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.
Canonical reference
Title resolution pending
Canonical reference. 83% of citing Pith papers cite this work as background.
41
Pith papers citing it
Background
83% of classified citations
citation-role summary
background 5
method 1
citation-polarity summary
representative citing papers
AdaSID adaptively regulates semantic ID overlaps in multimodal recommendations to improve retrieval performance, codebook utilization, and downstream metrics like GMV.
Auto-regressive next-token prediction is strictly equivalent to full-vocabulary maximum likelihood estimation in generative recommendation under bijective item-to-token-sequence mapping.
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.
IAT compresses each historical interaction instance into a unified embedding token via temporal-order or user-order schemes, allowing standard sequence models to learn long-range preferences with better performance and transferability.
NSGR is a tree-structured generative reranker that progressively generates optimal lists via next-scale expansion and multi-scale neighbor loss to balance perspectives and align training signals.
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.
DIGER makes semantic IDs in generative recommendation differentiable via Gumbel noise and decay schedules, yielding consistent gains on public datasets by aligning indexing and recommendation losses.
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
GenPage is a transformer that autoregressively generates entire structured Netflix homepages from user prompts, delivering +0.24% engagement lift and 20% latency reduction versus production baseline in online tests.
A generative recommender that feeds continuous item embeddings into the Transformer and uses multi-faceted hierarchical quantized codes only as prediction targets outperforms prior semantic-ID recommenders by 15.8% NDCG@10 on average.
ComeIR introduces dual-level Engram memory and memory-restoring prediction to reconstruct SID-token embeddings and restore token granularity in generative recommendation.
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%.
The framework replaces Video IDs with depth-truncated Semantic IDs and introduces a Global-Aware Compression Transformer to model ultra-long user sequences at billion-user scale with reduced memory and compute.
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.
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
MLTFR combines user-guided token filtering with a multi-LLM mixture-of-experts and Fisher-weighted consensus expert to deliver stable gains in corpus-free sequential 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.
RoTE is a multi-level rotary time embedding module that explicitly models time spans in sequential recommendation and improves NDCG@5 by up to 20.11% when added to standard backbones on public benchmarks.
UniRec bridges the expressive gap in generative recommendation by prefixing semantic ID sequences with structured attribute tokens, recovering explicit feature crossing and yielding +22.6% HR@50 gains plus online lifts in PVCTR, orders, and GMV.
ACARec attends over artist catalogs to generate CF embeddings for new tracks, more than doubling recall and NDCG versus content-only baselines in music recommendation.
CRAB mitigates popularity bias in generative recommenders by rebalancing the semantic token codebook through splitting popular tokens and applying a tree-structured regularizer to boost representations for unpopular items.
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.
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.
-
Beyond Static Collision Handling: Adaptive Semantic ID Learning for Multimodal Recommendation at Industrial Scale
AdaSID adaptively regulates semantic ID overlaps in multimodal recommendations to improve retrieval performance, codebook utilization, and downstream metrics like GMV.
-
On the Equivalence Between Auto-Regressive Next Token Prediction and Full-Item-Vocabulary Maximum Likelihood Estimation in Generative Recommendation--A Short Note
Auto-regressive next-token prediction is strictly equivalent to full-vocabulary maximum likelihood estimation in generative recommendation under bijective item-to-token-sequence mapping.
-
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.
-
IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems
IAT compresses each historical interaction instance into a unified embedding token via temporal-order or user-order schemes, allowing standard sequence models to learn long-range preferences with better performance and transferability.
-
Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan
NSGR is a tree-structured generative reranker that progressively generates optimal lists via next-scale expansion and multi-scale neighbor loss to balance perspectives and align training signals.
-
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.
-
Differentiable Semantic ID for Generative Recommendation
DIGER makes semantic IDs in generative recommendation differentiable via Gumbel noise and decay schedules, yielding consistent gains on public datasets by aligning indexing and recommendation losses.
-
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.
