machine learning

Airbnb Technology Team

Jan 24, 2025 · Artificial Intelligence

Chronon — An Open-Source Framework for Production-Level Feature Engineering in Machine Learning

Chronon is an open‑source framework that centralizes feature definitions to guarantee training‑inference consistency, eliminates complex ETL pipelines, and supports real‑time and batch processing across diverse data sources, cutting feature‑development cycles from months to under a week, as demonstrated by Airbnb’s 40,000‑feature deployment.

ChrononData PipelineHive

0 likes · 10 min read

Chronon — An Open-Source Framework for Production-Level Feature Engineering in Machine Learning

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 Modelsalgorithm frameworkanti-fraud

0 likes · 19 min read

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

Xiaohongshu Tech REDtech

Oct 9, 2024 · Operations

AIOps Implementation at Xiaohongshu: Fault Localization and Intelligent Operations

Xiaohongshu’s AIOps initiative builds a four‑layer framework that leverages machine‑learning‑driven anomaly detection, causal analysis, and trace‑based fault localization to automatically identify root‑cause services in micro‑service environments, achieving over 80 % accuracy across 1000 daily diagnoses while guiding future enhancements in change correlation and automated remediation.

AIOpsAnomaly DetectionDevOps

0 likes · 28 min read

AIOps Implementation at Xiaohongshu: Fault Localization and Intelligent Operations

Xiaohongshu Tech REDtech

Sep 19, 2024 · Artificial Intelligence

Target-Driven Distillation (TDD): A Multi‑Goal Distillation Method for Accelerating Diffusion Models

Target‑Driven Distillation (TDD) is a multi‑goal distillation method that flexibly selects short‑range target steps and decouples guidance during training, enabling 4‑to‑8‑step diffusion generation that preserves high‑resolution detail, works with LoRA, ControlNet, InstantID, and outperforms existing consistency distillation techniques in speed and quality.

AI accelerationImage Generationdiffusion models

0 likes · 9 min read

Target-Driven Distillation (TDD): A Multi‑Goal Distillation Method for Accelerating Diffusion Models

Alimama Tech

Sep 11, 2024 · Artificial Intelligence

A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective

The paper introduces a coupled generative adversarial framework that merges biased observational with unbiased experimental data to create a bias‑free dataset for causal inference, enabling robust treatment‑effect estimation under collider bias from an out‑of‑distribution perspective, and demonstrates superior bias reduction on three public advertising datasets.

Generative Adversarial Networksadvertisingcausal inference

0 likes · 10 min read

A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective

DaTaobao Tech

Aug 19, 2024 · Frontend Development

Challenges and Solutions in AI-Powered Front-End Code Generation for B2C Platforms

The article details how Taobao’s AI team automated repetitive UI tasks for B2C front‑end development, achieving a 15 % efficiency gain across five projects, and outlines key challenges—prompt cost, low OCR accuracy, hallucinations, excess nodes, and customization variance—along with practical solutions such as a dedicated evaluation platform, OCR translation, model upgrades, prompt segmentation, output simplification, and a reusable component library.

AICode GenerationUI automation

0 likes · 9 min read

Challenges and Solutions in AI-Powered Front-End Code Generation for B2C Platforms

Ximalaya Technology Team

Jul 12, 2024 · Artificial Intelligence

Multi-Path Recall and Ranking Techniques in Real-Time Bidding Advertising Systems

In real‑time bidding advertising, a multi‑path recall framework quickly filters billions of ads using parallel non‑personalized and personalized strategies—such as hot‑item rules, collaborative‑filtering, skip‑gram vectors, and GraphSAGE embeddings—while respecting targeting constraints, before a ranking stage optimizes eCPM, with effectiveness measured offline and online and future extensions planned with large language models.

Rankingadvertisinggraph neural network

0 likes · 18 min read

Multi-Path Recall and Ranking Techniques in Real-Time Bidding Advertising Systems

Ximalaya Technology Team

Apr 30, 2024 · Artificial Intelligence

Multi‑Stage Funnel Architecture and Optimization Practices in an Advertising Engine

The advertising engine uses a five‑stage funnel—retrieval, recall, coarse ranking, fine ranking, and re‑ranking—each optimized with specialized indexes, multi‑channel recall, multi‑objective twin‑tower models, deep CTR/CVR predictors, and cold‑start paths, delivering up to 33 % spend growth, 6 % eCPM lift and lower latency while maintaining diversity.

