Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

arXiv:2609.38819 · cs.CV, cs.AI, q-bio.NC · Submitted 2026-09-30 · Read on arXiv

cs.CV, cs.AI, q-bio.NC

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Alignment — 34× in this paper · explained in 1 episode
• Accuracy — 22× in this paper · explained in 1 episode
• Diffusion Model — 14× in this paper · explained in 8 episodes
• Diffusion Models — 11× in this paper · explained in 6 episodes
• Generative Model — 9× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Generative AI — 4× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 4× in this paper
• Generative Models — 3× in this paper · explained in 2 episodes
• Predictive Coding — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Computational Biology — 1× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 1× in this paper
• Elias — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes

Sources

• Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
• The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
• TokenFlow: Consistent Diffusion Features for Consistent Video Editing
• Diffusion-Based Action Recognition Generalizes to Untrained Domains
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
• Gen4U: Unifying Video Generation and Understanding via Diffusion
• Flow Matching for Generative Modeling
• Emergent Temporal Correspondences from Video Diffusion Transformers
• Scalable Diffusion Models with Transformers
• Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
• Wan: Open and Advanced Large-Scale Video Generative Models
• Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
• Video-Mirai: Autoregressive Video Diffusion Models Need Foresight
• Helios: Real Real-Time Long Video Generation Model
• Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
• VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

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