This page shows the most relevant public items for Computer Vision, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Feb 8, 2026 • arXiv • Zhengqing Gao, Ziwen Li, Xin Wang, Tongliang Liu
To bridge the simulation-to-real gap, we introduce Mirage2Matter, a physically grounded Gaussian world model that generates high-fidelity embodied training data from multi-view videos. We reconstru...
Paper • Feb 9, 2026 • arXiv • Minhyuk Lee, Hyekyung Yoon, Myungjoo Kang
Text-to-Image (T2I) diffusion models enable high-quality synthesis, but deployment demands safeguards. We formalize the tension between safety and alignment through a total variation (TV) lens, yie...
Paper • Feb 13, 2026 • arXiv • Ying Yang, Fang Kang, Mengqi Zhang, Zheng Lian
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (>10B), entailing prohibitive costs. We present DeepGen 1.0, a lightweight 5B unified m...
Paper • Feb 13, 2026 • arXiv • Krish Agarwal, Zhuoming Chen, Cheng Luo, Beidi Chen
The quadratic complexity of attention severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the sparse spatio-temporal attention patterns in Video DiTs can be...