TurboGR trains up to 0.2B-parameter generative recommendation models on Ascend NPUs at 54.71% MFU with 0.97 near-linear scalability via jagged acceleration, hierarchical parallelism, and negative sampling optimizations.
hub
Generative recommen- dation: Towards next-generation recommender paradigm
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
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.
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.
BLOGER is a bi-level optimization framework that jointly optimizes the tokenizer and recommender for generative recommendation, outperforming prior methods on real-world datasets.
BBDRec applies Brownian bridge diffusion to enable direct item-to-history transitions in sequential recommendation, outperforming prior diffusion and sequential baselines on public datasets.
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
A2Gen models temporal user action sequences with context-aware attention and autoregressive generation to improve short video recommendation accuracy, showing gains in watch time and retention on large-scale tests.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
-
TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation
TurboGR trains up to 0.2B-parameter generative recommendation models on Ascend NPUs at 54.71% MFU with 0.97 near-linear scalability via jagged acceleration, hierarchical parallelism, and negative sampling optimizations.
-
Factorized Latent Reasoning for LLM-based Recommendation
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
-
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.
-
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.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
Action-Aware Generative Sequence Modeling for Short Video Recommendation
A2Gen models temporal user action sequences with context-aware attention and autoregressive generation to improve short video recommendation accuracy, showing gains in watch time and retention on large-scale tests.