Get started
Author

Tianyu He

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
2026 · Ziqin Zhou, Yifan Yang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2
HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball
2026 · Yuan, Jinghui, Zhang, Hongtao, et al. · arXiv (Cornell University)
PDF
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
2026 · Huang, Junchao, Fang, Guian, et al. · arXiv (Cornell University)
PDF
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
2026 · Hanxin Zhu, Cong Wang, et al. · International Journal of Computer Vision
PDF
CP4D: Compositional Physics-aware 4D Scene Generation
2026 · Zhu, Hanxin, Wang, Cong, et al. · arXiv (Cornell University)
PDF
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
2026 · Yue, Yang, Wei, Fangyun, et al. · arXiv (Cornell University)
PDF
Beyond Pixel Histories: World Models with Persistent 3D State
2026 · Garcin, Samuel, Walker, Thomas, et al. · arXiv (Cornell University)
PDF
LIVE: Long-horizon Interactive Video World Modeling
2026 · Huang, Junchao, Ye, Ziyang, et al. · arXiv (Cornell University)
PDF
HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
2026 · Association for Artificial Intelligence 2026, Dai, Qi, et al. · Underline Science Inc.
Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration
2026 · Association for Artificial Intelligence 2026, Chen, Zhibo, et al. · Underline Science Inc.
Embodied VAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
2026 · Jiayi Luo, Hanxin Zhu, et al. · Lecture notes in computer science
PDF
On the Emergent Structures of Deep Neural Networks
2025 · He, Tianyu · University Libraries (University of Maryland)
Works count: 13
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type