3 papers
cs.PL2026
Well-Typed ComfyUI Cannot Go Wrong: Gradual Refinement Types for Generative-AI Workflow Graphs
Pingchuan Ma, Zhantong Xue, Hui Li +4
Generative-AI workflows are programs assembled from independently developed models and operators. Their correctness depends on relationships among model families, tensor geometry,…
cs.SE2026
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Pingchuan Ma, Zhaoyu Wang, Zimo Ji +5
Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external tools and environments. However, their autonomy poses significant…
cs.CR2026
ZK-Value: A Practical Zero-Knowledge System for Verifiable Data Valuation
Zhaoyu Wang, Pingchuan Ma, Zhantong Xue +4
Data valuation is a foundational task in data marketplaces, where a Shapley-value attribution determines how a buyer's payment is distributed among data providers. Typically, the m…