KuaiLive is the first publicly released real-time interactive dataset for live streaming recommendation, with logs from 23,772 users and 452,621 streamers over 21 days plus timestamps, multi-type interactions, and side features.
hub
Onerec technical report
32 Pith papers cite this work. Polarity classification is still indexing.
32
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
TokenMinds extends Semantic ID tokenization from items to users, producing paired discrete tokens and dense embeddings via an LLM-adapted encoder-decoder for industrial recommendation.
TRACER uses token reassignment for concept-related items plus a coherence regularizer to unlearn specific concepts in generative recommendation while preserving utility better than baselines.
PrefixMem encoder for Semantic IDs improves deepest-level accuracy by up to 46% relative and full-SID retrieval recall by up to 22% relative on Pinterest data across LLM families.
Exact LTI Koopman models for nonlinear control systems require affine linear dynamics under controllability and coordinate inclusion assumptions.
Beam-search negatives induce partial AUC optimization in GRPO for LLM recommenders; Windowed Partial AUC and TAWin improve Top-K alignment on four datasets.
GenRec combines page-wise NTP, token compression, and GRPO-SR reinforcement learning to scale generative retrieval, delivering 9.5% click and 8.7% transaction gains in production A/B tests on the JD App.
Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
GenRecEdit injects cold-start items into generative recommendation models via context-aware token editing and interference-reducing triggers, boosting cold-start accuracy while using only 9.5% of retraining time.
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
A single LLM trained to emit semantic item codes can fulfill complex shopping intents with fewer tool hand-offs, improving multi-turn follow-up on Taobao-derived tasks.
IntuRec anchors LLM latent reasoning for recommendation by deriving an intuition embedding from top-K candidates via self- and cross-attention to initialize more accurate trajectories.
Closed-loop LLM simulations find generative recommenders form fewer exposure-level information cocoons than traditional sequential baselines on Amazon data, though tokenization strategy and model scale affect concentration in generated SID space.
GBLA extends kernelized linear attention with local causal mixing, key gating, and gated RMSNorm; a 1:2 hybrid with self-attention matches full bidirectional self-attention quality on Yandex Music data while delivering up to 8.2x speedup at length 32768.
A 7B model using intent-driven Semantic ID generation and profile-aware reasoning matches GPT-4 RAG on coarse accuracy while beating it on finer metrics at 100x lower cost and works for cold-start users where baselines fail.
Injecting commercial value into Semantic ID construction, autoregressive decoding, and online beam search improves generative advertising recommendation, with reported offline HR@100 +37.04% and online GMV +1.5%.
GloRank reformulates list-wise reranking as token generation over a global item identifier space, using supervised pre-training followed by reinforcement learning to maximize list-wise utility and outperforming baselines on benchmarks and industrial data.
LWGR applies personalized soft instructions for LLM knowledge extraction and Lagrangian primal-dual optimization to selectively fuse beneficial world knowledge into generative recommendation while bounding degradation.
ReAd retrieves collaboratively similar items, builds an augmentation embedding via a lightweight module, and fuses it to refine sequential recommendation predictions, outperforming baselines on five datasets.
STAMP mitigates semantic dilution in SID-based generative recommendation via adaptive input pruning and densified output supervision, delivering 1.23-1.38x speedup and 17-55% VRAM savings with maintained or improved accuracy.
Agentic Recommender Systems turn static recommendation pipelines into self-evolving collections of agents using reinforcement learning and LLM-driven architecture generation.
AutoModel uses three core agents (AutoTrain, AutoFeature, AutoPerf) connected by a shared coordination layer to automate model design, feature evolution, performance management, and paper-driven reproduction in large-scale recommender systems.
UniSID jointly optimizes embeddings and Semantic IDs end-to-end with multi-granularity contrastive learning and summary-based reconstruction, outperforming RQ-based methods by up to 4.62% in Hit Rate for ad recommendation.
Next Interest Flow models user intent as continuous evolutionary trajectories on a high-dimensional latent interest manifold with kinematic constraints, bidirectional alignment, and temporal causality mechanisms, yielding reported gains on industrial CTR data.
citing papers explorer
-
KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
KuaiLive is the first publicly released real-time interactive dataset for live streaming recommendation, with logs from 23,772 users and 452,621 streamers over 21 days plus timestamps, multi-type interactions, and side features.
-
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
TokenMinds extends Semantic ID tokenization from items to users, producing paired discrete tokens and dense embeddings via an LLM-adapted encoder-decoder for industrial recommendation.
-
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
TRACER uses token reassignment for concept-related items plus a coherence regularizer to unlearn specific concepts in generative recommendation while preserving utility better than baselines.
-
LLMs Need Encoders for Semantic IDs Too
PrefixMem encoder for Semantic IDs improves deepest-level accuracy by up to 46% relative and full-SID retrieval recall by up to 22% relative on Pinterest data across LLM families.
-
Limitations of LTI Koopman Modeling for Nonlinear Control Systems
Exact LTI Koopman models for nonlinear control systems require affine linear dynamics under controllability and coordinate inclusion assumptions.
-
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
Beam-search negatives induce partial AUC optimization in GRPO for LLM recommenders; Windowed Partial AUC and TAWin improve Top-K alignment on four datasets.
