Delta tokens compress VFM feature differences into single tokens, enabling a lightweight generative world model that predicts diverse futures with far lower compute than existing approaches.
1.58-bit FLUX
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
FreqFlow introduces frequency-aware conditioning and a two-branch architecture to flow matching, reaching FID 1.38 on ImageNet-256 and outperforming DiT and SiT.
citing papers explorer
-
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
Delta tokens compress VFM feature differences into single tokens, enabling a lightweight generative world model that predicts diverse futures with far lower compute than existing approaches.
-
When Do Diffusion Models learn to Generate Multiple Objects?
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
-
Frequency-Aware Flow Matching for High-Quality Image Generation
FreqFlow introduces frequency-aware conditioning and a two-branch architecture to flow matching, reaching FID 1.38 on ImageNet-256 and outperforming DiT and SiT.
- RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models