Microsoft’s 671B LLM Unifies Offline Ad Tasks—Can It Cut Compute Costs?

Microsoft’s AdNanny replaces a forest of specialized offline models with a single 671 B LLM, using a three‑stage data factory to generate reasoning‑rich corpora, dynamic task re‑weighting, RL‑based metric alignment, and a hybrid 31‑pipeline‑parallel architecture that halves compute cost while boosting performance on core ad‑ranking tasks.

AdNannyLLMLarge Model

0 likes · 9 min read

Microsoft’s 671B LLM Unifies Offline Ad Tasks—Can It Cut Compute Costs?

High Availability Architecture

Nov 4, 2024 · Operations

Ctrip's Weak Network Identification Model: Design, Implementation, and Practice

This article details Ctrip's approach to weak network detection, covering background, data collection, processing, dynamic weighting algorithms, result output, deployment effects, and future plans, and provides practical code examples and threshold settings for improving mobile network performance.

Weak Network Detectiondata collectiondynamic weighting

0 likes · 26 min read

Ctrip's Weak Network Identification Model: Design, Implementation, and Practice

NetEase Smart Enterprise Tech+

Feb 28, 2024 · Artificial Intelligence

Mastering Multi-Task Learning: Network Designs & Loss Balancing

This article reviews the challenges of multi‑task learning, compares various network architectures such as hard‑parameter sharing, MMoE, CGC, and PLE, and examines loss‑balancing techniques like GradNorm, Dynamic Weight Average and task‑prioritization, offering insights on how to mitigate the “seesaw” effect and improve overall performance.

AI researchNeural Networksdynamic weighting

0 likes · 15 min read

Mastering Multi-Task Learning: Network Designs & Loss Balancing

IEG Growth Platform Technology Team

Nov 28, 2022 · Artificial Intelligence

Bidden-MarfNet: Feature Missing-aware Routing-and-Fusion Network for Customer Lifetime Value Prediction

This paper presents Bidden-MarfNet, a novel architecture that explicitly encodes feature‑missing information and dynamically re‑weights samples to address feature missingness and label sparsity in user‑level LTV prediction for advertising, demonstrating superior performance over existing methods through extensive experiments.

LTV predictionMixture of Expertsdynamic weighting

0 likes · 13 min read

Bidden-MarfNet: Feature Missing-aware Routing-and-Fusion Network for Customer Lifetime Value Prediction