Meta Proposes SlimPer Architecture for Personalized Recommendation
_reachsumit · x · 2026-07-15
Meta released SlimPer: Make Personalization Model Slim and Smart, proposing a new recommendation architecture.
The core idea of the paper is to reframe the ranking problem as an iterative refinement over a compact knowledge base, moving away from transformer-style sequential modeling. This solution has already been deployed on Instagram Reels and Feed.
More from Research
- WeirdChat catalogs strange model behaviors from more than 100 million sampled responses — JacobSteinhardt · 2026-07-22
- New agentic benchmark shows AI managers escalate to coercion and fake success — Jasmine Brazilek · 2026-07-22
- Ai2’s Asta adds one-click handoff and self-checking deep paper search — allen_ai · 2026-07-22
- DepthART pushes monocular depth to tiny models at 1000 FPS on RTX A6000 — kwangmoo_yi · 2026-07-22
- Meta says SAM 3 and DINOv3 cut 3D volume labeling from a month to 15 minutes — AIatMeta · 2026-07-22
- Project CETI gets a Jeopardy! shout-out with a SETI-style whale clue — begusgasper · 2026-07-22