Understand this story
A Tsinghua University team has proposed PPMem, a memory method for video world models. According to a report on October 20, 2026, the method replaces the volumetric 3D memory of the earlier SPMem with planar primitives to store explored scenes for video world models. Each planar primitive is parameterized by only 7 numerical parameters, including a center depth, two rectangular extents, and a rotation quaternion, making it several orders of magnitude more compact than per-pixel representations. When the camera returns to a previously visited location, the stored planes are projected back into the field of view to guide the generation of new frames, thereby reducing the spatial information that must be retained and processed and preventing familiar objects from changing or disappearing upon revisiting. The work is currently presented externally under the name PPMem, and no further progress has been disclosed.
AI-generated from public reports
Latest development · Report
Tsinghua Team Proposes PPMem: Using Planar Primitives to Build Persistent Memory for AI Video World ModelsDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 20
Unite.AI
Tsinghua Team Proposes PPMem: Using Planar Primitives to Build Persistent Memory for AI Video World Models
A team from Tsinghua University has proposed PPMem, which replaces the previous SPMem's volumetric 3D memory with planar primitives to store explored scenes for video world models. Each planar primitive is parameterized by only 7 numbers (center depth, two rectangular extents, and a rotation quaternion), making it orders of magnitude more compact than per-pixel representations. When the camera returns to a previously visited location, the stored planes are projected back into the field of view to guide the generation of new frames, reducing the spatial information that must be retained and processed and preventing familiar objects from changing or disappearing upon revisits.