-
GenPage: Towards End-to-End Generative Homepage Construction at Netflix
GenPage is a transformer that autoregressively generates entire structured Netflix homepages from user prompts, delivering +0.24% engagement lift and 20% latency reduction versus production baseline in online tests.
-
Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization
A generative recommender that feeds continuous item embeddings into the Transformer and uses multi-faceted hierarchical quantized codes only as prediction targets outperforms prior semantic-ID recommenders by 15.8% NDCG@10 on average.
-
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.
-
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%.
-
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
The framework replaces Video IDs with depth-truncated Semantic IDs and introduces a Global-Aware Compression Transformer to model ultra-long user sequences at billion-user scale with reduced memory and compute.
-
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.
-
MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
-
Multi-LLM Token Filtering and Routing for Sequential Recommendation
MLTFR combines user-guided token filtering with a multi-LLM mixture-of-experts and Fisher-weighted consensus expert to deliver stable gains in corpus-free sequential recommendation.
-
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.
-
RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation
RoTE is a multi-level rotary time embedding module that explicitly models time spans in sequential recommendation and improves NDCG@5 by up to 20.11% when added to standard backbones on public benchmarks.
-
UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute
UniRec bridges the expressive gap in generative recommendation by prefixing semantic ID sequences with structured attribute tokens, recovering explicit feature crossing and yielding +22.6% HR@50 gains plus online lifts in PVCTR, orders, and GMV.
-
Leveraging Artist Catalogs for Cold-Start Music Recommendation
ACARec attends over artist catalogs to generate CF embeddings for new tracks, more than doubling recall and NDCG versus content-only baselines in music recommendation.
-
CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation
CRAB mitigates popularity bias in generative recommenders by rebalancing the semantic token codebook through splitting popular tokens and applying a tree-structured regularizer to boost representations for unpopular items.
-
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.
-
Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation
Adding visual evidence and LLM-mined item-side intent descriptors before semantic-ID quantization, plus a relevance-gated quality reward, improves SID-based generative recommendation on three Amazon categories.
-
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.
-
SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation
SCASRec unifies ranking and redundancy elimination for route lists via stepwise corrective rewards and an adaptive end-of-recommendation token, claiming SOTA results on two datasets and real deployment.
-
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.
-
Sequential Data Augmentation for Generative Recommendation
GenPAS unifies common data augmentation strategies for generative recommendation as special cases of a bias-controlled stochastic sampling process and demonstrates gains in accuracy, data efficiency, and parameter efficiency on benchmarks and industrial data.
-
Generative Bid Shading in Real-Time Bidding Advertising
GBS replaces two-stage bid landscape modeling with an autoregressive generative model plus reward-aligned policy optimization to improve short- and long-term advertiser surplus in real-time bidding.
-
Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation
Statement-level ranking with an LLM-extracted, paraphrase-clustered Amazon benchmark shows popularity baselines often beat SOTA models in item-level personalized explanation ranking.
-
EvoRec: Self Evolving Agentic Recommender Systems
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
-
Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search
GrowthGR combines ItemLTV counterfactual prediction with MultiGR generative retrieval and MoPO optimization to deliver 5.3% new item GMV lift and 0.3% overall GMV gain on Taobao production.
-
Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
CQ-SID semantic IDs and EG-GRPO RL improve generative retrieval hit rates up to 26.76% over RQ-VAE baselines and deliver +1.15% GMV in live e-commerce A/B tests.
-
FedMM: Federated Collaborative Signal Quantization for Multi-Market CTR Prediction
FedMM applies a residual quantized VAE with a global federated codebook and local market-specific codebooks to transmit discrete codes that capture shared and specific collaborative patterns for improved CTR prediction across markets.
-
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.
-
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: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
OneRec unifies retrieval and ranking in a generative recommender using session-wise decoding and iterative DPO-based preference alignment, achieving real-world gains on Kuaishou.
-
Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models
SIF replaces item-ID history tokens with lossily compressed full-sample tokens and reports consistent CTR/CVR gains in offline and live recommender tests.
- Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation