PPaperPicks

Quanyu Dai

23 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
  2. Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation
  3. Breaking the Self-Evaluation Barrier: Reinforced Neuro-Symbolic Planning with Large Language Models
  4. CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
  5. Distributional LLM-as-a-Judge
  6. EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
  7. Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent
  8. Improving Retrospective Language Agents via Joint Policy Gradient Optimization
  9. KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
  10. MCNet: Monotonic Calibration Networks for Expressive Uncertainty Calibration in Online Advertising
    WWW 2025 · Quanyu Dai
  11. MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
  12. MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
  13. MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents
  14. MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
  15. RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
  16. SocialEval: Evaluating Social Intelligence of Large Language Models
  17. Benchmarking News Recommendation in the Era of Green AI
  18. MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation
  19. Modeling User Attention in Music Recommendation
  20. Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey
  21. Reflective Multi-Agent Collaboration based on Large Language Models
  22. UniEmbedding: Learning Universal Multi-Modal Multi-Domain Item Embeddings via User-View Contrastive Learning
  23. Would You Like Your Data to Be Trained? A User Controllable Recommendation Framework