| 生成、排序与冷启动 |
One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations |
Tencent，2026-09-16 |
未发现官方代码 |
angle |
| 展示层生成与个性化 |
Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation |
Baidu，2026-09-14 |
未发现官方代码 |
gese |
| 排序与长序列建模 |
LazFormer: Scaling Transformers for Industrial Recommendation via Transferable Generative Pre-training |
Alibaba International Digital Commerce Group，2026-09-14 |
未发现官方代码 |
lazformer |
| 生成、排序与冷启动 |
ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling |
Tencent，2026-09-11 |
未发现官方代码 |
chronicle-rec |
| 生成、排序与冷启动 |
MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive Assignment |
Alibaba International Digital Commerce Group，2026-09-11 |
未发现官方代码 |
mima |
| 内容理解、审核与风险控制 |
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control |
Xiaohongshu，2026-09-10 |
未发现官方代码 |
sirf |
| 多阶段排序与混排 |
UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems |
Kuaishou，2026-09-10 |
未发现官方代码 |
unirec |
| Serving 与研究基础设施 |
BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests |
Dable，2026-09-08 |
未发现官方代码 |
baff |
| 多阶段排序与混排 |
SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching |
ByteDance / Douyin，2026-09-08 |
未发现官方代码 |
sequenceo1 |
| Serving 与研究基础设施 |
AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems |
NetEase, Inc.，2026-09-04 |
未发现官方代码 |
autolr |
| Serving 与研究基础设施 |
Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro |
Allegro.com，2026-09-04 |
未发现官方代码 |
allecompanion |
| Serving 与研究基础设施 |
CORAL: An LLM-Native Harness for Production Recommender Systems |
Meta AI，2026-09-02 |
未发现官方代码 |
coral |
| 生成、排序与冷启动 |
From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs |
ByteDance，2026-09-01 |
未发现官方代码 |
rest |
| 生成、排序与冷启动 |
TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning |
Tencent，2026-09-01 |
未发现官方代码 |
tgr |
| 内容理解、审核与风险控制 |
CAMIE: Co-Engagement-Aware Multimodal Item Embeddings for Snap Dynamic Product Ads Retrieval |
Snap Inc.，2026-08-31 |
未发现官方代码 |
camie |
| Serving 与研究基础设施 |
SetMIR: Multi-Interest Retrieval as Set Prediction |
Snap Inc.，2026-08-31 |
未发现官方代码 |
setmir |
| 生成、排序与冷启动 |
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling |
AI VK，2026-08-27 |
已开源 |
friend-gnn |
| 生成、排序与冷启动 |
DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search |
Taobao & Tmall Group, Alibaba，2026-08-26 |
未发现官方代码 |
dceo |
| 生成、排序与冷启动 |
TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation |
Renmin University of China / Taobao & Tmall Group, Alibaba，2026-08-26 |
未发现官方代码 |
transretrieval |
| 生成、排序与冷启动 |
TAGR: Temporally Adaptive Generative Recommendation for Industrial Live-Streaming Advertising |
Kuaishou Technology，2026-08-25 |
未发现官方代码 |
tagr |
| 生成、排序与冷启动 |
From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation |
Kuaishou Technology，2026-08-21 |
未发现官方代码 |
dynamic-codebook |
| 生成、排序与冷启动 |
OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking |
Xiaohongshu，2026-08-19 |
未发现官方代码 |
onemodel |
| 内容理解、审核与风险控制 |
Multimedia Asset Personalization via Multimodal Embeddings at Netflix |
Netflix，2026-08-18 |
未发现官方代码 |
netflix-mediafm |
| 多阶段排序与混排 |
Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs |
Kuaishou Technology，2026-08-18 |
未发现官方代码 |
ogr |
| 生成、排序与冷启动 |
DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation |
Shenzhen University，2026-08-13 |
未发现官方代码 |
drem |
| 生成、排序与冷启动 |
Sona Technical Report |
Yandex，2026-08-11 |
未发现官方代码 |
sona |
| 大模型能力与推荐融合 |
ConnectionMind: A General Social-Personalized Recommendation System with LLM Reasoning |
Michigan State University，2026-08-10 |
未发现官方代码 |
connectionmind |
| 大模型能力与推荐融合 |
DREAM: A Dual-Loop Recommendation Evolution Framework Powered by Large Language Models |
Taobao & Tmall Group / Alibaba，2026-08-10 |
未发现官方代码 |
dream |
| 训练目标与决策优化 |
From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation |
LinkedIn，2026-08-10 |
未发现官方代码 |
incrementality |
| 大模型能力与推荐融合 |
GenRec: An LLM-Backed Recommendation Ranker at Netflix |
Netflix，2026-08-10 |
未发现官方代码 |
genrec-netflix |
| 生成、排序与冷启动 |
IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation |
Amap / Alibaba，2026-08-10 |
未发现官方代码 |
inthq |
| 生成、排序与冷启动 |
MetaStrategy: Generative Ranking with Executable LLM Strategies |
Alibaba / Taobao，2026-08-10 |
未发现官方代码 |
metastrategy |
| 生成、排序与冷启动 |
PushDualGen: Enabling LLMs to Generate Semantic IDs with Interpretable Copy for Industrial Push Recommendation |
Kuaishou Technology，2026-08-08 |
未发现官方代码 |
pushdualgen |
| 生成、排序与冷启动 |
Teacher Retains Full Tokens, Student Merges Efficiently: TM20K for E-Commerce Sequence Modeling in Ad Recommendation |
ByteDance，2026-08-07 |
未发现官方代码 |
tm20k |
| 生成、排序与冷启动 |
Gryphon-v2: One Model in Place of a Cascade — Generate-and-Rank Recommender with Rollout Distillation |
Yandex，2026-08-06 |
未发现官方代码 |
