Official Alimama tech channel, showcasing all of Alimama's technical innovations.
Graphia, a new LLM‑based social simulation framework, leverages social graph data as high‑quality supervision to jointly align microscopic interaction predictions and macroscopic network structures, achieving significant gains on TDGG and IDGG benchmarks across three real‑world datasets.
The article presents LLM-Auction, a novel AI‑native marketing mechanism that unifies ad allocation and answer generation by training large language models to conduct auctions directly on their output distribution, achieving higher allocation efficiency without extra inference cost.
The DARA framework splits online advertising budget allocation into a few‑shot LLM reasoning stage and a fine‑grained optimizer stage, enhanced by a dynamically updated RL‑fine‑tuning algorithm (GRPO‑Adaptive), achieving significantly lower ROI variance than traditional baselines in both real and simulated environments.
This article analyzes the challenges of traditional product selection on Taobao and presents an LLM‑driven solution that combines multi‑round online search, DeepSearch vs. WideSearch strategies, sample construction, SFT and RL training, and shows experimental results that improve relevance, diversity, and efficiency of the selected product set.
The article analyzes the evolution from traditional modular recommendation models to a generative Large User Model (LUM), detailing its three‑stage paradigm, tokenization, training objectives, scaling‑law findings, offline and online experiments, and the AI‑infra innovations that enabled a 4.5% CTR lift in production.
This article presents the BiCB (Binary Constrained Bidding) algorithm, a lightweight auto‑bidding solution for live advertising that combines optimal bidding formulas derived from linear‑programming dual analysis with traffic‑prediction statistics to achieve near‑optimal performance under budget and CPC constraints.
This paper introduces ABPlanner, a few‑shot, context‑aware budget planner that enhances budget‑constrained auto‑bidding in online advertising by hierarchically allocating budgets across short‑term stages and training a sequential decision‑maker with deep reinforcement learning, achieving significant gains in simulated and real‑world A/B tests.
This article details Alibaba‑Mama’s AI‑coding initiative, describing how a decoupled CommonAds architecture and a multi‑agent framework called “Yuanfang” transform large‑scale advertising engine development by integrating AI‑friendly design, context‑driven specifications, and automated code‑generation, testing, and validation pipelines.
This article explains how Alibaba Mama’s advertising engine adopted a Serverless, Graph‑as‑a‑Service (GaaS) model to unify budgeting across multiple ad lands, align development‑to‑delivery granularity with graph structures, and dramatically improve testing, experimentation, and production release efficiency.
This article examines the limitations of Vibe Coding for large AI infrastructure, proposes a text‑driven, document‑centric workflow, and presents a time‑multiplexed GPU scheduling solution that dramatically improves rollout throughput and reduces timeouts in large‑scale Agentic RL training.
