Get started
Author

Zhizhou Sha

TokenCompose: Text-to-Image Diffusion with Token-Level Supervision
2024 · Zirui Wang, Zhizhou Sha, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 16
PDF
OmniControlNet: Dual-stage Integration for Conditional Image Generation
2024 · Yilin Wang, Haiyang Xu, et al. · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 7
PDF
Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling
2025 · Yang Cao, Bo Chen, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 4
PDF
Differential Privacy Mechanisms in Neural Tangent Kernel Regression
2025 · Jiuxiang Gu, Yingyu Liang, et al. · IEEE Winter Conference on Applications of Computer Vision · 4
PDF
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
2024 · Liang, Yingyu, Sha, Zhizhou, et al. · arXiv (Cornell University) · 3
PDF
HSR-Enhanced Sparse Attention Acceleration
2024 · Chen, Bo, Liang, Yingyu, et al. · arXiv (Cornell University) · 2
PDF
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
2025 · Yingyu Liang, Zhizhou Sha, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 1
PDF
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
2025 · Cao, Yuefan, Li, Xiaoyu, et al. · arXiv (Cornell University) · 1
PDF
RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation
2025 · Cao, Yuefan, Gong, Chengyue, et al. · arXiv (Cornell University) · 1
PDF
Looped ReLU MLPs May Be All You Need as Practical Programmable Computers
2024 · Liang, Yingyu, Sha, Zhizhou, et al. · arXiv (Cornell University) · 1
PDF
LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation
2026 · Huang, Suozhi, Fu, Kelsey, et al. · arXiv (Cornell University)
PDF
The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion
2026 · Li, Xiaoyu, Gao, Zheng, et al. · arXiv (Cornell University)
PDF
A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges
2026 · Li, Xiaoyu, Sha, Zhizhou, et al. · arXiv (Cornell University)
PDF
The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction
2026 · Li, Xiaoyu, Sha, Zhizhou, et al. · arXiv (Cornell University)
PDF
QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs
2026 · Xu, Weili, Li, Jisen, et al. · arXiv (Cornell University)
PDF
Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks
2026 · Li, Xiaoyu, Sha, Zhizhou, et al. · arXiv (Cornell University)
PDF
ISO: An RLVR-Native Optimization Stack
2026 · Zhu, Hanqing, Cong, Wenyan, et al. · arXiv (Cornell University)
PDF
Learning from the Self-future: On-policy Self-distillation for dLLMs
2026 · Luo, Yifu, Chen, Zeyu, et al. · arXiv (Cornell University)
PDF
No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions
2026 · Yang, Xu, Sha, Zhizhou, et al. · arXiv (Cornell University)
PDF
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
2026 · Xie, Yunfei, Wang, Kevin, et al. · arXiv (Cornell University)
PDF
UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment
2026 · Yecheng Zhang, Rong Zhao, et al. · Lecture notes in computer science
PDF
The Path Not Taken: RLVR Provably Learns Off the Principals
2025 · Zhu, Hanqing, Zhang, Zhenyu, et al. · arXiv (Cornell University)
PDF
Discriminator-Free Direct Preference Optimization for Video Diffusion
2025 · Cheng, Haoran, Dong, Qide, et al. · arXiv (Cornell University)
PDF
HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
2025 · Liang, Yingyu, Sha, Zhizhou, et al. · arXiv (Cornell University)
PDF
On Computational Limits of FlowAR Models: Expressivity and Efficiency
2025 · Cao, Yang, Gong, Chengyue, et al. · arXiv (Cornell University)
PDF
Works count: 28
Citation count: 40
H-index: 4
I10-index: 1
Year
Topic
Type