Cold StartRankingadvertising

0 likes · 15 min read

Multi‑Stage Funnel Architecture and Optimization Practices in an Advertising Engine

DaTaobao Tech

Mar 4, 2024 · Artificial Intelligence

Iris Classification with Machine Learning: Data Exploration and Classic Algorithms

This beginner-friendly guide walks through loading the classic Iris dataset, performing exploratory data analysis, and implementing four fundamental classifiers—Decision Tree, Logistic Regression, Support Vector Machine, and K‑Nearest Neighbors—complete with training, visualization, and accuracy evaluation, illustrating a full machine‑learning workflow.

SVMclassificationdecision tree

0 likes · 22 min read

Iris Classification with Machine Learning: Data Exploration and Classic Algorithms

Xiaohongshu Tech REDtech

Jan 12, 2024 · Artificial Intelligence

Negative Sample Assisted Distillation for Large Language Models

The AAAI‑2024 paper introduces a Negative Sample Assisted Distillation framework—comprising Negative Assistance Training, Negative Calibration Enhancement, and Adaptive Self‑Consistency—that leverages both correct and incorrect reasoning examples to train a compact LLaMA‑7B student, achieving up to 75.75 % accuracy gains over fine‑tuning on MATH and improving out‑of‑domain benchmarks.

Chain-of-ThoughtLLMknowledge distillation

0 likes · 13 min read

Negative Sample Assisted Distillation for Large Language Models

Alimama Tech

Nov 28, 2023 · Artificial Intelligence

Evolution of Alibaba's AI-Driven Advertising Decision Technologies

The article traces Alibaba’s Alimama platform from classic control‑based bidding through linear programming and reinforcement‑learning approaches to generative‑AI‑driven strategies, detailing how deep‑learning models, offline and sustainable online RL frameworks, and large‑language‑model‑based bidding reshape automated auctions, fairness, and scalability in e‑commerce advertising.

AIadvertisingauction design

0 likes · 38 min read

Evolution of Alibaba's AI-Driven Advertising Decision Technologies

Alimama Tech

Nov 15, 2023 · Artificial Intelligence

Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking (HC²)

The HC² framework enhances multi‑scenario ad ranking by jointly applying a generalized contrastive loss on shared representations and an individual contrastive loss on scenario‑specific layers, using label‑aware positive sampling, diffusion‑noise negative sampling, and inverse‑similarity weighting, achieving consistent offline gains and up to 2.5% CVR and 3.7% GMV improvements in Alibaba’s live system.

Recommendation systemsad rankingcontrastive learning

0 likes · 16 min read

Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking (HC²)

Xiaohongshu Tech REDtech

Nov 6, 2023 · Artificial Intelligence

Large Models and Recommendation Systems: Challenges, Opportunities, and Future Directions

At CNCC 2023, leading researchers and industry experts convened to examine how large language models can transform recommendation systems, outlining four core challenges—model integration, fluency versus intelligence, hallucination versus deception, and user understanding—while highlighting opportunities such as multimodal content, cold‑start solutions, zero‑shot ranking, instruction‑driven algorithms, and responsible, interactive recommendation pipelines.

AICNCC 2023Cold Start

0 likes · 16 min read

Large Models and Recommendation Systems: Challenges, Opportunities, and Future Directions

DaTaobao Tech

Apr 24, 2023 · Artificial Intelligence

Daily Good Shop: Two‑Stage Card Ranking and Multi‑Task Modeling for E‑commerce Recommendations

Daily Good Shop improves e‑commerce recommendations by first ranking products with long‑term user behavior models, assembling top items into cards, then ranking those cards using a shared‑bottom multi‑task network that jointly predicts click, subscription and lead‑IPV, and finally re‑ranking card sequences via beam‑search, yielding over 2 % more clicks, 34 % more subscriptions, 33 % more lead‑IPV and 22 % longer dwell time.