gryphon-v2 |
| 多阶段排序与混排 |
DEGR: Dual Exploration-Driven Generative Re-Ranking for Adaptive Cross-Request Context Bridging |
JD.com，2026-08-05 |
未发现官方代码 |
degr |
| 多阶段排序与混排 |
Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting |
Twitch，2026-08-05 |
未发现官方代码 |
twitch-mor |
| 生成、排序与冷启动 |
LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation |
NAVER WEBTOON，2026-08-04 |
未发现官方代码 |
llm-ts-prior |
| 多阶段排序与混排 |
A Self-Triggered Agentic Push Recommendation System |
ByteDance / Douyin，2026-08-03 |
未发现官方代码 |
steps |
| 内容理解、审核与风险控制 |
Douyin Multimodal Embedding Model Technical Report |
ByteDance / Douyin，2026-08-03 |
未发现官方代码 |
dme |
| 训练目标与决策优化 |
Knowledge–Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation |
Xiamen University / Shopee，2026-08-03 |
已开源 |
kgd |
| 多阶段排序与混排 |
SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search |
Dewu，2026-08-03 |
已开源 |
spear |
| 生成、排序与冷启动 |
Hierarchical Residual Policy Optimization for Generative Recommendations |
City University of Hong Kong / Kuaishou，2026-08-01 |
已开源 |
hrpo |
| 内容理解、审核与风险控制 |
GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System |
Rajax Network Technology / Taobao Shangou / Alibaba，2026-07-31 |
未发现官方代码 |
gala |
| 训练目标与决策优化 |
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems |
Huazhong Agricultural University (Kuaishou internship)，2026-07-31 |
已开源 |
recharness |
| 生成、排序与冷启动 |
TransX: Scaling Transformer-based Recommendation via Behavioral and Serving Stream Crossings |
LinkedIn，2026-07-31 |
未发现官方代码 |
transx |
| 大模型能力与推荐融合 |
Building a User Foundation Model for the Open Web |
Teads，2026-07-30 |
未发现官方代码 |
open-web-ufm |
| 生成、排序与冷启动 |
CCFormer: Efficient Cross-Field Interaction and Hierarchical Sequence Compression for Industrial Recommendation at Tencent |
Tencent Platform and Content Group，2026-07-30 |
未发现官方代码 |
ccformer |
| 训练目标与决策优化 |
From Understanding to Action: Feedback-Grounded Policy Discovery for Generative Recommendation |
Huazhong Agricultural University (Kuaishou internship)，2026-07-30 |
未发现官方代码 |
feedback-policy |
| 生成、排序与冷启动 |
Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case Study |
Google / Discover，2026-07-30 |
未发现官方代码 |
ha-moe |
| 生成、排序与冷启动 |
LLM-Based Generative Retrieval for Snapchat Content Recommendation |
Snap Inc.，2026-07-30 |
未发现官方代码 |
snaplgr |
| 生成、排序与冷启动 |
ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation |
Meta AI，2026-07-30 |
已开源 |
rocs |
| 训练目标与决策优化 |
ASARL: Autonomous Social-Aware Relevance Learning for QQ Search |
Tencent PCG，2026-07-29 |
未发现官方代码 |
asarl |
| 生成、排序与冷启动 |
ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling |
YouTube / Google DeepMind，2026-07-29 |
未发现官方代码 |
clockrope |
| 多阶段排序与混排 |
DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval |
University of Science and Technology of China，2026-07-29 |
未发现官方代码 |
director |
| 多阶段排序与混排 |
OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval |
Meta / Instagram，2026-07-29 |
未发现官方代码 |
oneshot-index |
| 多阶段排序与混排 |
PSG: Pair-Space Generation for Efficient Generative Reranking |
Kuaishou Technology，2026-07-29 |
未发现官方代码 |
psg |
| 训练目标与决策优化 |
Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness |
Alibaba International Digital Commerce / Dalian University of Technology，2026-07-28 |
未发现官方代码 |
swag-bid |
| 大模型能力与推荐融合 |
RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation |
Kuaishou / Nankai University / Chinese Academy of Sciences，2026-07-28 |
未发现官方代码 |
reco-reward |
| 训练目标与决策优化 |
Reward Guided Decoding for Generative Recommendation |
Institute of Information Engineering, Chinese Academy of Sciences，2026-07-28 |
未发现官方代码 |
reward-guided-decoding |
| 生成、排序与冷启动 |
TWICE: Two-Clock, Two-Window Learning for Long-Horizon Conversion Prediction in Online Advertising |
Kuaishou，2026-07-28 |
未发现官方代码 |
twice |
| 生成、排序与冷启动 |
CORE: A Unified Cascaded Ordinal Relevance Estimation Framework for E-commerce Search |
Meituan / Beijing Institute of Technology，2026-07-27 |
未发现官方代码 |
core-relevance |
| Serving 与研究基础设施 |
Memory Layer: Train the In-Model Cache for Recommendation Models |
Meta / Instagram Reels，2026-07-27 |
未发现官方代码 |
memory-layer |
| 生成、排序与冷启动 |
Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta |
Meta，2026-07-27 |
未发现官方代码 |
mosaic |
| 生成、排序与冷启动 |
OxygenREC-v2: Internalizing Discrimination into Generative Recommendation |
JD.COM，2026-07-27 |
未发现官方代码 |
oxygenrec-v2 |
| 生成、排序与冷启动 |
SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation |
Zhejiang University，2026-07-27 |
未发现官方代码 |
specformer |
| 生成、排序与冷启动 |
Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence |
Kuaishou / IIE, CAS / UCAS，2026-07-27 |
未发现官方代码 |
unir2 |
| 生成、排序与冷启动 |
Breaking the Loop: An Empirical Comparison of Strategies for Novelty and Freshness in YouTube Music |
