when…