S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
cs.CV
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
- The Seriality Gap in Video Diffusion Models
- On the Content Bias in Fr'echet Video Distance
- "PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
- T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation
- Video Diffusion Models
- Multiplayer Interactive World Models with Representation Autoencoders
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics
- Back to Basics: Let Denoising Generative Models Denoise
- PhyGround: Benchmarking Physical Reasoning in Generative World Models
- Flow Matching for Generative Modeling
- The Serial Scaling Hypothesis
- Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
- Cosmos 3: Omnimodal World Models for Physical AI
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation
- Scalable Diffusion Models with Transformers
- History-Guided Video Diffusion
- Towards Accurate Generative Models of Video: A New Metric & Challenges
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models