XY
Xingrui Yu
cs.AIcs.LGstat.MLcs.CRcs.CVcs.ROcs.CLcs.SE
On Valency
published · living versionsW_n92rp5hh·v1 · currentpublished
LOGIV: Graph-Verified Execution with Causal Local Repair for Long-Horizon Robot Tasks
with Enqiao Lu, Yuxiang Xie, Yuyang Wang, Yipeng Gu +8
1 version
Preprints & journals
24 papers in the corpus · 2018–2026CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning2609.32750v1 · Xin Yan, Zhengbo Jiao, Jiaqi Liu et al.2026 · 0 citationsarXiv
SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models2608.27857v1 · Enqiao Lu, Xingrui Yu, Yiwei Fu et al.2026 · 0 citationsarXiv
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight2606.21399v2 · Chubin Zhang, Zhenglin Wan, Xingrui Yu et al.2026 · 0 citationsarXiv
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents2606.21409v1 · Chubin Zhang, Zhenglin Wan, Xingrui Yu et al.2026 · 0 citationsarXiv
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models2606.04945v2 · Xin Yan, Aqiang Wang, Zhenglin Wan et al.2026 · 0 citationsarXiv
Adversarial Dual On-Policy Distillation from Expressive Teacher2605.27095v2 · Zhenglin Wan, Jingxuan Wu, Xingrui Yu et al.2026 · 0 citationsarXiv
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models2605.09005v1 · Ming Sun, Rui Wang, Xingrui Yu et al.2026 · 0 citationsarXiv
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks2605.01293v1 · Jie-Jing Shao, Haiyan Yin, Yueming Lyu et al.2026 · 0 citationsarXiv
Advancing Analytic Class-Incremental Learning through Vision-Language Calibration2602.13670v3 · Binyu Zhao, Wei Zhang, Xingrui Yu et al.2026 · 0 citationsarXiv
HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models2602.13710v2 · Xin Yan, Zhenglin Wan, Feiyang Ye et al.2026 · 0 citationsarXiv
SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning2602.00743v1 · Xu Pan, Zhenglin Wan, Xingrui Yu et al.2026 · 0 citationsarXiv
Denoising Time Matters:Diverse Generation in Diffusion Language Models2601.22629v3 · Jingxuan Wu, Zhenglin Wan, Yuzhe Yang et al.2026 · 0 citationsarXiv
Reflection-Driven Control for Trustworthy Code Agents2512.21354v1 · Bin Wang, Jiazheng Quan, Xingrui Yu et al.2025 · 0 citationsarXiv
Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching2510.09060v2 · Jingxuan Wu, Zhenglin Wan, Xingrui Yu et al.2025 · 0 citationsarXiv
FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning2510.09222v3 · Zhenglin Wan, Jingxuan Wu, Xingrui Yu et al.2025 · 0 citationsarXiv
Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration2506.20307v1 · Heyang Zhao, Xingrui Yu, David M. Bossens et al.2025 · 0 citationsarXiv
Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection2503.01234v3 · Sijin Sun, Ming Deng, Xingrui Yu et al.2025 · 2 citationsarXiv
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration2411.06965v2 · Xingrui Yu, Zhenglin Wan, David Mark Bossens et al.2024 · 0 citationsarXiv
Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity2410.06151v4 · Zhenglin Wan, Xingrui Yu, David Mark Bossens et al.2024 · 0 citationsInternational Conference on Machine Learning (ICML 2025)
Intrinsic Reward Driven Imitation Learning via Generative Model2006.15061v4 · Xingrui Yu, Yueming Lyu, Ivor W. Tsang2020 · 27 citationsarXiv
Deep Adversarial Learning in Intrusion Detection: A Data Augmentation Enhanced Framework1901.07949v3 · He Zhang, Xingrui Yu, Peng Ren et al.2019 · 47 citationsarXiv
How does Disagreement Help Generalization against Label Corruption?1901.04215v3 · Xingrui Yu, Bo Han, Jiangchao Yao et al.2019 · 538 citationsarXiv
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust1809.11008v3 · Bo Han, Gang Niu, Xingrui Yu et al.2018 · 100 citationsarXiv
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels1804.06872v3 · Bo Han, Quanming Yao, Xingrui Yu et al.2018 · 1,620 citationsarXiv
Career total: 46 works. 24 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.