#generative-retrieval
The latest AI and developer news about #generative-retrieval, with the original source and a short summary.
The latest AI and developer news about #generative-retrieval, with the original source and a short summary.
The model uses semantic IDs and multi-teacher distillation to improve search relevance by 2.1 points and recommendation recall by 2.65pp.
Google Research and UIUC unveiled R4T, which distills RL-trained query fan-out behaviors into a 53.9M parameter diffusion model, reducing search latency by 12–20x.