YouTube Music / Google，2026-07-26 |
未发现官方代码 |
youtube-freshness |
| 大模型能力与推荐融合 |
Melo: A Production LLM-Powered Music Recommendation Agent |
NetEase Cloud Music / Zhejiang University of Technology，2026-07-26 |
未发现官方代码 |
melo |
| 生成、排序与冷启动 |
Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in Recommendation Systems |
Google DeepMind / YouTube，2026-07-26 |
未发现官方代码 |
dual-sid |
| 大模型能力与推荐融合 |
EGR: Embedding-Native Generative Retrieval with a Shared LLM |
Snap Inc.，2026-07-25 |
未发现官方代码 |
egr |
| 生成、排序与冷启动 |
Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation |
Tencent，2026-07-23 |
未发现官方代码 |
barge |
| 生成、排序与冷启动 |
PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest |
Pinterest，2026-07-23 |
未发现官方代码 |
pinequalizer |
| Serving 与研究基础设施 |
PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale |
Pinterest，2026-07-21 |
未发现官方代码 |
pindco |
| 生成、排序与冷启动 |
TSGR: Taobao Search Generative Retrieval |
Taobao & Tmall Group of Alibaba / Zhejiang University，2026-07-21 |
未发现官方代码 |
tsgr |
| 训练目标与决策优化 |
RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways |
Huawei Ireland Research Center / University College Dublin，2026-07-20 |
已开源 |
ramp |
| Serving 与研究基础设施 |
RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems |
Google，2026-07-20 |
未发现官方代码 |
recevolve |
| 生成、排序与冷启动 |
Pin-SCALE: Semantic Cascading and Alignment Learning for Engagement-Aware IDs in Cold-Start Recommendations |
Pinterest，2026-07-19 |
未发现官方代码 |
pin-scale |
| 训练目标与决策优化 |
Uncertainty as Remedy: Mitigating Satisfaction Label Bias in Short Video Multi-Objective Ensemble Ranking |
Kuaishou Technology，2026-07-19 |
未发现官方代码 |
uame |
| 生成、排序与冷启动 |
WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture |
Meta Platforms, Inc.，2026-07-19 |
未发现官方代码 |
whale |
| 大模型能力与推荐融合 |
RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation |
Kuaishou Technology / USTC，2026-07-17 |
未发现官方代码 |
recap |
| 大模型能力与推荐融合 |
RecGPT-V3 Technical Report |
Alibaba / Taobao，2026-07-17 |
未发现官方代码 |
recgpt-v3 |
| 多阶段排序与混排 |
LLM-Based Re-Ranking for Real Estate Search |
QuintoAndar，2026-07-16 |
未发现官方代码 |
real-estate-rerank |
| 训练目标与决策优化 |
Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment |
University of Washington，2026-07-15 |
未发现官方代码 |
adaptive-ad-load |
| 生成、排序与冷启动 |
Long-History User Transformers for Real-Time Ad Ranking |
Yandex，2026-07-15 |
未发现官方代码 |
long-history-transformer |
| 训练目标与决策优化 |
Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning |
Pinterest，2026-07-15 |
未发现官方代码 |
downstream-rewards |
| 生成、排序与冷启动 |
TMallGS: Scaling Unified Feature and Sequence Modeling for Generative E-commerce Search |
Taobao & Tmall Group of Alibaba，2026-07-15 |
未发现官方代码 |
tmallgs |
| 生成、排序与冷启动 |
Cheaper is Better: A Discount-Aware Network for Conversion Rate Prediction in E-commerce Recommendation System |
Alibaba Group / Tmall，2026-07-14 |
已开源 |
danet |
| 训练目标与决策优化 |
Deep-learning Causal Retrieval Optimization for Efficient e-commerce Distribution in Pinterest |
Pinterest，2026-07-14 |
未发现官方代码 |
causal-retrieval |
| 生成、排序与冷启动 |
Learning to Forget: Satiation-Aware Long-Sequence Transducers for Mitigating Post-Purchase Redundancy |
Alibaba Group，2026-07-14 |
未发现官方代码 |
sam |
| 生成、排序与冷启动 |
MESH: Scaling Up Retrieval with Heterogeneous Content Unification |
Pinterest，2026-07-14 |
未发现官方代码 |
mesh |
| 生成、排序与冷启动 |
Not Only NTP: Extending Training Signal Coverage for Generative Recommendation |
Meituan，2026-07-14 |
未发现官方代码 |
nontp |
| 生成、排序与冷启动 |
Proximity Features: Privacy-Compliant Cold-Start Personalization at Airbnb |
Airbnb，2026-07-14 |
未发现官方代码 |
proximity-features |
| 生成、排序与冷启动 |
SlimPer: Make Personalization Model Slim and Smart |
Meta Platforms, Inc.，2026-07-14 |
未发现官方代码 |
slimper |
| 生成、排序与冷启动 |
Guess Where You Go: Generative Next Point-of-Interest Recommendation in Amap |
Amap / Alibaba，2026-07-13 |
已开源 |
guess-where-you-go |
| 生成、排序与冷启动 |
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation |
Technical University of Denmark，2026-07-12 |
未发现官方代码 |
zorro |
| 大模型能力与推荐融合 |
Multilingual Semantic Retrieval for Apple Music Search |
Apple，2026-07-11 |
未发现官方代码 |
elise |
| 训练目标与决策优化 |
Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval |
Meta，2026-07-01 |
未发现官方代码 |
cluster-goobs |
| 大模型能力与推荐融合 |
Prompt Generation Technical Report |
Alibaba / Taobao Search，2026-07 |
未发现官方代码 |
prompt-generation |
| 多阶段排序与混排 |
GenPage: Towards End-to-End Generative Homepage Construction at Netflix |
Netflix，2026-06-30 |
未发现官方代码 |
genpage |
| 多阶段排序与混排 |
POEM: Partial-Order Enhanced Real-Time Sequential Modeling for Recommendation |
Kuaishou，2026-06-29 |
未发现官方代码 |
poem |
| 大模型能力与推荐融合 |
NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model |
Meta，2026-06-27 |
未发现官方代码 |
next-vlm |
| 生成、排序与冷启动 |
