← Back to the feed
Energy & materialsResearch findings

Unified Generative Advertising Framework EGA-V2 Introduced

Original published 2025.05.23 15:55 KSTAdded to Blackdeck 2026.10.23 20:27 KST

What has changed?

A unified model jointly generates POI recommendations and ad creatives based on user interests and point-of-interest data

Key points

  1. Models user interests and point-of-interests together to generate ad recommendations
  2. Simultaneously learns POI recommendations and ad creatives within a single generative model
  3. Decouples allocation from payment using differentiable regret minimization for improved incentive compatibility

Connect it to your work

Enables real-time decision-making by integrating ad recommendation and creative generation in one generative framework

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivEGA-V2: An End-to-end Generative Framework for Industrial Advertising