English(EN)ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation
新研究通过上下文优化和高效推理解决生成式推荐问题
作者PulseAugur 编辑部·[13 个来源]·
近期研究探索了生成式推荐系统的先进技术，重点在于提高效率和准确性。论文介绍了诸如上下文充分性边界（Context-Sufficiency Frontier）等方法，以优化所提供上下文的相关性，超越了单纯增加数据量的方法。其他研究提出了新颖的推理过程，如ReSolve，它通过复用候选推理来降低计算成本和token使用量。此外，FineSID和SpeakGR等新框架旨在增强语义标识符学习，并在生成式检索模型中保留语言生成能力，以应对稀疏梯度和模型专业化等挑战。
AI
arXiv:2610.00654v1 Announce Type: new Abstract: Personalization has long relied on customer data to infer what an individual is likely to value. We call this customer evidence: the customer's historical behavior and preferences. Generative AI extends personalization by allowing p…
arXiv cs.AI
TIER_1English(EN)·Bangji Yang, Jiajun Fan, Hongba Ma, Xi Zhu, Weizhi Zhang, Minghao Guo, Ye Li, Hamid Palangi, Jiaxuan You·
arXiv:2610.01140v1 Announce Type: new Abstract: Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a training-free inference procedure that reuses this candidate reasoning through sele…
Generative recommendation, has been attracted a surge of attentions in industrial and academic research community, towards to build more smart system to build next-generation recommender. Under the significant developing wave of large language model, our team have been developed …
arXiv:2609.36670v1 Announce Type: new Abstract: A critical prerequisite of generative recommendation is designing semantic identifiers (SIDs) that are both scalable to large item sets and efficiently learnable. Existing SID learning methods fundamentally rely on Top-1 hard assign…
Generative retrieval (GR) enables end-to-end retrieval by generating document semantic identifiers (SIDs). However, retrieval-only fine-tuning can over-specialize pretrained language models to SID prediction, substantially distorting their natural-language distribution and limiti…
Generative recommenders retrieve items by generating identifiers, but a valid identifier can remain outside the beam after catalog expansion. This raises two connected questions: which failures can identifier assignment repair, and how should retrieval proceed beyond the initial …
In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms. We argue that existing harm taxonomies and threat models require extension to (1) address novel causal drivers of well-studied representational and qu…
arXiv cs.AI
TIER_1English(EN)·Mengdan Zhu, Yufan Zhao, Sophie Di, Yao Zhao, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao·
arXiv:2609.29973v1 Announce Type: cross Abstract: Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user's interaction history. Semantic IDs further make this paradigm effective and sca…
arXiv cs.AI
TIER_1English(EN)·Mengdan Zhu, Yufan Zhao, Yao Zhao, Sophie Di, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao·
arXiv:2609.29983v1 Announce Type: cross Abstract: Semantic IDs (SIDs) encode each catalog item as a short token sequence, enabling generative recommenders to predict the next item autoregressively. Reasoning-enhanced variants, an increasingly common extension, first generate a te…
Semantic IDs (SIDs) encode each catalog item as a short token sequence, enabling generative recommenders to predict the next item autoregressively. Reasoning-enhanced variants, an increasingly common extension, first generate a textual trace and then decode a next-item SID by bea…
Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user's interaction history. Semantic IDs further make this paradigm effective and scalable by representing each item as discrete codes,…
Generative recommendation has emerged as an active research direction, where items are commonly represented by semantic IDs (SIDs): discrete codes generated token by token. Despite strong empirical results, SID designs vary widely in construction strategy, codebook organization, …
<h3> Generative AI </h3> <p>Generative AI refers to <strong>AI systems that learn patterns from existing data and use those learned pattern to generate new content such as</strong> text, video, audio, code and images. </p> <p>Gen AI is a <strong>type of AI focused on generating n…
