PPaperPicks

Yong Liu

Huawei Noah's Ark Lab, Singapore

40 papers at tracked venues · 34 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Accelerating Generative Recommendation via Simple Categorical User Sequence Compression
  2. Bridging Personalization and AI: From RAG to Agent
  3. Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
  4. Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
  5. FollowTable: A Benchmark for Instruction-Following Table Retrieval
  6. FuXi-γ: Efficient Sequential Recommendation with Exponential-Power Temporal Encoder and Diagonal-Sparse Positional Mechanism
  7. Full Retraining, Incremental Fine-tuning, and Hybrid Serving: Model Updating and Serving for Industrial Generative Recommender Systems
  8. Generative Data Transformation: From Mixed to Unified Data
  9. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
  10. Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
  11. Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
  12. Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
  13. To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
  14. Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
  15. Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
  16. Breaking the Bottleneck: User-Specific Optimization and Real-Time Inference Integration for Sequential Recommendation
  17. DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction
  18. FuXi-α: Scaling Recommendation Model with Feature Interaction Enhanced Transformer
  19. Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation
  20. Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model
  21. LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
  22. MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
  23. MIT: A Multi-Tower Information Transfer Framework Based on Hierarchical Task Relationship Modeling
  24. MMDocIR: Benchmarking Multimodal Retrieval for Long Documents
  25. Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction
  26. P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models
  27. RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
  28. Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
  29. SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
    ICML 2025 · Yong Liu
  30. Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
    NeurIPS 2025 · Yong Liu
  31. Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology
  32. Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
  33. ToolACE: Winning the Points of LLM Function Calling
  34. Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
  35. Dataset Regeneration for Sequential Recommendation
  36. Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation
  37. Enhancing Click-through Rate Prediction in Recommendation Domain with Search Query Representation
  38. Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization
  39. The 2nd Workshop on Recommendation with Generative Models
  40. User Behavior Enriched Temporal Knowledge Graphs for Sequential Recommendation