Author

Runqi Lin

Observed name: Lin, Runqi

Institutions: The University of Sydney, University of Oxford

Observed institutions: The University of Sydney, University of Oxford

ORCID: 0009-0000-6607-7754

Observed ORCID: 0009-0000-6607-7754

OpenAlex ID: A5102678196

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

2023 · Runqi Lin, Chaojian Yu, et al. · neural information processing systems · 12

PDF

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

2023 · Lin, Runqi, Yu, Chaojian, et al. · arXiv (Cornell University) · 3

PDF

Instance-Dependent Early Stopping for Adaptive Data Pruning

2026 · Suqin Yuan, Runqi Lin, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1

Instance-dependent Early Stopping

2025 · Yuan, Suqin, Lin, Runqi, et al. · arXiv (Cornell University) · 1

PDF

Decoupling Token Roles in Autoregressive Pretraining

2026 · Yuan, Suqin, Lin, Runqi, et al. · arXiv (Cornell University)

PDF

SEES: A Self-Evolving Embodied System via Failure-Guided VLA Policy Adaptation

2026 · Li, Ziwen, Zhang, Hanlue, et al. · arXiv (Cornell University)

PDF

Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment

2026 · Yuan, Suqin, Lin, Runqi, et al. · arXiv (Cornell University)

PDF

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

2026 · Ye, Tong, Han, Kunyang, et al. · arXiv (Cornell University)

PDF

AnisoLift: Anisotropic Latent Representations for Coarse Particle Liquid Enhancement

2026 · Gao, Zhengqing, Huang, Huaxi, et al. · arXiv (Cornell University)

PDF

Mobile-VTON: High-Fidelity On-Device Virtual Try-On

2026 · Wan, Zhenchen, Chen, Ce, et al. · arXiv (Cornell University)

PDF

Mirage2Matter: A Physically Grounded Gaussian World Model from Video

2026 · Gao, Zhengqing, Li, Ziwen, et al. · arXiv (Cornell University)

PDF

Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks

2025 · Lin, Runqi · arXiv (Cornell University)

PDF

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

2024 · Lin, Runqi, Yu, Chaojian, et al. · arXiv (Cornell University)

PDF

Works count: 14

Citation count: 17

H-index: 2

I10-index: 1