A joint bidding mechanism enables stores and brand suppliers to collaborate in advertising auctions
Explore technology by industry and role
Newest additions first. Explore past and current notes by industry and role.
All notes
Newest additions first. Explore past and current notes by industry and role.
Users are partitioned into independent threads for parallel similarity computation
A distributed neural controller using only neighbor communication achieves performance improvement without sacrificing stability during PnP operations.
A multi-head attention mechanism enables simultaneous learning of diverse feature interactions among user history, interests, and target ads.
A two-stage framework efficiently predicts revenue under quota conditions and allocates creatives under capacity constraints.
Experimental evidence shows darker skin models face reduced ad effectiveness and higher costs
A simulation environment incorporating real-world logs and a target exploration mechanism with change-point detection is introduced.
Separating advertising from marketplace functions may reduce targeting precision
Generates background images and foreground design blueprints aligned with campaign messages, enabling full automation
Proposes a conversation-based recommendation system using NLP insights.
Introduced onboard Global Localization (GBLC) using a commercial processor to autonomously match ground and orbital imagery, enabling precise global positioning
A unified model jointly generates POI recommendations and ad creatives based on user interests and point-of-interest data
Unifies ad ranking into a single end-to-end model to eliminate stage-level inconsistencies
It proves that previous non-deterministic allocation methods fail in most cases and proposes JTransNet, which achieves both deterministic allocation and anonymy
Explicitly models global externalities and interactions between ads and adjacent organic content