2 papers
cs.LG2026
The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges
Avinash Raju, Kai Zhang
Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. The two objectives share the sa…
cs.CV2026
Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation
Yueting Zhu, Yuehao Song, Kaicheng Zhang +5
Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming…