Author

Zhiyuan Li

Observed name: Li, Zhiyuan

Institutions: Jilin University, University of Macau, The Ohio State University, Aalto University

Observed institutions: Jilin University, University of Macau, The Ohio State University, Aalto University

OpenAlex ID: A5138726122

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

2026 · NeoHorse Team, Cao, Guoliang, et al. · arXiv (Cornell University)

PDF

EditaLive! Unified Character Video Editing for Live Streaming

2026 · Li, Zhiyuan, Pun, Chi-Man, et al. · arXiv (Cornell University)

PDF

CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval

2026 · Li, Zhiyuan, Gao, Linyuan, et al. · arXiv (Cornell University)

PDF

ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models

2026 · Zhang, Zhengshu, Li, Zhiyuan · arXiv (Cornell University)

PDF

Kimi K3: Open Frontier Intelligence

2026 · Kimi Team, Bai, Tongtong, et al. · arXiv (Cornell University)

PDF

Context-Adaptive Inference: A Unified Statistical and Foundation-Model View

2026 · Yao, Yue, Ellington, Caleb N., et al. · arXiv (Cornell University)

PDF

QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration

2026 · Zhou, Shen, Zhang, Jinghui, et al. · arXiv (Cornell University)

PDF

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

2026 · Chen, Jialei, Wang, Kai, et al. · arXiv (Cornell University)

PDF

A Theoretical Framework for Self-Play Theorem Proving Algorithms

2026 · Chen, Thomas, Li, Zhiyuan · arXiv (Cornell University)

PDF

Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization

2026 · Zhao, Rongzhen, Li, Zhiyuan, et al. · arXiv (Cornell University)

PDF

Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence

2026 · Li, Zhiyuan, Zhao, Rongzhen, et al. · arXiv (Cornell University)

PDF

Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing

2026 · Li, Zhiyuan, Yang, Wenyan, et al. · arXiv (Cornell University)

PDF

Do World Action Models Generalize Better than VLAs? A Robustness Study

2026 · Zhang, Zhanguang, Li, Zhiyuan, et al. · arXiv (Cornell University)

PDF

H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model

2026 · Huang, Jinbang, Chen, Wenyuan, et al. · arXiv (Cornell University)

PDF

Study of Switched Step-size Based Filtered-x NLMS Algorithm for Active Noise Cancellation

2026 · Li, Zhiyuan, Yu, Yi, et al. · arXiv (Cornell University)

PDF

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation

2025 · Zhang, Lingfeng, Liu, Yuecheng, et al. · arXiv (Cornell University)

PDF

Works count: 16

Citation count:

H-index:

I10-index: