5 papers
PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Changguo Jia, Zhiyou Xiao, Xinbei Ma +5
Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We intro…
VeriSkill: A Self-Evolution Framework for Program Verification Skills
Changguo Jia, Tianqi Zhao, Zhiyou Xiao +2
Automating program verification with LLM agents requires generating specifications, annotations, auxiliary lemmas, and tool invocations, all of which depend on reusable skills. A n…
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Changguo Jia, Tianqi Zhao, Runzhi He +1
Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing artifacts whose identities, ver…
Do All Vision Transformers Need Registers? A Cross-Architectural Reassessment
Spiros Baxevanakis, Platon Karageorgis, Ioannis Dravilas +1
Training Vision Transformers (ViTs) presents significant challenges, one of which is the emergence of artifacts in attention maps, hindering their interpretability. Darcet et al. (…
Code Clone Detection via an AlphaFold-Inspired Framework
Changguo Jia, Yi Zhan, Tianqi Zhao +2
Code clone detection plays a critical role in software maintenance and vulnerability analysis. Substantial methods have been proposed to detect code clones. However, they struggle…