Rankinge-commercemachine learning

0 likes · 11 min read

Daily Good Shop: Two‑Stage Card Ranking and Multi‑Task Modeling for E‑commerce Recommendations

HelloTech

Apr 12, 2023 · Artificial Intelligence

Integrating Machine Learning Ranking into Elasticsearch: Architecture, Components, and Performance

The team embedded a full machine‑learning ranking pipeline as an Elasticsearch plug‑in—combining real‑time and offline feature stores, hot‑loadable model jars via Dragonfly, an MLeap execution engine, and a DSL for feature definition—replacing the coarse‑ranking logistic‑regression with a tree model that adds ~10 ms latency but yields a 1.2 % AB‑test lift, while maintaining high throughput, low CPU usage, and supporting future batch deep‑learning rescoring.

Model Deploymentelasticsearchfeature engineering

0 likes · 16 min read

Integrating Machine Learning Ranking into Elasticsearch: Architecture, Components, and Performance

DaTaobao Tech

Mar 22, 2023 · Artificial Intelligence

A Comprehensive Overview of Text-to-Image Generation: From GANs to Stable Diffusion and Advanced Techniques

The article traces the evolution of text‑to‑image generation from early GANs through auto‑regressive and CLIP‑guided diffusion models, explains Stable Diffusion’s architecture and prompt engineering, and reviews advanced personalization techniques such as Textual Inversion, DreamBooth, ControlNet, plus efficient OneFlow deployment and diverse real‑world applications.

AI artStable Diffusiondiffusion models

0 likes · 17 min read

A Comprehensive Overview of Text-to-Image Generation: From GANs to Stable Diffusion and Advanced Techniques

vivo Internet Technology

Feb 15, 2023 · Information Security

Ad Traffic Anti‑Fraud: Algorithms, System Architecture, and Case Studies

The article explains how ad traffic fraud—ranging from simulated impressions to click farms—can be combated using a four‑layer risk‑control system that leverages unsupervised (DBSCAN, Isolation Forest) and supervised (Logistic Regression, Random Forest) algorithms, detailing data pipelines, model training, monitoring, and real‑world case studies.

Anomaly Detectionad fraudadvertising

0 likes · 15 min read

Ad Traffic Anti‑Fraud: Algorithms, System Architecture, and Case Studies

Alimama Tech

May 25, 2022 · Artificial Intelligence

UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation

The paper introduces UKD, an uncertainty‑regularized knowledge‑distillation framework that uses a click‑adaptive teacher to generate pseudo‑conversion labels for unclicked impressions and trains a student model with uncertainty‑weighted loss, thereby mitigating sample‑selection bias and achieving up to 3.4% CVR improvement and 4.3% CPA reduction on large‑scale advertising datasets.

CVR debiasingadvertising algorithmsconversion rate estimation

0 likes · 20 min read

UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation

Alimama Tech

May 25, 2022 · Artificial Intelligence

AdaCalib: Posterior-Guided Feature-Adaptive Calibration Model for Online Advertising

AdaCalib is a posterior‑guided feature‑adaptive calibration model for online advertising that learns per‑feature piecewise‑linear calibration functions via a deep neural network with adaptive bucketing, improving probability estimates and ranking, achieving lower Field‑RCE, higher AUC, and a 5% CVR lift in live tests.

Deep neural networkscalibrationfeature adaptation

0 likes · 19 min read

AdaCalib: Posterior-Guided Feature-Adaptive Calibration Model for Online Advertising

Alimama Tech

May 18, 2022 · Artificial Intelligence

Multiple Boosting Calibration Trees (MBCT): Feature‑Aware Binning for Uncertainty Calibration

The paper introduces Multiple Boosting Calibration Trees, a feature‑aware binning ensemble that uses a new multi‑view calibration error metric and boosting to learn personalized, non‑monotonic calibrations for CTR prediction, achieving lower calibration error and higher click‑through rates and revenue than existing methods in both offline and online tests.

MVCEadvertisingfeature-aware binning

0 likes · 18 min read

Multiple Boosting Calibration Trees (MBCT): Feature‑Aware Binning for Uncertainty Calibration