PayPal's Bottom-Up Clustering Builds Better Semantic IDs Than RQ-VAE
_reachsumit · x · 2026-09-09
PayPal researchers propose a bottom-up clustering algorithm for constructing Semantic IDs in generative retrieval. While Semantic IDs beat arbitrary identifiers like hashes by capturing item semantics, ensuring each ID maps uniquely to a product while preserving downstream-useful structure is hard; prior work appended extra codewords and used residual quantization. The new method preserves local structure in the embedding space, yielding unique identifiers with improved clustering quality and downstream generative retrieval performance (6-page workshop paper).
More from Research
- Timothy Duff's ECCV 2026 SfM-DL workshop slides on algebraic optimality for minimal solvers — ducha_aiki · 2026-09-09
- Drop a fixed batch proportion instead of per-sample tokens: capi author shares training trick — giffmana · 2026-09-09
- Adding Greek to a Cosmos3 VLA policy: bilingual training helps but lags far behind English — KIEFERSA · 2026-09-09
- Transformers encode a partner's expertise early but only act on it in later layers — Mika Okamoto · 2026-09-09
- Cadence uses a time-series foundation model for error-bounded lossy compression of demand data — Roberto Tacconelli · 2026-09-09
- Fourth Perception Test Challenge at ECCV 2026 pushes multimodal models on city-scale spatial intelligence — AjdDavison · 2026-09-09