Official Alimama tech channel, showcasing all of Alimama's technical innovations.
This article presents a differentiable solver search method that quickly finds high‑quality sampling paths for diffusion models, demonstrating significant FID improvements across Rectified‑Flow, DDPM/VP, and text‑to‑image models while requiring no model parameter changes.
This article details the author's experience designing a top‑performing AI Werewolf agent for the Taotian Group's AI Werewolf Challenge, covering game rules, core challenges, prompt engineering, caching, concurrent requests, model selection, reinforcement‑learning‑style tuning, and tactical strategies for each role, with code examples.
This article explores Alibaba’s Taotian technology team, revealing how its young engineers blend cutting‑edge AI research with playful projects like AI‑driven Werewolf games, develop large‑scale recommendation models such as RecGPT, and foster a culture of curiosity, rapid experimentation, and flat, tech‑first management.
This article introduces ConfuseBench, a benchmark that classifies LLM uncertainty into document‑missing, ability‑limited, and ambiguous types, and presents methods—including retrieval, chain‑of‑thought, and clarification—to detect and actively resolve uncertainty, improving answer quality across diverse tasks.
ROLL is an open‑source reinforcement‑learning framework designed for large language model post‑training that combines multi‑task RL, agentic support, flexible algorithm configuration, elastic resource scheduling, and rich observability, delivering significant accuracy gains across benchmarks while remaining easy to use for researchers, product developers, and infrastructure engineers.
This article presents a large‑scale advertising risk‑control solution that combines deep‑research paradigms, domain‑graph constraints, and large language models to enable explainable, responsible, and high‑precision fraud detection, detailing system architecture, challenges, demo workflow, and future directions.
The article presents the Universal Recommendation Model (URM), a large‑language‑model‑based recall framework that integrates world knowledge and e‑commerce expertise through knowledge injection and prompt‑driven alignment, achieving significant offline recall gains and a 3.1% increase in ad consumption while meeting high‑QPS, low‑latency production constraints.
The campus AI Agent competition showcased how large‑language‑model‑powered agents can reason, deceive, and collaborate in a social deduction game, revealing model performance trends, participant insights, and future directions for multi‑agent AI research.
Distribution‑aware Graph Prompt Tuning (DAGPrompT) tackles the pre‑training/downstream mismatch on heterophilic graphs by jointly applying low‑rank GLoRA adaptation and hop‑specific prompts that recast tasks as link‑prediction, yielding up to 4.79% accuracy gains and an average 2.43% improvement in few‑shot node classification.
The paper introduces an explainable LLM framework (ELLM‑rele) that uses chain‑of‑thought reasoning and a multi‑dimensional knowledge distillation pipeline to compress large‑model relevance judgments into lightweight student models, achieving superior offline relevance scores and online click‑through and conversion improvements in Taobao’s search advertising.
