https://pyemma.github.io/I am a coding monkey, and I am proud of it. I have done lots of work in machine learning area, especially recommendation system and AutoML. This blog summarize my journey to become an expert monkey in distributed system and LLM. 2026-06-03T05:51:23+00:00 Coding Monkey https://pyemma.github.io/ Jekyll © 2026 Coding Monkey /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png 2026-06-01T00:00:00+00:00 2026-06-01T00:00:00+00:00 https://pyemma.github.io/A-Random-Walk-Down-Recsys-Part-6/ pyemma

Welcome back to the sixth installment of A Random Walk Down Recsys. This batch is smaller than the last — four papers — but two of them line up neatly enough that they deserve a side-by-side read: Industrial distillation pipelines — ByteDance’s Rec-Distill and Meta’s LoopFM are both attacking the same problem (transferring knowledge from an expensive teacher / foundation model into the prod...

2026-05-10T00:00:00+00:00 2026-05-10T00:00:00+00:00 https://pyemma.github.io/A-Random-Walk-Down-Recsys-Part-5/ pyemma

Welcome back to the fifth installment of A Random Walk Down Recsys. This batch of papers reflects how quickly the generative recommendation playbook is being adapted to new verticals and tightened for production. Six papers, four themes: Generative Recommendation for Ads — two concurrent works, one from Kuaishou and one from Tencent, both attacking the same gap: today’s GR systems are heavi...

2026-03-07T00:00:00+00:00 2026-03-07T00:00:00+00:00 https://pyemma.github.io/A-Random-Walk-Down-Recsys-Part-4/ pyemma

Welcome back to the fourth installment of A Random Walk Down Recsys. This time, the three papers span a range of practical challenges in generative recommendation: efficiently compressing long user sequences through recurrent memory, accelerating constrained decoding on hardware accelerators via trie vectorization, and rethinking how semantic IDs are trained and maintained with a dynamic, end-t...

2026-02-22T00:00:00+00:00 2026-02-22T00:00:00+00:00 https://pyemma.github.io/A-Random-Walk-Down-Recsys-Part-3/ pyemma

Welcome back to the third installment of A Random Walk Down Recsys. This time, all five papers revolve around a single theme: Semantic IDs (SIDs) — how to generate them, how to improve their quality, and how to leverage them effectively in generative recommender (GR) models. The papers span a wide range of ideas: compressing long user sequences through SID hierarchies, injecting reasoning capab...

2026-02-05T00:00:00+00:00 2026-02-05T00:00:00+00:00 https://pyemma.github.io/A-Random-Walk-Down-Recsys-Part-2/ pyemma

Welcome back to the second installment of A Random Walk Down Recsys. In this post, I continue surveying interesting papers from the Arxiv IR section, covering five recent works: HyFormer, Token-level Collaborative Alignment, OneMall, a Sparse Attention approach for long-term user behaviors, and Farewell to Item IDs. HyFormer: Hybrid Cross-Attention for Sequential and Non-Sequential Features ...