Author

Shiyi Zhang

Observed name: Zhang, Shiyi

Institutions: Hong Kong University of Science and Technology, Tencent (China), Future Academy, Tsinghua Shenzhen International Graduate School, Tsinghua University

Observed institutions: Hong Kong University of Science and Technology, Tencent (China), Future Academy, Tsinghua Shenzhen International Graduate School, Tsinghua University

OpenAlex ID: A5138286755

EchoWM: Open and Enterable Omnimodal World Models

2026 · Zhang, Songchun, Li, Yaowei, et al. · arXiv (Cornell University)

PDF

InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter

2026 · Tong, Yunze, Liu, Mushui, et al. · arXiv (Cornell University)

PDF

Kimi K3: Open Frontier Intelligence

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

PDF

Self Gradient Forcing: Native Long Video Extrapolation

2026 · Zhuang, Junhao, Zhang, Shiyi, et al. · arXiv (Cornell University)

PDF

EchoStory: Slot-Paired Audio-Visual Memory for Multi-Shot Long Audio-Video Storytelling

2026 · Jie Huang, Yijun Liu, et al.

Echo-Memory: A Controlled Study of Memory in Action World Models

2026 · King, Wayne, Xue, Zeyue, et al. · arXiv (Cornell University)

PDF

Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

2026 · Huang, Jie, Lu, Xin, et al. · arXiv (Cornell University)

PDF

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation

2026 · Bian, Yuxuan, Xue, Zeyue, et al. · arXiv (Cornell University)

PDF

Generative Visual Chain-Of-Thought for Image Editing

2026 · Zijin Yin, Tiankai Hang, et al.

Meta-CoT: Enhancing Granularity and Generalization in Image Editing

2026 · Zhang, Shiyi, Cheng, Yiji, et al. · arXiv (Cornell University)

PDF

Generative Visual Chain-of-Thought for Image Editing

2026 · Yin, Zijin, Hang, Tiankai, et al. · arXiv (Cornell University)

PDF

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

2026 · Tong, Yunze, Liu, Mushui, et al. · arXiv (Cornell University)

PDF

TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

2026 · Xu, Yu, Yan, Hongbin, et al. · arXiv (Cornell University)

PDF

Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

2026 · He, Runze, Cheng, Yiji, et al. · arXiv (Cornell University)

PDF

Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation

2025 · Zhu, Tianrui, Zhang, Shiyi, et al. · arXiv (Cornell University)

PDF

Works count: 15

Citation count:

H-index:

I10-index: