Snap Paper: Fixing Lost Semantics in LLM-Based Recommenders
_reachsumit · x · 2026-08-11
Shared a paper from the Snap team titled "Preserving Item Semantics for Free".
The paper reveals that semantic ID tokens in LLM-based recommenders end up encoding popularity rather than semantics. The team fixes this issue with a free centroid initialization method.
More from Research
- Anthropic Sets Up Bay Area Wet Lab, Plans to Have Claude Run Experiment Robots — FinanceYF5 · 2026-09-21
- KLPO: a critic-free, single-rollout RL method for agentic LLMs, framed as 'Q* solved' — inductionheads · 2026-09-21
- FutureHouse publishes 'Millennium Problems for Biology' as wetlab-verifiable evals for AI — burny_tech · 2026-09-21
- No scientific test for consciousness exists even in humans — how can we declare AI unconscious? — burny_tech · 2026-09-21
- Formal Reasoning in AI: Song guest-lectures Virginia Tech course, slides public — wellecks · 2026-09-21
- Biologist: FutureHouse's Bio Millennium List Is Too Narrow — Really Just Synbio — burny_tech · 2026-09-21