Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Layer Normalization
- PonderNet: Learning to Ponder
- Universal Transformers
- OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
- Depth-Adaptive Transformer
- Adaptive Computation Time for Recurrent Neural Networks
- Training Large Language Models to Reason in a Continuous Latent Space
- Session-based Recommendations with Recurrent Neural Networks
- Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation
- LoRA: Low-Rank Adaptation of Large Language Models
- CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction
- UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation
- LARES: Latent Reasoning for Sequential Recommendation
- Decoupled Weight Decay Regularization
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
- Recurrent Neural Networks for Long and Short-Term Sequential Recommendation
- Where Reasoning Matters: Rethinking Latent Reasoning in Semantic ID-based Generative Recommendation
- Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents