3 papers
cs.LG2026
Intent-aligned Formal Specification Synthesis via Traceable Refinement
Zhe Ye, Aidan Z. H. Yang, Huangyuan Su +6
Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obt…
cs.LG2026
Learning Adaptive LLM Decoding
Chloe H. Su, Zhe Ye, Samuel Tenka +3
Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncer…
math.CT2025
Additive Invariants of Open Petri Nets
Benjamin Merlin Bumpus, Sophie Libkind, Jordy Lopez Garcia +2
We classify all additive invariants of open Petri nets: these are -valued invariants which are additive with respect to sequential and parallel composition of open Petr…