Generative recommendation has recently emerged as a transformative paradigm that directly generates target items, surpassing traditional cascaded approaches. It typically involves two components: a tokenizer that learns item identifiers and a recommender trained on them. Existing methods often decouple tokenization from recommendation or rely on asynchronous alternating optimization, limiting full end-to-end alignment. To address this, we unify the tokenizer and recommender under the ultimate recommendation objective via differentiable soft item identifiers, enabling joint end-to-end training. However, this introduces three challenges: training-inference discrepancy due to soft-to-hard mismatch, item identifier collapse from codeword usage imbalance, and collaborative signal deficiency due to an overemphasis on fine-grained token-level semantics. To tackle these challenges, we propose UniGRec, a unified generative recommendation framework that addresses them from three perspectives. UniGRec employs Annealed Inference Alignment during tokenization to smoothly bridge soft training and hard inference, a Codeword Uniformity Regularization to prevent identifier collapse and encourage codebook diversity, and a Dual Collaborative Distillation mechanism that distills collaborative priors from a lightweight teacher model to jointly guide both the tokenizer and the recommender. Extensive experiments on real-world datasets demonstrate that UniGRec consistently outperforms state-of-the-art baseline methods. Our codes are available at https://github.com/Jialei-03/UniGRec.

翻译：生成式推荐作为一种变革性范式，近期崭露头角，它能够直接生成目标物品，超越了传统的级联式方法。该方法通常包含两个组件：一个学习物品标识符的分词器和一个基于这些标识符训练的推荐器。现有方法往往将分词与推荐过程解耦，或依赖于异步交替优化，限制了完全的端到端对齐。为解决这一问题，我们通过可微分的软物品标识符，将分词器和推荐器在最终推荐目标下统一起来，实现了联合端到端训练。然而，这引入了三个挑战：由软硬不匹配导致的训练-推断差异、码字使用不均衡引起的物品标识符坍缩，以及因过度关注细粒度词元级语义而导致的协同信号缺失。为应对这些挑战，我们提出了UniGRec，一个统一的生成式推荐框架，从三个角度解决上述问题。UniGRec在分词过程中采用退火推断对齐，以平滑地桥接软训练与硬推断；采用码字均匀性正则化来防止标识符坍缩并促进码本多样性；并设计了一种双重协同蒸馏机制，从一个轻量级教师模型中蒸馏出协同先验知识，以共同指导分词器和推荐器。在真实世界数据集上进行的大量实验表明，UniGRec在性能上持续优于最先进的基线方法。我们的代码公开于 https://github.com/Jialei-03/UniGRec。