cold-start

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

Power Tools for AI Engineers With Deadlines

This repository includes some papers that I have read or which I think may be very interesting.

[Up-to-date] A curated list of resources on cold-start recommendations.

Universal User Representation Pre-training for Cross-domain Recommendation and User Profiling

深度学习与推荐系统学习，理论结合代码更香。

Source code for KDD 2020 paper "Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation"

(Python, R, C) Collective (multi-view/multi-way) matrix factorization, including cold-start functionality (recommender systems, imputation, dimensionality reduction)

ColdRec: An Open-Source Toolbox for Cold-Start Recommendation.

Scaffolding for Cloud Functions deployed with the Firebase CLI that minimize cold starts by using TypeScript async imports

Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scratch. Kubernetes-native checkpoint & restore that runs alongside your existing stack.

Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)

An application to help prevent cold starts in AWS Lambda functions.

Source code for MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation. TKDE 2022.

Lambda Dispatch for AWS Lambda - Avoid cold starts, save up to 80%!

keep lambdas warm and monitor cold starts with a simple decorator

cross-domain recommendation，transfer learning，pre-training，self-supervise learning papers and datasets

Persistent memory and operational continuity for AI coding agents — append-only event ledger (AgentBook), rolling summaries, self-model, belief knowledge, and turn-1 frontpage injection for deterministic cold-start.

Offical Code of MICCAI'25 Best-Paper-Shortlist paper "MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization"

A recommender engine built for a Bay Area online dating website to maximize the successful matches by introducing hybrid recommender system and reverse match technique.