Author

Zijun Wang

Observed name: Wang, Zijun

Institutions: University of California, Santa Cruz, Hong Kong University of Science and Technology, Peking University, Northeastern University

Observed institutions: University of California, Santa Cruz, Hong Kong University of Science and Technology, Peking University, Northeastern University

OpenAlex ID: A5135337335

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

2026 · Minhua Lin, Juncheng Wu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 49

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

2026 · Zijun Wang, Haoqin Tu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 26

RedFlow: Redirect Failure into Action-level Corrections for Flow-matching VLA Policy

2026 · Yan, Zhengyang, Li, Junhao, et al. · arXiv (Cornell University) · 6

InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition

2026 · Liu, Fengze, Zhou, Weidong, et al. · arXiv (Cornell University) · 4

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

2026 · Chen, Hardy, Lau, Nancy, et al. · arXiv (Cornell University) · 2

Target-Oriented Pretraining Data Selection via Neuron-Activated Graph

2026 · Wang, Zijun, Tu, Haoqin, et al. · arXiv (Cornell University) · 2

Positive mass theorems for singular asymptotically hyperbolic manifolds

2026 · Shi, Yuguang, Sun, Chengzhang, et al. · arXiv (Cornell University)

Sharp Root Anti-Concentration via Projective Incidence and Ordered Root Laws

2026 · Wang, Zijun, Miao, Yuchen, et al. · arXiv (Cornell University)

Works count: 8

Citation count: 89

H-index: 4

I10-index: 2