Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
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…
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
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…