- 标签:
- AI (136)
- Daily (111)
- Tech Trends (111)
- 技术趋势 (18)
- 周报 (18)
- 推荐系统 (16)
- 日报 (15)
- Recommendation Systems (11)
- Weekly (11)
- Papers (11)
- Agentic Engineering (7)
- 思考 (6)
- 论文 (6)
- 深度学习 (4)
- 工具 (3)
- Harness Engineering (3)
- 推荐 (2)
- 强化学习 (1)
- 思维模型 (1)
- Transformer (1)
- LLM (1)
- 管理 (1)
- 生成式 (1)
2017 年,Ilya Sutskever 读到《Attention Is All You Need》时,立即意识到”这就是我们需要的一切”。OpenAI 随即放弃了 RNN/LSTM 路线,全面转向 Transformer,催生出整个 GPT 系列。Transformer 的并行能力让他们得以实现一直相信的 Scaling 路径。八年后的今天,推荐系统终于走到了同样的路口。 2024 年之前,推荐领域有了 HSTU、TIGER 这样的工作,但大多数团队还在观望。2025 年,我观察到一个明显的转变:大家开始认真地把排序模型 Dense Scaling Up,搞生成式召回和端到端推荐。这很像 2017 年——当时大家忙着把 LR/GBDT/FM 切换到 Deep Model 和双塔,切换过程持续了一两年,之后再没人回头。我的判断是,2026 年将是推荐系统 All-In Transformer 的一年,不改变就落后。
从精排切换成深度学习以来,工业界一直会把排序的模型结构研究切分成基本的两部分,序列处理和特征交叉,甚至有一些公司的排序组,下面都拆成两个Team分别处理行为序列和特征交叉。从最早的时候,比如序列用DIN来处理,序列就被压成了一个或多个向量表征,再参与与其他特征的交叉。我们可以理解成MLP(concat(DIN, Features)),发展到今天大多数的模型研究,还是分立地把MLP换成DCN,增加个LHUC,复杂化为Rank Mixer或Transformer,把DIN叠加MHA,直接换成Transformer,可以写成RankMixer(concat(Transformer, Features))。 从MLP(concat(DIN, Features))到RankMixer(concat(Transformer, Features)),本质没有变,就是序列处理和特征交叉是一个隐式的两阶段处理,序列被压缩到Vector Space才和特征发生交叉。而LLM的有趣之处,就是在Next Token Prediction利用到的交叉发生在词序列的Token Space之中,它能启发推荐排序模型的,就是每一个特征的交叉应该发生在用户序列的Token Space之中。
Two technical threads dominate Week 11 of 2026 (March 8–14) in recommendation system research. First, generative recommendation (GR) is undergoing full-stack optimization — transitioning from "making it work" to "making it work well, fast, and fairly" — Netflix/Meta's exponential reward-weighted SFT addresses post-training alignment, LinkedIn's causal attention reformulation halves sequence length, Kuaishou's FP8 quantization reduces OneRec-V2 inference latency by 49%, and Alibaba's differentiable geometric indexing eliminates long-tail bias at its root. Five papers advance GR's industrial maturity across five dimensions. Second, LLM-based recommendation is shifting from "single-pass inference" toward an agentic paradigm — Meta's VRec inserts verification steps into reasoning chains, Meituan's RecPilot replaces traditional recommendation lists with a multi-agent framework, USTC's TriRec introduces tri-party coordination for the first time, and RUC/JD's RecThinker enables autonomous tool invocation.
Industrial recommendation ranking shifts to systematic scaling engineering. Alibaba's SORT achieves orders +6.35%, Kuaishou's FlashEvaluator and SOLAR optimize evaluator and attention efficiency, ByteDance's HAP enables adaptive compute budget allocation. Generative recommendation enters objective alignment phase. 36 papers analyzed.