Kuaishou and Beihang Propose 'Recommendation-as-Generation' (RaG) Framework
jiqizhixin · x · 2026-07-06
Kuaishou Technology and Beihang University have proposed the 'Recommendation-as-Generation' (RaG) framework. Instead of matching users with existing videos, it uses shared semantic IDs that separate content from style to instantly generate new videos tailored to their interests. Already deployed across a user base of over 400 million DAU, online A/B testing showed an ad revenue increase of up to 1.87% compared to a strong production baseline, proving that on-demand personalized video generation can drive new value at an industrial scale.
More from Multimodal
- A fine-tuned Krea 2 raw model produced a rainy-night driving scene — darlens13 · 2026-07-27
- Users ask whether Video2X can load custom OpenModelDB models — Used-Profit2355 · 2026-07-27
- A builder wants AI to reverse-engineer viral video effects into ComfyUI workflows — stale2000 · 2026-07-27
- Midjourney V8.2 adds personalization and shows off stylized image outputs — Mr_AllenT · 2026-07-27
- Midjourney’s image variety draws a Krea 2 comparison and asks how to reproduce it — diffusion_throwaway · 2026-07-27
- AI short film sets a 1985 dystopia to music and leans into cinema — ProfessorKey98 · 2026-07-27