UTTSI selectively scales test-time compute for CTR prediction by triggering stochastic feature-path exploration only on high-uncertainty instances, yielding gains on four datasets and a 5.3% online CTR lift.
Title resolution pending
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
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.
SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.
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.
ComeIR introduces dual-level Engram memory and memory-restoring prediction to reconstruct SID-token embeddings and restore token granularity in generative recommendation.
Pro-GEO introduces a geo-centroid coordinate system and geo-rotary position encoding to model geographic proximity as rotational transformations, enabling balanced semantic-spatial modeling in local service recommendations.
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
MBGR is a new generative recommendation framework using business-aware semantic IDs, multi-business prediction, and label dynamic routing to handle multiple businesses without seesaw effects or representation confusion, validated by experiments and deployed at Meituan.
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.
SpecTran applies a spectral-aware transformer adapter with learnable position encoding to aggregate informative components across the full spectrum of LLM embeddings, yielding 9.17% average gains on sequential recommendation tasks.
BLOGER is a bi-level optimization framework that jointly optimizes the tokenizer and recommender for generative recommendation, outperforming prior methods on real-world datasets.
A2Gen treats timed user actions on short videos as generative sequences and reports large-scale online gains in watch time, interactions, and retention.
RecoChain unifies generative candidate generation via hierarchical semantic IDs and SIM-based ranking in a single Transformer to improve top-K recommendation performance.
A tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
TASTE dataset and MuQ-token aggregation enable effective use of audio features from large music models to improve content-based music recommendations over collaborative filtering alone.
citing papers explorer
-
Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration
UTTSI selectively scales test-time compute for CTR prediction by triggering stochastic feature-path exploration only on high-uncertainty instances, yielding gains on four datasets and a 5.3% online CTR lift.
-
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.
-
User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation
SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.
-
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.
-
Conditional Memory Enhanced Item Representation for Generative Recommendation
ComeIR introduces dual-level Engram memory and memory-restoring prediction to reconstruct SID-token embeddings and restore token granularity in generative recommendation.
-
Birds of a Feather Cluster Nearby: a Proximity-Aware Geo-Codebook for Local Service Recommendation
Pro-GEO introduces a geo-centroid coordinate system and geo-rotary position encoding to model geographic proximity as rotational transformations, enabling balanced semantic-spatial modeling in local service recommendations.
-
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
-
MBGR: Multi-Business Prediction for Generative Recommendation at Meituan
MBGR is a new generative recommendation framework using business-aware semantic IDs, multi-business prediction, and label dynamic routing to handle multiple businesses without seesaw effects or representation confusion, validated by experiments and deployed at Meituan.
-
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.
-
SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation
SpecTran applies a spectral-aware transformer adapter with learnable position encoding to aggregate informative components across the full spectrum of LLM embeddings, yielding 9.17% average gains on sequential recommendation tasks.
-
Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
BLOGER is a bi-level optimization framework that jointly optimizes the tokenizer and recommender for generative recommendation, outperforming prior methods on real-world datasets.
-
Action-Aware Generative Sequence Modeling for Short Video Recommendation
A2Gen treats timed user actions on short videos as generative sequences and reports large-scale online gains in watch time, interactions, and retention.
-
Harmonizing Generative Retrieval and Ranking in Chain-of-Recommendation
RecoChain unifies generative candidate generation via hierarchical semantic IDs and SIM-based ranking in a single Transformer to improve top-K recommendation performance.
-
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
A tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
-
Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models
TASTE dataset and MuQ-token aggregation enable effective use of audio features from large music models to improve content-based music recommendations over collaborative filtering alone.