Researcher — paper.dinq.me

作者位次 #4/5ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Sparse Relaxed-Lasso Steering: Automatic Sparse Autoencoder Feature Selection for Precise Image Editing

Zongxin Liu · Xiaoyong Xue · Weidi Sun · Shengchao Qin · Lijun Zhang

可解释性多模态社会与人本OpenReview

作者位次 #9/10ACL 2026Workshop· ACL System Demonstrations

Formally Specifying the Intended Behavior of the Program: LLM -Driven Neuro-Symbolic Program Specification Synthesis

Cheng Wen · Hu Junjie · YiKun Hu · Jie Su · Bin Yu · Dugang Liu · Zhiwu Xu · Weidi Sun · Shengchao Qin · Cong Tian

摘要

Formal verification can provide strong mathematical guarantees about software correctness, but it typically requires developers to write detailed formal specifications (e.g., contracts and loop invariants), which is costly and error-prone. We introduce AutoSpec+, an LLM-driven neuro-symbolic demo...

评测与基准代码推理OpenReview 项目页

Shengchao Qin

获取完整研究档案

联系方式

2026 顶会论文

Sparse Relaxed-Lasso Steering: Automatic Sparse Autoencoder Feature Selection for Precise Image Editing

Formally Specifying the Intended Behavior of the Program: LLM -Driven Neuro-Symbolic Program Specification Synthesis

常见合作者