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems |
Meta，2026-06-26 |
未发现官方代码 |
cmsl |
| Serving 与研究基础设施 |
NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems |
Tencent，2026-06-25 |
未发现官方代码 |
nova |
| 生成、排序与冷启动 |
UniFormer: Efficient and Unified Model-Centric Scaling for Industrial Recommendation |
Kuaishou，2026-06-25 |
未发现官方代码 |
uniformer |
| 生成、排序与冷启动 |
Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale |
Kuaishou / Beihang University，2026-06-24 |
未发现官方代码 |
rag-generation |
| 大模型能力与推荐融合 |
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems |
Google DeepMind / YouTube，2026-06-23 |
未发现官方代码 |
tokenminds |
| 生成、排序与冷启动 |
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation |
Meta，2026-06-18 |
未发现官方代码 |
g2rec |
| 生成、排序与冷启动 |
JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling |
Airbnb，2026-06-17 |
未发现官方代码 |
journeyformer |
| Serving 与研究基础设施 |
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation |
Meta，2026-06-16 |
未发现官方代码 |
rankgraph2 |
| Serving 与研究基础设施 |
EvoRec: Self-Evolving Agentic Recommender Systems |
Alibaba International Digital Commerce Group，2026-06-15 |
未发现官方代码 |
evorec |
| 生成、排序与冷启动 |
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation |
Renmin University of China，2026-06-15 |
未发现官方代码 |
onerank |
| 多阶段排序与混排 |
PIANO: Personalized Reranking via Information Aggregation Node for Music Search Optimization |
NetEase Cloud Music，2026-06-15 |
未发现官方代码 |
piano |
| 大模型能力与推荐融合 |
Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations |
The Hong Kong Polytechnic University，2026-06-09 |
未发现官方代码 |
atomic-intent |
| 大模型能力与推荐融合 |
ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants |
Huazhong University of Science and Technology，2026-06-07 |
未发现官方代码 |
toolrec |
| 生成、排序与冷启动 |
SSRLive: Live Streaming Recommendation with Dynamic Semantic ID |
Taobao & Tmall Group, Alibaba，2026-06-05 |
未发现官方代码 |
ssrlive |
| 生成、排序与冷启动 |
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation |
Kuaishou Technology，2026-06-02 |
未发现官方代码 |
taiji |
| 训练目标与决策优化 |
Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems |
Meta，2026-05-29 |
未发现官方代码 |
scalr |
| 训练目标与决策优化 |
Rec-Distill: An Industrial Distillation Pipeline for Large-Scale Recommendation Models |
ByteDance / Douyin / TikTok，2026-05-28 |
未发现官方代码 |
rec-distill |
| 训练目标与决策优化 |
Causal Representation Learning for Generalisable Recommendation |
University of Warwick，2026-05-26 |
未发现官方代码 |
causal-representation |
| 大模型能力与推荐融合 |
L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation |
NetEase Cloud Music，2026-05-26 |
未发现官方代码 |
l2rec |
| 大模型能力与推荐融合 |
MuChator: Enabling Active Music Discovery via Conversational Music LLMs in Douyin Music |
ByteDance，2026-05-26 |
未发现官方代码 |
muchator |
| 训练目标与决策优化 |
Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems |
Spotify，2026-05-26 |
未发现官方代码 |
primal-dual-decoding |
| 生成、排序与冷启动 |
DeGRe: Listwise Generative Reranking with Offline Lookahead Distillation |
Alibaba Group / Zhejiang University，2026-05-25 |
未发现官方代码 |
degre |
| 生成、排序与冷启动 |
From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark |
University of Science and Technology of China / Alibaba，2026-05-25 |
未发现官方代码 |
qgs |
| 大模型能力与推荐融合 |
From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs |
Alibaba Group / Peking University，2026-05-22 |
未发现官方代码 |
akt-rec |
| 大模型能力与推荐融合 |
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval |
Microsoft AI / Bing Ads，2026-05-22 |
未发现官方代码 |
harness-lm |
| 生成、排序与冷启动 |
Memento: Personalized RAG-Style Long-Retention Data Scaling for Online Ads Recommendation |
Meta，2026-05-22 |
未发现官方代码 |
memento |
| 大模型能力与推荐融合 |
TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery |
Tubi，2026-05-22 |
未发现官方代码 |
tubifm |
| 大模型能力与推荐融合 |
FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation |
TikTok / ByteDance，2026-05-20 |
未发现官方代码 |
fluid |
| 训练目标与决策优化 |
PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation |
TikTok，2026-05-20 |
未发现官方代码 |
pearl-percentile |
| 训练目标与决策优化 |
Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation |
论文作者团队（原文未标注公司），2026-05-19 |
已开源 |
mdcns |
| 训练目标与决策优化 |
DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems |
Kuaishou Technology，2026-05-18 |
已开源 |
dadf |
| 生成、排序与冷启动 |
Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search |
Alibaba Group / Taobao & Tmall，2026-05-18 |
未发现官方代码 |
growthgr |
| 生成、排序与冷启动 |
Policy-Grounded Dynamic Facet Suggestions for Job Search |
LinkedIn，2026-05-15 |
未发现官方代码 |
policy-facet |
| 生成、排序与冷启动 |
Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL |
Alibaba Taobao & Tmall Group，2026-05-14 |
未发现官方代码 |
cq-sid |
| 多阶段排序与混排 |
A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems |
Pinterest，2026-05-08 |
未发现官方代码 |
prl-puts |
| 训练目标与决策优化 |
Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling |
ByteDance，2026-05-07 |
未发现官方代码 |
pa-bridge |
| 生成、排序与冷启动 |
Effective Knowledge Transfer for Multi-Task Recommendation Models |
Huawei Technologies，2026-05-07 |
未发现官方代码 |
ektm |
| 大模型能力与推荐融合 |
RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation |
Alibaba / Taobao，2026-05-06 |
未发现官方代码 |
recgpt-mobile |
| 生成、排序与冷启动 |
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling |
Google，2026-05-04 |
未发现官方代码 |
semantic-native-longseq |
| 大模型能力与推荐融合 |
A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems |
Meta，2026-05 |
未发现官方代码 |
mm-llm |
| 大模型能力与推荐融合 |
Fine-Tuned LLM as a Complementary Predictor Improving Ads System |
Pinterest，2026-05 |
未发现官方代码 |
pinterest-ads-llm |
| 大模型能力与推荐融合 |
LLM Retrieval for Stable and Predictable Ad Recommendations |
Meta，2026-05 |
未发现官方代码 |
llm-ad-retrieval |
| 大模型能力与推荐融合 |
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation |
Alibaba International / CAS，2026-05 |
未发现官方代码 |
lwgr |
| 大模型能力与推荐融合 |
Unified Value Alignment for Generative Recommendation in Industrial Advertising |
Tencent / WeChat Channels，2026-05 |
未发现官方代码 |
univa |
| 生成、排序与冷启动 |
From Local Indices to Global Identifiers: Generative Reranking via Global Action Space |
City University of Hong Kong / Kuaishou / UC San Diego，2026-04-28 |
未发现官方代码 |
glorank |
| 生成、排序与冷启动 |
Beyond Static Collision Handling: Adaptive Semantic ID Learning for Multimodal Recommendation at Industrial Scale |
University of Electronic Science and Technology of China / Kuaishou，2026-04-26 |
未发现官方代码 |
adasid |
| 训练目标与决策优化 |
AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization |
Google / Discover，2026-04-21 |
未发现官方代码 |
agentic-rec-tune |
| 多阶段排序与混排 |
CS3: Efficient Online Capability Synergy for Two-Tower Recommendation |
Kuaishou Technology，2026-04-21 |
已开源 |
cs3 |
| 大模型能力与推荐融合 |
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations |
Shanghai Jiao Tong University，2026-04-20 |
未发现官方代码 |
marc |
| 生成、排序与冷启动 |
RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems |
Tencent，2026-04-20 |
未发现官方代码 |
rankup |
| 生成、排序与冷启动 |
GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation |
JD.com，2026-04-16 |
未发现官方代码 |
genrec |
| 生成、排序与冷启动 |
Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation |
Meta / Facebook and Instagram Ads，2026-04-14 |
未发现官方代码 |
hill-index |
| 生成、排序与冷启动 |
UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute |
Authors did not disclose affiliation / large-scale e-commerce platform，2026-04-14 |
未发现官方代码 |
unirec-coa |
| 大模型能力与推荐融合 |
SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling |
Meta，2026-04-13 |
未发现官方代码 |
solaris |
| 生成、排序与冷启动 |
SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search |
Kuaishou Technology，2026-04-12 |
未发现官方代码 |
sid-coord |
| 多阶段排序与混排 |
Dual-Rerank: Fusing Sequential Dependencies and Utility for Generative Reranking |
Kuaishou Technology，2026-04-08 |
未发现官方代码 |
dual-rerank |
| 生成、排序与冷启动 |
MBGR: Multi-Business Generative Recommendation |
Meituan，2026-04-03 |
未发现官方代码 |
mbgr |
| 生成、排序与冷启动 |
RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation |
Alibaba International Digital Commerce Group，2026-03-30 |
未发现官方代码 |
rclrec |
| 生成、排序与冷启动 |
UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking |
Taobao & Tmall Group / Alibaba，2026-03-25 |
未发现官方代码 |
uniscale |
| 生成、排序与冷启动 |
GateSID: Adaptive Gating for Semantic-Collaborative Alignment in Cold-Start Recommendation |
Alibaba International Digital Commerce，2026-03-24 |
未发现官方代码 |
gatesid |
| 内容理解、审核与风险控制 |
TagLLM: A Fine-Grained Tag Generation Approach for Note Recommendation |
Tongji University，2026-03-23 |
未发现官方代码 |
tagllm |
| 生成、排序与冷启动 |
AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation |
Taobao & Tmall Group / Alibaba，2026-03-20 |
未发现官方代码 |
aigq |
| 生成、排序与冷启动 |
GenFacet: End-to-End Generative Faceted Search via Multi-Task Preference Alignment in E-Commerce |
JD.com，2026-03-20 |
未发现官方代码 |
genfacet |
| 训练目标与决策优化 |
SaFRO: Satisfaction-Aware Fusion via Dual-Relative Policy Optimization for Short-Video Search |
Kuaishou Technology，2026-03-20 |
未发现官方代码 |
safro |
| 生成、排序与冷启动 |
Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify |
Spotify，2026-03-18 |
未发现官方代码 |
glide |
| 多阶段排序与混排 |
Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds |
Bilibili，2026-03-04 |
未发现官方代码 |
cgr |
| 生成、排序与冷启动 |
Not All Candidates are Created Equal: Heterogeneity-Aware Pre-ranking |
ByteDance / Toutiao，2026-03-04 |
已开源 |
hap |
| 生成、排序与冷启动 |
SORT: A Systematically Optimized Ranking Transformer for Industrial-scale Recommenders |
Alibaba International Digital Commerce，2026-03-04 |
未发现官方代码 |
sort-ranking |
| 生成、排序与冷启动 |
OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation |
Tencent，2026-03-03 |
未发现官方代码 |
