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.
Onepiece: Bringing context engineering and reasoning to industrial cascade ranking system.arXiv preprint arXiv:2509.18091
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 11representative citing papers
Exact LTI Koopman models for nonlinear control systems require affine linear dynamics under controllability and coordinate inclusion assumptions.
LoopCTR trains CTR models with recursive layer reuse and process supervision so that zero-loop inference outperforms baselines on public and industrial 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.
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative 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.
UniPinRec unifies retrieval and ranking into a single model and pipeline deployed at Pinterest, reporting +1% engagement lift, 11.1% lower latency, and 63.6% higher QPS.
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.
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%.
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.
Token Factory transforms traditional signals into soft tokens for efficient integration and compression into Large Recommendation Models, avoiding prompt length explosion while enhancing performance.
citing papers explorer
-
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.
-
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.
-
LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
LoopCTR trains CTR models with recursive layer reuse and process supervision so that zero-loop inference outperforms baselines on public and industrial 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.
-
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.
-
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.
-
UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
UniPinRec unifies retrieval and ranking into a single model and pipeline deployed at Pinterest, reporting +1% engagement lift, 11.1% lower latency, and 63.6% higher QPS.
-
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.
-
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%.
-
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.
-
Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
Token Factory transforms traditional signals into soft tokens for efficient integration and compression into Large Recommendation Models, avoiding prompt length explosion while enhancing performance.