VaLiDRec uses variable-length LLM-aligned IDs and runs 87.49× faster than LC-Rec
_reachsumit · x · 2026-07-29
VaLiDRec introduces variable-length semantic IDs built from native LLM vocabulary tokens, then predicts them with graph-aware soft prompts instead of autoregressive SID decoding.
- Reduces overcompression and better aligns IDs with pretrained LLM vocabularies.
- Avoids beam search and token-by-token SID generation.
- Outperforms strong sequential and generative recommendation baselines on four real-world datasets.
- Shows better zero-shot cold-start performance and 87.49× faster inference than LC-Rec.
More from Infra
- Google posts first quarter of negative free cash flow after years of growth — michalmalewicz · 2026-07-29
- South Korea’s AI-linked stocks sink 10.84% as Samsung and SK Hynix plunge — emmanuelvivier · 2026-07-29
- OpenAI launches Presence for real-time voice agents and enterprise chatbots — emmanuelvivier · 2026-07-29
- French Startup ZML Releases Free Inference Server Compatible Across AI Chips — emmanuelvivier · 2026-07-29
- AI Chip Startup SambaNova Raises $1B at $11B Valuation — emmanuelvivier · 2026-07-29
- Microsoft is building internal AI models to cut OpenAI dependence and costs by up to 89% — emmanuelvivier · 2026-07-29