Get started
Author

Shumin Deng

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
2026 · Wang, Xuehai, Qin, Haowei, et al. · arXiv (Cornell University)
PDF
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
2026 · Wang, Mengru, Fang, Junfeng, et al. · arXiv (Cornell University)
PDF
Unsupervised Skill Discovery for Agentic Data Analysis
2026 · Qiu, Zhisong, Song, Kangqi, et al. · arXiv (Cornell University)
PDF
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
2026 · Association for Computational Linguistics 2026, Chen, Yijun, et al. · Underline Science Inc.
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
2026 · Association for Computational Linguistics 2026, Chen, Huajun, et al. · Underline Science Inc.
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
2026 · Association for Computational Linguistics 2026, Chen, Huajun, et al. · Underline Science Inc.
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
2026 · Association for Computational Linguistics 2026, Chen, Huajun, et al. · Underline Science Inc.
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
2026 · Yu, Zhuoyun, Xie, Xin, et al. · arXiv (Cornell University)
PDF
SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research
2026 · Qiao, Shuofei, Wei, Yunxiang, et al. · arXiv (Cornell University)
PDF
KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks
2026 · Xi, Zekun, Nie, Yichen, et al. · arXiv (Cornell University)
PDF
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
2026 · Xu, Haoming, Zhao, Ningyuan, et al. · arXiv (Cornell University)
PDF
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
2026 · Haoming Xu, Weihong Xu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Exploring Autonomous Agentic Data Engineering for Model Specialization
2026 · Yujie Luo, Xiangyuan Ru, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 13
Citation count:
H-index:
I10-index:
Year
Topic
Type