Diffusion Transformer (DiT)

The researchers present Self Gradient Forcing (SGF) to solve the lack of gradient flow in historical KV caches during autoregressive video generation. This method enables much more stable and consistent long-form video extrapolation without the massive memory overhead of full backpropagation.

The researchers present Self Gradient Forcing (SGF) to solve the lack of gradient flow in historical KV caches during autoregressive video generation. This method enables much more stable and consistent long-form video extrapolation without the massive memory overhead of full backpropagation.

This paper proposes ReChannel, a novel architecture that transforms text-to-image models from RGB generators into efficient dense prediction engines. By treating transformer tokens as spatial carriers for task-specific data rather than RGB pixels, the method achieves new state-of-the-art performance with much higher computational efficiency.

This paper proposes ReChannel, a novel architecture that transforms text-to-image models from RGB generators into efficient dense prediction engines. By treating transformer tokens as spatial carriers for task-specific data rather than RGB pixels, the method achieves new state-of-the-art performance with much higher computational efficiency.