activity
20242026
collaborators

14 papers

cs.CV2026

OpenCoF: Learning to Reason Through Video Generation

Xinyan Chen, Ziyu Guo, Renrui Zhang +2

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reaso…

cs.CV2026

GLEAM: Learning to Match and Explain in Cross-View Geo-Localization

Xudong Lu, Zhi Zheng, Yi Wan +11

Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location. However, existing CV…

cs.CV2025

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark

Ziyu Guo, Xinyan Chen, Renrui Zhang +7

Recent video generation models can produce high-fidelity, temporally coherent videos, indicating that they may encode substantial world knowledge. Beyond realistic synthesis, they…

cs.CV2025

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Ziyu Guo, Renrui Zhang, Chengzhuo Tong +9

Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strate…

cs.CV2025

Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation

Yi Xin, Le Zhuo, Qi Qin +8

AutoRegressive (AR) models have made notable progress in image generation, with Masked AutoRegressive (MAR) models gaining attention for their efficient parallel decoding. However,…

cs.CV2025

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Dongzhi Jiang, Ziyu Guo, Renrui Zhang +6

Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning…