Free Reads
Sign in to view your remaining parses.
Tag Filter
Autoregressive Video Diffusion Models
Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Published:10/4/2025
Autoregressive Video Diffusion ModelsMinecraft Scene GenerationSpatio-Temporal Memory FrameworkGeometry-Indexed Spatial MemoryIncremental 3D Reconstruction
The paper introduces the 'Memory Forcing' framework, which combines spatiotemporal memory for consistent scene generation in Minecraft. It features hybrid training and chained forward training to guide the model in utilizing temporal memory during exploration and spatial memory
02
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
Published:12/18/2025
Autoregressive Video Diffusion ModelsSelf-Resampling Training MethodLong-Horizon Generation CapabilityTemporal Causal MaskParameter-Free History Retrieval Mechanism
This paper presents a teacherfree selfresampling method for training autoregressive video diffusion models, addressing exposure bias and enabling efficient longhorizon generation with competitive performance and improved temporal consistency.
04
From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
Published:12/11/2024
Autoregressive Video Diffusion ModelsDiffusion Model DistillationVideo Generation AccelerationDynamic Video GenerationLong-Horizon Video Synthesis
The paper introduces a novel autoregressive video diffusion model that transforms a slow bidirectional model into a fast one using distribution matching distillation. With teacher trajectory initialization and asymmetric distillation, it achieves an 84.27 score on VBenchLong, si
02