Get started
Author

Chengzhuo Tong

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
2025 · Chengzhuo Tong, Ziyu Guo, et al. · neural information processing systems · 5
PDF
Let’s Verify and Reinforce Image Generation Step by Step
2025 · Renrui Zhang, Chengzhuo Tong, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 4
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
2025 · Guo, Ziyu, Zhang, Renrui, et al. · arXiv (Cornell University) · 2
PDF
SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
2024 · Guo, Ziyu, Zhang, Renrui, et al. · arXiv (Cornell University) · 1
PDF
MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
2024 · Zhang, Renrui, Wei, Xinyu, et al. · arXiv (Cornell University) · 1
PDF
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
2026 · Li, Bozhou, Zhang, Jiahang, et al. · arXiv (Cornell University)
PDF
Flux-OPD: On-Policy Distillation with Evolving Contexts
2026 · Wang, Yuran, Wang, Zekun, et al. · arXiv (Cornell University)
PDF
ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
2026 · Meng, Zijie, Liu, Jiwen, et al. · arXiv (Cornell University)
PDF
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
2026 · Dai, Yifan, Wu, Zhenhua, et al. · arXiv (Cornell University)
PDF
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
2026 · Tang, Yuqi, Shi, Yang, et al. · arXiv (Cornell University)
PDF
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
2026 · DataFlow Team, Zeng, Bohan, et al. · arXiv (Cornell University)
PDF
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
2026 · Zeng, Bohan, Zhu, Kaixin, et al. · arXiv (Cornell University)
PDF
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
2026 · Tong, Chengzhuo, Chang, Mingkun, et al. · arXiv (Cornell University)
PDF
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
2025 · Wang, Yuran, Zeng, Bohan, et al. · arXiv (Cornell University)
PDF
Works count: 17
Citation count: 13
H-index: 2
I10-index:
Year
Topic
Type