-
GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation
GenRec combines page-wise NTP, token compression, and GRPO-SR reinforcement learning to scale generative retrieval, delivering 9.5% click and 8.7% transaction gains in production A/B tests on the JD App.
-
Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation
Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
-
GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items
GenRecEdit injects cold-start items into generative recommendation models via context-aware token editing and interference-reducing triggers, boosting cold-start accuracy while using only 9.5% of retraining time.
-
S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
-
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
A single LLM trained to emit semantic item codes can fulfill complex shopping intents with fewer tool hand-offs, improving multi-turn follow-up on Taobao-derived tasks.
-
Intuition-Guided Latent Reasoning for LLM-Based Recommendation
IntuRec anchors LLM latent reasoning for recommendation by deriving an intuition embedding from top-K candidates via self- and cross-attention to initialize more accurate trajectories.
-
Do Generative Recommenders Deepen the Information Cocoon? A Closed-Loop Simulation with LLM-powered User Simulators
Closed-loop LLM simulations find generative recommenders form fewer exposure-level information cocoons than traditional sequential baselines on Amazon data, though tokenization strategy and model scale affect concentration in generated SID space.
-
Gated Bidirectional Linear Attention for Generative Retrieval
GBLA extends kernelized linear attention with local causal mixing, key gating, and gated RMSNorm; a 1:2 hybrid with self-attention matches full bidirectional self-attention quality on Yandex Music data while delivering up to 8.2x speedup at length 32768.
-
Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation
A 7B model using intent-driven Semantic ID generation and profile-aware reasoning matches GPT-4 RAG on coarse accuracy while beating it on finer metrics at 100x lower cost and works for cold-start users where baselines fail.
-
UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent
Injecting commercial value into Semantic ID construction, autoregressive decoding, and online beam search improves generative advertising recommendation, with reported offline HR@100 +37.04% and online GMV +1.5%.
-
From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
GloRank reformulates list-wise reranking as token generation over a global item identifier space, using supervised pre-training followed by reinforcement learning to maximize list-wise utility and outperforming baselines on benchmarks and industrial data.
-
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
LWGR applies personalized soft instructions for LLM knowledge extraction and Lagrangian primal-dual optimization to selectively fuse beneficial world knowledge into generative recommendation while bounding degradation.
-
Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation
ReAd retrieves collaboratively similar items, builds an augmentation embedding via a lightweight module, and fuses it to refine sequential recommendation predictions, outperforming baselines on five datasets.
-
Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation
STAMP mitigates semantic dilution in SID-based generative recommendation via adaptive input pruning and densified output supervision, delivering 1.23-1.38x speedup and 17-55% VRAM savings with maintained or improved accuracy.
-
Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
Agentic Recommender Systems turn static recommendation pipelines into self-evolving collections of agents using reinforcement learning and LLM-driven architecture generation.
-
AgenticRS-Architecture: System Design for Agentic Recommender Systems
AutoModel uses three core agents (AutoTrain, AutoFeature, AutoPerf) connected by a shared coordination layer to automate model design, feature evolution, performance management, and paper-driven reproduction in large-scale recommender systems.
-
End-to-End Semantic ID Generation for Generative Advertisement Recommendation
UniSID jointly optimizes embeddings and Semantic IDs end-to-end with multi-granularity contrastive learning and summary-based reconstruction, outperforming RQ-based methods by up to 4.62% in Hit Rate for ad recommendation.
-
Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Next Interest Flow models user intent as continuous evolutionary trajectories on a high-dimensional latent interest manifold with kinematic constraints, bidirectional alignment, and temporal causality mechanisms, yielding reported gains on industrial CTR data.
-
SSRLive: Live Streaming Recommendation with Dynamic Semantic ID
SSRLive combines generative and discriminative modules with dynamic semantic IDs to improve live streaming recommendations, reporting gains of +3.38% watch time, +0.72% GMV, +3.12% follower growth, and +2.92% interaction volume in online A/B tests.
-
RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching
RcLLM accelerates generative recommendation inference by 1.31x-9.51x in TTFT through beyond-prefix KV caching, replicated user caches, sharded item caches, affinity scheduling, and selective attention with negligible accuracy loss.
-
Mitigating Collaborative Semantic ID Staleness in Generative Retrieval
A model-agnostic SID alignment update mitigates staleness from temporal drift in user-item interactions for generative retrievers, improving Recall@K and nDCG@K while reducing compute by 8-9x versus full retraining.
-
SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress
SIGMA deploys a semantic-grounded, instruction-driven generative model with hybrid tokenization and adaptive fusion for multi-task recommendation at AliExpress.
-
OneRec-V2 Technical Report
OneRec-V2 scales generative recommendation to 8B parameters via decoder-only design and real-world preference alignment, improving user engagement metrics in production A/B tests.
-
Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
Token Factory maps dense, sparse, and sequence features into learned soft tokens, cutting LRM prompt length by ~70% while keeping ranking quality on par and improving retrieval of fresh videos.
-
Kwai Keye-VL-2.0 Technical Report
Kwai Keye-VL-2.0-30B-A3B is a 30B MoE model with 3B active parameters using DSA adaptation and MOPD distillation that reports SOTA results on video understanding and agent benchmarks.
-
Fine-Tuned LLM as a Complementary Predictor Improving Ads System
Fine-tuned LLM acts as ancillary advertiser predictor in production ads RecSys, augmenting retrieval and ranking with measurable offline and online gains.