Diffusion models are awesome! Check out our survey on 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 𝐟𝐨𝐫 𝐕𝐢𝐬𝐮𝐚𝐥 𝐂𝐨𝐦𝐩𝐮𝐭𝐢𝐧𝐠! We give an introduction to diffusion models and highlight how they are used by state-of-the-art methods in graphics and vision. arxiv.org/abs/2310.07204

Video World Models with Long-term Spatial Memory video generation framework relies on long-term spatial memory, working memory, and sparse episodic memory

Real-time video generation is finally real — without sacrificing quality. Introducing Self-Forcing, a new paradigm for training autoregressive diffusion models. The key to high quality? Simulate the inference process during training by unrolling transformers with KV caching.

"World model" has been an overloaded term, used by different communities in various contexts. Here's a fantastic blog from Xun, packed with great insights on what world models could look like. A very valuable read for anyone working in this space!

Long video generation usually results in context increasing/scaling during chunk/frame-wise rollout. Considering context scaling may require context selection, we thus introduce the idea of MoE into long context modelling and propose Mixture of Contexts. All previous