让视频扩散模型学会“自我想象”物理规律，生成动作更符合真实世界。
arXiv:2606.27741v1 Announce Type: new Abstract: Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated m…
视频扩散模型新突破：细粒度稀疏注意力FG-Attn，大幅提升计算效率与生成质量。
arXiv:2509.16518v2 Announce Type: replace Abstract: Using diffusion transformers for media generation may require evaluating attention over extremely …
让视觉语言模型看懂动作——利用视频扩散模型注入运动信息，提升动态场景理解能力，CVPR 2026接收。
arXiv:2606.06853v1 Announce Type: cross Abstract: The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackli…
视频扩散模型不再只求逼真，引入强化学习实现时空逻辑约束下的可验证推理，提升智能体规划能力。
arXiv:2605.15458v1 Announce Type: new Abstract: Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they…