oneranker |
| 生成、排序与冷启动 |
PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest |
Pinterest，2026-03-03 |
未发现官方代码 |
pinclip |
| 大模型能力与推荐融合 |
IDProxy: Cold-Start CTR Prediction for Ads and Recommendation at Xiaohongshu with Multimodal LLMs |
Xiaohongshu / Shanghai Jiao Tong University / Fudan University，2026-03-02 |
未发现官方代码 |
idproxy |
| 生成、排序与冷启动 |
Beyond the Flat Sequence: Hierarchical and Preference-Aware Generative Recommendations |
Harbin Institute of Technology，2026-03-01 |
未发现官方代码 |
hpgr |
| 大模型能力与推荐融合 |
Zero-shot Cross-domain Knowledge Distillation: A Case study on YouTube Music |
Google / YouTube，2026-03 |
未发现官方代码 |
cross-domain-kd |
| 生成、排序与冷启动 |
Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale |
University of Electronic Science and Technology of China / Kuaishou，2026-02-28 |
未发现官方代码 |
quasid |
| 生成、排序与冷启动 |
Learning to Reflect and Correct: Towards Better Decoding Trajectories for Large-Scale Generative Recommendation |
Alibaba International / Wuhan University，2026-02-27 |
未发现官方代码 |
grc |
| 大模型能力与推荐融合 |
Generative Pseudo-Labeling for Pre-Ranking with LLMs |
Alibaba Group / Renmin University，2026-02-24 |
未发现官方代码 |
gpl-prerank |
| 生成、排序与冷启动 |
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders |
Alibaba / Taobao，2026-02-24 |
未发现官方代码 |
hisac |
| 训练目标与决策优化 |
A Long-term Value Prediction Framework In Video Ranking |
Alibaba Group / Tsinghua University，2026-02-19 |
未发现官方代码 |
ltv-video-ranking |
| 生成、排序与冷启动 |
Bending the Scaling Law Curve in Large-Scale Recommendation Systems |
Meta，2026-02-19 |
未发现官方代码 |
ultra-hstu |
| 生成、排序与冷启动 |
Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System |
Meta，2026-02-18 |
未发现官方代码 |
mfli |
| 生成、排序与冷启动 |
MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders |
ByteDance / Douyin，2026-02-15 |
未发现官方代码 |
mixformer |
| 生成、排序与冷启动 |
Climber-Pilot: A Non-Myopic Generative Recommendation Model Towards Better Instruction-Following |
NetEase Cloud Music，2026-02-14 |
未发现官方代码 |
climber-pilot |
| 训练目标与决策优化 |
Awakening Dormant Users: Generative Recommendation with Counterfactual Functional Role Reasoning |
Beihang University，2026-02-13 |
未发现官方代码 |
rolegen |
| Serving 与研究基础设施 |
CAPTS: Channel-Aware, Preference-Aligned Trigger Selection for Multi-Channel Item-to-Item Retrieval |
Kuaishou Technology，2026-02-13 |
未发现官方代码 |
capts |
| 训练目标与决策优化 |
Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework |
Kuaishou Technology，2026-02-13 |
未发现官方代码 |
unimvt |
| 大模型能力与推荐融合 |
RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems |
Forth AI / Shopee / Singapore University of Technology and Design，2026-02-13 |
未发现官方代码 |
rgalign-rec |
| 内容理解、审核与风险控制 |
RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction |
Tencent，2026-02-13 |
未发现官方代码 |
rq-gmm |
| 生成、排序与冷启动 |
An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking |
LinkedIn，2026-02-12 |
未发现官方代码 |
linkedin-feed-sr |
| 生成、排序与冷启动 |
Compress, Cross and Scale: Multi-Level Compression Cross Networks for Efficient Scaling in Recommender Systems |
Bilibili，2026-02-12 |
未发现官方代码 |
mlcc |
| Serving 与研究基础设施 |
CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer |
LinkedIn，2026-02-11 |
未发现官方代码 |
cadet |
| 生成、排序与冷启动 |
Compute Only Once: UG-Separation for Efficient Large Recommendation Models |
ByteDance AML，2026-02-11 |
未发现官方代码 |
ug-sep |
| 生成、排序与冷启动 |
DiffuReason: Bridging Latent Reasoning and Generative Refinement for Sequential Recommendation |
Tencent，2026-02-10 |
未发现官方代码 |
diffureason |
| 生成、排序与冷启动 |
Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design |
Meta，2026-02-10 |
未发现官方代码 |
kunlun |
| 内容理解、审核与风险控制 |
SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking |
Institute of Information Engineering, CAS / Kuaishou，2026-02-10 |
未发现官方代码 |
sarm |
| 大模型能力与推荐融合 |
Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents |
Google / YouTube，2026-02-10 |
未发现官方代码 |
self-evolving-rec |
| Serving 与研究基础设施 |
SMES: Towards Scalable Multi-Task Recommendation via Expert Sparsity |
Kuaishou Technology，2026-02-10 |
未发现官方代码 |
smes |
| Serving 与研究基础设施 |
ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest |
Pinterest，2026-02-09 |
未发现官方代码 |
ml-dcn |
| 生成、排序与冷启动 |
PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendation |
Beijing University of Posts and Telecommunications，2026-02-09 |
未发现官方代码 |
pit |
| 生成、排序与冷启动 |
MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization |
ByteDance / Douyin，2026-02-07 |
未发现官方代码 |
mdl |
| 生成、排序与冷启动 |
MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation |
ByteDance / Douyin Search，2026-02-07 |
未发现官方代码 |
msn |
| 生成、排序与冷启动 |
TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders |
ByteDance，2026-02-06 |
未发现官方代码 |
tokenmixer-large |
| 生成、排序与冷启动 |
DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan |
