Author

Yulin Chen

Observed names: Chen, Y, Chen, Yulin

Institutions: National University of Singapore, National University of Defense Technology, Zhejiang University

Observed institutions: National University of Singapore, National University of Defense Technology, Zhejiang University

OpenAlex ID: A5136570826

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

2026 · Zeyuan Wang, Da Li, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?

2025 · He, Yufei, Li, Yuexin, et al. · arXiv (Cornell University) · 1

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

2026 · Sun, Qi, Zhang, Siyue, et al. · arXiv (Cornell University)

Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

2026 · Wang, Zeyuan, Li, Da, et al. · arXiv (Cornell University)

The Unlearnability Phenomenon in RLVR for Language Models

2026 · Chen, Yulin, He, He, et al. · arXiv (Cornell University)

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

2026 · Cao, Tri, Chen, Yulin, et al. · arXiv (Cornell University)

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

2026 · Sui, Yuan, Chen, Yulin, et al. · arXiv (Cornell University)

Causal Discovery as Dialectical Aggregation: A Quantitative Argumentation Framework

2026 · Wei, Sheng, Chen, Yulin, et al. · arXiv (Cornell University)

Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents

2026 · Liu, Yizhou, Sun, Qi, et al. · arXiv (Cornell University)

Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrödinger Bridge

2026 · Gong, Yuehu, Wang, Zeyuan, et al. · arXiv (Cornell University)

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

2026 · Association for Artificial Intelligence 2026, Bai, Liang, et al. · Underline Science Inc.

Deep Learning-Enabled Drywall Classification for C&D Waste: A Recycling-Oriented Dataset

2026 · Yulin Chen, Shenzhou Dai, et al.

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

2025 · Zhang, Anqi, Chen, Yulin, et al. · arXiv (Cornell University)

High spatiotemporal Resolution free-breathing quantitative bowel perfusion imaging

2019 · Obmann, Verena Carola, Yang, K, et al. · Bern Open Repository and Information System (University of Bern)

Works count: 14

Citation count: 3

H-index: 1

I10-index: