Nature Comm: Single Sample Influence in Diffusion Models Decreases with Data Size
maier_ak · x · 2026-08-25
A 2026 Nature Communications study finds that in diffusion models, the causal influence of a single training image shrinks as the dataset grows, following an inverse power-law.
- The Causal Responsibility (CR) becomes so small that attributing an output to one sample is impossible.
- This suggests that in models trained on massive datasets, identifying or protecting the influence of a single data source is mathematically extremely difficult.
More from Research
- Goodfire's Nick Cammarata: neural networks are "already clean" in a possible interpretability breakthrough — tszzl · 2026-10-15
- tszzl: interpretability breakthrough feels like my understanding of neural nets jumped five years — tszzl · 2026-10-15
- LightSuite: fast cell detection and whole-brain atlas registration on a standard workstation — hisspikeness · 2026-10-15
- Pathway CSO pitches BDH as post-Transformer architecture uniting memory, reasoning, adaptation — schwentker · 2026-10-15
- AI-designed molecular scissors cut Alzheimer's proteins — but is it really AI? — gerardsans · 2026-10-15
- EmbodiedEvo tops RoboDojo at 38.95% success by letting robots inherit failed practice — thetripathi58 · 2026-10-15