Meituan，2026-02-04 |
未发现官方代码 |
dos |
| 大模型能力与推荐融合 |
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment |
Apple，2026-02-01 |
未发现官方代码 |
rag-qac |
| 生成、排序与冷启动 |
Generative Recommendation for Large-Scale Advertising |
Kuaishou，2026-02 |
未发现官方代码 |
gr4ad |
| 大模型能力与推荐融合 |
S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage |
Tencent / WeChat Channels，2026-02 |
未发现官方代码 |
s-grec |
| 大模型能力与推荐融合 |
SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress |
Alibaba / AliExpress，2026-02 |
未发现官方代码 |
sigma |
| 生成、排序与冷启动 |
OneMall: One Model, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce |
Kuaishou，2026-01-29 |
未发现官方代码 |
onemall |
| 生成、排序与冷启动 |
Zenith: Scaling up Ranking Models for Billion-scale Livestreaming Recommendation |
North Carolina State University，2026-01-29 |
未发现官方代码 |
zenith |
| Serving 与研究基础设施 |
Towards End-to-End Alignment of User Satisfaction via Questionnaire in Video Recommendation |
Kuaishou Technology，2026-01-28 |
未发现官方代码 |
easq |
| 大模型能力与推荐融合 |
LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation |
Meta，2026-01-27 |
未发现官方代码 |
llatte |
| 生成、排序与冷启动 |
S2GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation |
Kuaishou Technology，2026-01-26 |
未发现官方代码 |
s2gr |
| 生成、排序与冷启动 |
Unleashing the Potential of Sparse Attention on Long-term Behaviors for CTR Prediction |
Institute of Software, Chinese Academy of Sciences，2026-01-25 |
未发现官方代码 |
sparsectr |
| 训练目标与决策优化 |
Hierarchical Contextual Uplift Bandits for Catalog Personalization |
Dream11，2026-01-20 |
未发现官方代码 |
hcub |
| 生成、排序与冷启动 |
HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction |
ByteDance / Douyin Search，2026-01-19 |
未发现官方代码 |
hyformer |
| Serving 与研究基础设施 |
Applying Embedding-Based Retrieval to Airbnb Search |
Airbnb，2026-01-11 |
未发现官方代码 |
airbnb-ebr |
| 生成、排序与冷启动 |
PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations |
Kuaishou Technology，2026-01-08 |
未发现官方代码 |
promise |
| 多阶段排序与混排 |
Rethinking Multi-objective Ranking Ensemble in Recommender System: From Score Fusion to Rank Consistency |
Kuaishou Technology，2026-01-06 |
未发现官方代码 |
harmonrank |
| 生成、排序与冷启动 |
Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify |
Spotify，2026-01-05 |
未发现官方代码 |
podcast-mtl |
| 生成、排序与冷启动 |
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent |
Tencent，2025-12-31 |
未发现官方代码 |
higr |
| 大模型能力与推荐融合 |
RecGPT-V2 Technical Report |
Alibaba / Taobao，2025-12-16 |
未发现官方代码 |
recgpt-v2 |
| 生成、排序与冷启动 |
DualGR: Generative Retrieval with Long and Short-Term Interests Modeling |
USTC / Kuaishou Technology，2025-11-16 |
未发现官方代码 |
dualgr |
| 生成、排序与冷启动 |
OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender |
ByteDance，2025-10-30 |
未发现官方代码 |
onetrans |
| 大模型能力与推荐融合 |
From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance |
Meituan，2025-10-13 |
未发现官方代码 |
crsd |
| 大模型能力与推荐融合 |
PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations |
Google DeepMind / YouTube，2025-10-09 |
未发现官方代码 |
plum |
| 生成、排序与冷启动 |
IntSR: An Integrated Generative Framework for Search and Recommendation |
Alibaba / Amap，2025-09-25 |
未发现官方代码 |
intsr |
| 生成、排序与冷启动 |
OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking |
Shopee，2025-09-22 |
未发现官方代码 |
onepiece |
| 训练目标与决策优化 |
Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest |
Pinterest，2025-09-05 |
未发现官方代码 |
drl-put |
| 训练目标与决策优化 |
MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever |
Kuaishou Technology，2025-08-28 |
未发现官方代码 |
mpformer |
| 生成、排序与冷启动 |
OneRec-V2 Technical Report |
Kuaishou，2025-08 |
未发现官方代码 |
onerec-v2 |
| 生成、排序与冷启动 |
SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation |
Alibaba，2025-08 |
未发现官方代码 |
saviorrec |
| 生成、排序与冷启动 |
RankMixer: Scaling Up Ranking Models in Industrial Recommenders |
ByteDance / Douyin，2025-07-21 |
未发现官方代码 |
rankmixer |
| 生成、排序与冷启动 |
Click A, Buy B: Rethinking Conversion Attribution in E-Commerce Recommendations |
Pinterest，2025-07-20 |
未发现官方代码 |
click-a-buy-b |
| 大模型能力与推荐融合 |
PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform |
Pinterest，2025-07-17 |
未发现官方代码 |
pinfm |
| 生成、排序与冷启动 |
Scaling Recommender Transformers to One Billion Parameters |
Yandex，2025-07 |
未发现官方代码 |
argus |
| 生成、排序与冷启动 |
Macro Graph of Experts for Billion-Scale Multi-Task Recommendation |
Alibaba，2025-06-12 |
已开源 |
mgoe |
| Serving 与研究基础设施 |
RADAR: Recall Augmentation through Deferred Asynchronous Retrieval |
Meta，2025-06-08 |
未发现官方代码 |
radar |
| 生成、排序与冷启动 |
TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation |
Pinterest，2025-06-02 |
未发现官方代码 |
transact-v2 |
| 生成、排序与冷启动 |
A Generative Re-ranking Model for List-level Multi-objective Optimization at Taobao |
Alibaba / Taobao & Tmall，2025-05-12 |
未发现官方代码 |
sort-gen |
| 生成、排序与冷启动 |
LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders |
ByteDance / Douyin，2025-05-07 |
未发现官方代码 |
longer |
| 生成、排序与冷启动 |
Towards Large-scale Generative Ranking |
Xiaohongshu，2025-05 |
未发现官方代码 |
genrank |
| 生成、排序与冷启动 |
PinRec: Outcome-Conditioned, Multi-Token Generative Retrieval for Industry-Scale Recommendation Systems |
Pinterest，2025-04 |
未发现官方代码 |
pinrec |
| 生成、排序与冷启动 |
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations |
Baidu，2025-03 |
未发现官方代码 |
cobra |
| 生成、排序与冷启动 |
OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment |
Kuaishou，2025-02-26 |
未发现官方代码 |
onerec |
| 大模型能力与推荐融合 |
FilterLLM: Text-To-Distribution LLM for Billion-Scale Cold-Start Recommendation |
Alibaba，2025-02-24 |
未发现官方代码 |
filterllm |
| 生成、排序与冷启动 |
FuXi-α: Scaling Recommendation Model with Feature Interaction Enhanced Transformer |
Huawei / USTC，2025-02-05 |
已开源 |
fuxi-alpha |
| 大模型能力与推荐融合 |
MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling |
Alibaba / Taobao，2025-02-01 |
已开源 |
mim |
| 大模型能力与推荐融合 |
Bursting Filter Bubble: Enhancing Serendipity Recommendations with Aligned Large Language Models |
Alibaba / Taobao，2025-02 |
未发现官方代码 |
seral |
| 生成、排序与冷启动 |
SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendation |
Meituan，2025-02 |
未发现官方代码 |
sessionrec |
| 大模型能力与推荐融合 |
Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model |
Alibaba，2025-02 |
未发现官方代码 |
lum |
| 生成、排序与冷启动 |
AdaF²M²: Comprehensive Learning and Responsive Leveraging Features in Recommendation System |
ByteDance / Douyin，2025-01-27 |
未发现官方代码 |
adaf2m2 |
| 大模型能力与推荐融合 |
Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction |
Meituan，2024-12 |
未发现官方代码 |
msd |
| 大模型能力与推荐融合 |
PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information |
Tencent / WeChat，2024-12 |
未发现官方代码 |
precise |
| 大模型能力与推荐融合 |
LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System |
Tencent / WeChat，2024-11 |
未发现官方代码 |
leadre |
| 生成、排序与冷启动 |
TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou |
Kuaishou，2024-07-23 |
未发现官方代码 |
twin-v2 |
| 多阶段排序与混排 |
Contextual Distillation Model for Diversified Recommendation |
Kuaishou Technology，2024-06-13 |
未发现官方代码 |
cdm |
| 生成、排序与冷启动 |
Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time |
Kuaishou Technology / Renmin University of China，2024-06-12 |
已开源 |
cwm |
| 大模型能力与推荐融合 |
Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application |
Kuaishou，2024-05 |
未发现官方代码 |
learn |
| 大模型能力与推荐融合 |
A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation |
Kuaishou，2024-03 |
已开源 |
lsvcr |
| 大模型能力与推荐融合 |
Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors |
Ant Group，2024-03 |
未发现官方代码 |
bahe |
| 大模型能力与推荐融合 |
NoteLLM: A Retrievable Large Language Model for Note Recommendation |
Xiaohongshu，2024-03 |
未发现官方代码 |
notellm |
| 生成、排序与冷启动 |
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations |
Meta，2024-02-27 |
已开源 |
hstu |
| 大模型能力与推荐融合 |
Large Language Model based Long-tail Query Rewriting in Taobao Search |
Alibaba，2023-11 |
未发现官方代码 |
beque |
| 大模型能力与推荐融合 |
Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models |
Huawei，2023-06 |
未发现官方代码 |
kar |
| 生成、排序与冷启动 |
Recommender Systems with Generative Retrieval |
Google / Google DeepMind，2023-05-08 |
未发现官方代码 |
tiger |
| 大模型能力与推荐融合 |
M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems |
Alibaba，2022-05 |
未发现官方代码 |
m6rec |
| 生成、排序与冷启动 |
Progressive Layered Extraction (PLE): A Novel Multi-Task Learning Model for Personalized Recommendations |
Tencent，2020-09-22 |
未发现官方代码 |
ple |
| 生成、排序与冷启动 |
DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems |
Google，2020-08-19 |
未发现官方代码 |
dcn-v2 |
| 生成、排序与冷启动 |
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for CTR Prediction |
Alibaba，2020-06-10 |
未发现官方代码 |
sim |
| 生成、排序与冷启动 |
Behavior Sequence Transformer for E-commerce Recommendation in Alibaba |
Alibaba，2019-05-15 |
未发现官方代码 |
bst |
| 生成、排序与冷启动 |
Deep Interest Evolution Network for Click-Through Rate Prediction |
Alibaba，2018-09-11 |
已开源 |
dien |
| 生成、排序与冷启动 |
Self-Attentive Sequential Recommendation |
UC San Diego，2018-08-20 |
已开源 |
sasrec |
| 生成、排序与冷启动 |
Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts |
Google，2018-08-19 |
未发现官方代码 |
mmoe |
| 生成、排序与冷启动 |
Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate |
Alibaba，2018-04-21 |
未发现官方代码 |
esmm |
| 生成、排序与冷启动 |
Deep Interest Network for Click-Through Rate Prediction |
Alibaba，2017-06-21 |
已开源 |
din |
| 生成、排序与冷启动 |
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction |
Huawei Noah's Ark Lab，2017-03-13 |
未发现官方代码 |
deepfm |
| 生成、排序与冷启动 |
Deep Neural Networks for YouTube Recommendations |
Google / YouTube，2016-09-15 |
未发现官方代码 |
youtube-dnn |
| 生成、排序与冷启动 |
Wide & Deep Learning for Recommender Systems |
Google，2016-06-24 |
已开源 |
wide-deep |