Official Alimama tech channel, showcasing all of Alimama's technical innovations.
Alibaba’s advertising team introduces semantic‑aware contrastive learning to pre‑train multimodal image‑text embeddings, integrates them via SimTier and MAKE into ID‑based CTR models, achieving up to 6.9% lift in Taobao display ad click‑through rates and improving long‑tail item performance.
The paper presents AIGB, a generative auto‑bidding framework that replaces reinforcement‑learning with a conditional diffusion model to generate optimal bidding trajectories, and demonstrates through offline benchmarks and Alibaba’s online A/B tests that it consistently outperforms RL baselines, boosting buy count, GMV, and ROI while maintaining low latency.
The article explains how NeurIPS ranks among top AI conferences, introduces the newly selected “Auto‑Bidding in Large‑Scale Auctions” competition, outlines its technical background, four generations of bidding strategies—from classic control to generative models—and details the competition’s tracks, rewards, and how researchers can participate.
The paper introduces LS‑IMP, a two‑stage local‑search algorithm with four novel operators that efficiently solves guaranteed‑delivery advertising inventory allocation under non‑convex multilinear media‑preference constraints, consistently outperforming commercial solvers and heuristics in solution quality and speed on real‑world datasets.
The 2024 NeurIPS Competition, organized by Peking University's PAAI lab and Alibaba‑Mama, challenges teams to build auto‑bidding agents—using generative models for the AIGB Track or handling uncertainty for the General Track—to maximize ad performance in large‑scale auctions, with registration open until August 8 and prize pools up to $6,000 per track.
CausalMMM introduces an encoder‑decoder framework that automatically discovers heterogeneous, interpretable causal graphs among advertising channels while modeling temporal decay and saturation, using Granger‑based variational inference, and achieves over 5.7% improvement in causal structure learning and significant GMV prediction gains on Alibaba’s data.
The article describes Alibaba's approach to distilling privileged features for CTR prediction using a calibration-compatible listwise distillation loss (CLID) that normalizes teacher and student outputs within sessions to align top‑ranking probabilities, improving both accuracy and ranking while preserving calibration.
Alibaba’s Mama technical team secured four paper acceptances at the prestigious KDD 2024 conference in Barcelona, presenting advances such as a diffusion‑based generative bidding model, truthful combinatorial bandit mechanisms for two‑stage ad auctions, bi‑objective contract allocation for guaranteed delivery advertising, and a fast local‑search algorithm for complex contract constraints.
The Mixed‑Modal Expert Model combines ID features with image and text embeddings through optimized representations and conditional output fusion, dramatically improving advertising recall—especially for long‑tail items—and delivering measurable gains in click‑recall, revenue, CTR, and page views in large‑scale online tests.
On May 18, 2024, CCF and Alibaba Mama will unveil the CCF‑Alibaba Mama Technology Fund—a global academia‑industry platform targeting next‑generation AI algorithms and large‑model research through ten projects in e‑commerce, knowledge‑enhanced generation, and legal AI, with a livestreamed forum featuring a keynote by Prof. Zhang Qi on boosting task performance.
