AsymRec decouples input and output representations in generative recommendation via multi-expert semantic projection and multi-faceted hierarchical quantization, outperforming prior models by 15.8% on average.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (60%).
33
Pith papers citing it
Background
60% of classified citations
citation-role summary
background 3
baseline 1
method 1
citation-polarity summary
representative citing papers
RecRM-Bench is a new large-scale benchmark dataset and framework for multi-dimensional reward modeling in agentic recommender systems, spanning instruction following, factual consistency, query-item relevance, and user behavior prediction.
QCMP-CL introduces learnable collaborative sequence augmentation from same-target and similar sequences plus a quality-aware weighting mechanism based on augmentation confidence, outperforming prior CL-based sequential recommendation methods on three real-world datasets.
BLADE uses Bayesian list-wise alignment with dynamic estimation to create a self-evolving target that overcomes limitations of static references in LLM-based recommendation, yielding sustained gains in ranking and complex metrics.
ProMax uses dense retrieval and dual distribution reshaping on LLM-derived profiles to guide recommender models toward preferences for unseen items, substantially boosting base model performance on public datasets.
SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
AdaTTA is an actor-critic RL framework that selects sequence-specific test-time augmentations and improves recommendation metrics by up to 26% over fixed augmentation strategies 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.
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.
SemaCDR builds a unified semantic space with LLM-generated domain-agnostic features and adaptive fusion to improve cross-domain sequential recommendations over baselines.
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.
MDCNS is a multi-source negative sampling framework for sequential recommendation that uses peer and teacher models plus divergence and consensus mechanisms to improve diversity and avoid local optima.
DC4SR improves sequential recommendation denoising by iteratively calibrating LLM semantic priors and model learning posteriors using their disagreement as a signal for better alignment with true user interests.
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.
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
FLAME condenses ensemble diversity into a single network via modular ensemble simulation and guided mutual learning during training, delivering ensemble-level performance with single-network inference speed on sequential recommendation tasks.
MoS applies theme-aware routing to extract multi-scale theme-specific subsequences from noisy long user sequences, achieving state-of-the-art recommendation performance with fewer FLOPs than comparable MoE models.
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.
citing papers explorer
-
Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization
AsymRec decouples input and output representations in generative recommendation via multi-expert semantic projection and multi-faceted hierarchical quantization, outperforming prior models by 15.8% on average.
-
RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
RecRM-Bench is a new large-scale benchmark dataset and framework for multi-dimensional reward modeling in agentic recommender systems, spanning instruction following, factual consistency, query-item relevance, and user behavior prediction.
-
Quality-Aware Collaborative Multi-Positive Contrastive Learning for Sequential Recommendation
QCMP-CL introduces learnable collaborative sequence augmentation from same-target and similar sequences plus a quality-aware weighting mechanism based on augmentation confidence, outperforming prior CL-based sequential recommendation methods on three real-world datasets.
-
Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation
BLADE uses Bayesian list-wise alignment with dynamic estimation to create a self-evolving target that overcomes limitations of static references in LLM-based recommendation, yielding sustained gains in ranking and complex metrics.
-
ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems
ProMax uses dense retrieval and dual distribution reshaping on LLM-derived profiles to guide recommender models toward preferences for unseen items, substantially boosting base model performance on public datasets.
-
Similar Users-Augmented Interest Network
SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
-
Beyond One-Size-Fits-All: Adaptive Test-Time Augmentation for Sequential Recommendation
AdaTTA is an actor-critic RL framework that selects sequence-specific test-time augmentations and improves recommendation metrics by up to 26% over fixed augmentation strategies 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.
-
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.
-
SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
SemaCDR builds a unified semantic space with LLM-generated domain-agnostic features and adaptive fusion to improve cross-domain sequential recommendations over baselines.
-
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.
-
Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
MDCNS is a multi-source negative sampling framework for sequential recommendation that uses peer and teacher models plus divergence and consensus mechanisms to improve diversity and avoid local optima.
-
Disagreement as Signals: Dual-view Calibration for Sequential Recommendation Denoising
DC4SR improves sequential recommendation denoising by iteratively calibrating LLM semantic priors and model learning posteriors using their disagreement as a signal for better alignment with true user interests.
-
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.
-
Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
-
From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
-
FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation
FLAME condenses ensemble diversity into a single network via modular ensemble simulation and guided mutual learning during training, delivering ensemble-level performance with single-network inference speed on sequential recommendation tasks.
-
Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
MoS applies theme-aware routing to extract multi-scale theme-specific subsequences from noisy long user sequences, achieving state-of-the-art recommendation performance with fewer FLOPs than comparable MoE models.
-
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.
-
ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
ADS-POI decomposes user mobility sequences into multiple parallel evolving latent sub-states with context-conditioned aggregation to improve next POI recommendation accuracy.
-
CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
CaST-POI improves next POI recommendation by conditioning user history attention on each candidate and adding candidate-relative temporal and spatial biases.
-
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.
-
BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
BlossomRec is a sparse attention mechanism that uses two distinct block-level patterns for long-term and short-term interests, fused by a gated output, to reduce computation in sequential recommendation Transformers.
-
Relative Contrastive Learning for Sequential Recommendation with Similarity-based Positive Pair Selection
RCL adds similarity-based weak positive samples to supervised contrastive learning in sequential recommendation and reports an average 4.88% improvement over state-of-the-art methods across six datasets.
-
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.
-
Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation
SDA uses structural alignment as a soft teacher and gated low-rank expert paths to adapt LVLMs for multimodal recommendation, reporting 6.15% Hit@10 and 8.64% NDCG@10 average gains plus larger long-tail improvements on Amazon datasets.
-
LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
LLM-EDT improves cross-domain sequential recommendation by using LLMs for transferable item augmentation, dual-phase training to handle domain transitions, and domain-aware profiling to build user profiles.
- BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models