Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

arXiv:2609.38140 · cs.CV, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: Accepted as a Spotlight paper at NeurIPS 2026. Project page: https://yuci-gpt.github.io/SplitMoE/

Code: https://github.com/genmoai/models

Project page: https://yuci-gpt.github.io/SplitMoE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 12× in this paper · explained in 2 episodes
• Diffusion Model — 8× in this paper · explained in 8 episodes
• Fidelity — 7× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Generative Model — 5× in this paper · explained in 2 episodes
• Generative Models — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Decoupling — 4× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Evaluation Dimensions — 2× in this paper · explained in 3 episodes
• Mixture-of-Experts (MoE) — 2× in this paper · explained in 7 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Temporal consistency — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Adaptive Partitioning — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Anchor Tokens — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Homogenization — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• HunyuanImage 3.0 Technical Report
• Scaling Diffusion Transformers to 16 Billion Parameters
• Seedance 1.0: Exploring the Boundaries of Video Generation Models
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• DeepSeek-V3 Technical Report
• Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe
• OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
• Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
• MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
• DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
• LongCat-Video Technical Report
• Wan: Open and Advanced Large-Scale Video Generative Models
• Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
• TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

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