AI recommendation

iQIYI Technical Product Team

Mar 1, 2024 · Artificial Intelligence

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI

iQIYI’s ad ranking system replaces static, hash‑based embeddings with TFRA dynamic embeddings to efficiently handle massive sparse ID features, eliminates collisions and I/O bottlenecks, isolates memory during hot model swaps, enabling billion‑parameter models that boost revenue by 4.3 % while planning adaptive embedding sizes for future improvements.

AI recommendationDynamic EmbeddingLarge-Scale Models

0 likes · 10 min read

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI

DataFunTalk

Oct 16, 2023 · Artificial Intelligence

Personalized Title Generation and Automatic Cover Image Synthesis for Information‑Flow Scenarios

This article presents technical approaches for generating personalized article titles and automatically synthesizing cover images, covering keyword‑based, click‑sequence‑based, and author‑style‑based title models, as well as image restoration, key‑information extraction, object detection, and layout generation techniques to improve user engagement in recommendation and search systems.

AI recommendationLSTMcover image synthesis

0 likes · 11 min read

Personalized Title Generation and Automatic Cover Image Synthesis for Information‑Flow Scenarios