Author

Alimama Tech

Official Alimama tech channel, showcasing all of Alimama's technical innovations.

247

Articles

Likes

770

Views

Comments

Latest from Alimama Tech

100 recent articles max

Alimama Tech

Dec 25, 2024 · Artificial Intelligence

WiS Platform: Evaluating LLM Multi-Agent Systems via Game-Based Analysis

The WiS Platform provides a game‑based environment for benchmarking large language models in multi‑agent settings, measuring reasoning, deception and collaboration through dynamic scenarios, offering fair experimental design, real‑time competition, visualizations, detailed metrics, and open‑source tools, with GPT‑4o outperforming other models such as Qwen2.5‑72B‑Instruct.

AI evaluationDefense StrategiesGame-Based Testing

0 likes · 8 min read

WiS Platform: Evaluating LLM Multi-Agent Systems via Game-Based Analysis

Alimama Tech

Dec 25, 2024 · Artificial Intelligence

Contextual Generative Auction with Permutation-level Externalities for Online Advertising

The paper introduces Contextual Generative Auction (CGA), a generative framework that directly optimizes ad placements while modeling permutation‑level externalities, decouples allocation from payment learning, and achieves near‑optimal Myerson‑style outcomes, delivering up to 3.2% higher RPM, 1.4% more CTR, 6.4% GMV growth, and 3.5% increased advertiser ROI in large‑scale Taobao experiments.

ExternalitiesGenerative ModelsMachine Learning

0 likes · 18 min read

Contextual Generative Auction with Permutation-level Externalities for Online Advertising

Alimama Tech

Dec 17, 2024 · Artificial Intelligence

Auto‑Bidding in Large‑Scale Auctions: The AIGB Paradigm and the AuctionNet Benchmark

At NeurIPS 2024, Alibaba's AliMama workshop introduced AIGB, a generative-model based auto-bidding solution, and released AuctionNet benchmark with billions of records; the competition attracted 1,861 participants across generative and uncertainty tracks, with winners earning prizes and internships, highlighting broader applications beyond advertising.

AuctionNetNeurIPSdecision intelligence

0 likes · 12 min read

Auto‑Bidding in Large‑Scale Auctions: The AIGB Paradigm and the AuctionNet Benchmark

Alimama Tech

Dec 17, 2024 · Artificial Intelligence

AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games

AuctionNet is a newly introduced benchmark that recreates a massive, realistic online advertising auction environment using latent diffusion‑generated traffic data, provides an 80 GB dataset of 5 × 10⁸ logs from 48 bidding agents, and offers baseline evaluations—including an Online LP that outperforms others—supporting thousands of fair NeurIPS 2024 competition submissions and open‑source tools for large‑scale game decision‑making research.

Generative Modelsauto-biddingbenchmark

0 likes · 15 min read

AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games

Alimama Tech

Dec 11, 2024 · Artificial Intelligence

Engineering Architecture of Alibaba's AI Digital Employee "AI XiaoWan"

Alibaba’s AI digital employee “AI XiaoWan” uses a native multi‑agent architecture where a Controller Agent interprets intent, plans tasks, and orchestrates execution while an Executable Agent performs domain‑specific operations, communicating via a standardized Agent Communication Protocol, leveraging a centralized Tool Center, a retrieval‑augmented knowledge base, and a data‑flywheel feedback loop to continuously improve and evolve toward memory‑based reasoning and self‑learning.

AIKnowledge BaseLarge Language Model

0 likes · 14 min read

Engineering Architecture of Alibaba's AI Digital Employee "AI XiaoWan"

Alimama Tech

Dec 4, 2024 · Artificial Intelligence

AIGB: Generative Auto‑Bidding via Diffusion Modeling

AIGB, introduced by Alibaba Mama in 2023, reframes large‑scale ad‑auction auto‑bidding as a generative sequence task using diffusion models, achieving up to 5 % GMV gains, improved stability and interpretability, and is now commercialized, open‑sourced, and featured in a NeurIPS‑endorsed competition.

AIGenerative Modelsauto-bidding

0 likes · 12 min read

AIGB: Generative Auto‑Bidding via Diffusion Modeling

Alimama Tech

Nov 27, 2024 · Artificial Intelligence

FlowDCN: Efficient Arbitrary-Resolution Image Generation via Groupwise Multi‑Scale Deformable Convolution

FlowDCN introduces Groupwise‑MSDCN, a sparse deformable convolution that replaces attention, enabling efficient arbitrary‑resolution image generation with linear complexity, fewer parameters and FLOPs, and achieving state‑of‑the‑art FID scores on ImageNet while requiring far fewer training steps.

Deformable Convolutionarbitrary resolutiondiffusion models

0 likes · 12 min read

FlowDCN: Efficient Arbitrary-Resolution Image Generation via Groupwise Multi‑Scale Deformable Convolution

Alimama Tech

Nov 13, 2024 · Artificial Intelligence

DeepString: Alibaba's Anti‑Fraud Platform Using Large Models for Real‑Time Traffic Detection

Alibaba's anti-fraud platform DeepString uses large unsupervised models to detect abnormal traffic in real time across multiple advertising products, combining a foundation model for event mining, anomaly measurement, and an alignment model for online filtering, reducing reliance on manual labeling and domain expertise.

Large ModelsMachine Learningalgorithm framework

0 likes · 19 min read

DeepString: Alibaba's Anti‑Fraud Platform Using Large Models for Real‑Time Traffic Detection

Alimama Tech

Nov 6, 2024 · Artificial Intelligence

How AI Generates Synchronized Video Narrations for E‑Commerce

This article presents the research behind Synchronized Video Storytelling, introducing the E‑SyncVidStory dataset, the VideoNarrator multimodal architecture, and extensive experiments that demonstrate high‑quality, product‑aware video narration generation for e‑commerce applications.

LLMdatasete-commerce

0 likes · 12 min read

How AI Generates Synchronized Video Narrations for E‑Commerce

Alimama Tech

Oct 17, 2024 · Artificial Intelligence

FLUX ControlNet Inpainting and 8-Step Turbo Acceleration Models

Alibaba’s Mama Intelligent Creation team has open‑sourced a FLUX‑based ControlNet inpainting model that leverages a DiT‑backed Interleave design for superior repair quality, and an 8‑step LoRA‑Turbo model that cuts inference time three‑fold while preserving near‑original image fidelity, both now available on Hugging Face and ModelScope.

AIControlNetFlux

0 likes · 9 min read

FLUX ControlNet Inpainting and 8-Step Turbo Acceleration Models