[Generative Recommendation] (3) 벡터 양자화와 VQ-VAE: 코드북 학습, Straight-Through Estimator, 그리고 코드북 붕괴 12 분 소요
[논문 리뷰] Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators 3 분 소요 논문 링크: Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators