From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself. However, the mechanism behind the improvement from SRA to Self-Flow, dual-time scheduling, remains under-examined: Self-Flow attributes its gain to interactions between tokens at different noise levels, where cleaner tokens help infer noisier ones. In this work, we revisit this explanatio
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%Transformer →
- FuzzySimilar title/name (fuzzy) · 84%roboflow/supervision →
“Fuzzy title match (0.92): “From SRA to Self-Flow: Data Augmentation or Self-Supervision” ≈ “roboflow/supervision””
- FuzzySimilar name plus overlapping authors · 67%bytedance/deer-flow →
“Title similarity 0.73; shared authors: wang”
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%BerriAI/litellm →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Dengyang Jiang →
“From SRA to Self-Flow: Data Augmentation or Self-Supervision?”