PPaperPicks

Zhiyu Li

35 papers at tracked venues · 29 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
  2. Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems
  3. Large-Scale Online Learning for Generative List Recommendation in E-commerce: An Environment Policy Optimization Approach
  4. Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory
  5. SEAP: Sparse Expert Activation Pruning Unlocks the Brainpower of Large Language Models
  6. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
  7. TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
  8. Text2Mem: A Unified Memory Operation Language for Memory Operating System
  9. Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries
  10. Vision-Language Model Based Transfer Learning for Historical Document Recognition
  11. A Card-based Co-Design Toolkit for Exploring Smart Material Applications with Multiple Stakeholders: A Case Study on Automotive Interior Design
  12. Adversarial Preference Learning for Robust LLM Alignment
  13. CARE-STaR: Constraint-aware Self-taught Reasoner
  14. E-Carry: An Intermittent Pneumatic System for Enhanced Backpack Carrying Comfort
  15. GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning
  16. HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
  17. Integrating Large Language Models and Möbius Group Transformations for Temporal Knowledge Graph Embedding on the Riemann Sphere
  18. MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios
  19. MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
  20. MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System
  21. NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
  22. QAEncoder: Towards Aligned Representation Learning in Question Answering Systems
  23. Robust Stabilization of an Autonomous Underwater Vehicle in Specified Finite-time with Disturbance Rejection
  24. SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
  25. Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models
  26. UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions
  27. xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation
  28. Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
  29. Do Not Wait: Learning Re-Ranking Model Without User Feedback At Serving Time in E-Commerce
  30. FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
  31. Improving Generalization and Convergence by Enhancing Implicit Regularization
  32. MagnaDip Kit: A User-Friendly Toolkit for Streamlined Fabrication of Electromagnetic Responsive Textiles
    CHI 2024 · Zhiyu Li
  33. NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
  34. UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
  35. Xinyu: An Efficient LLM-based System for Commentary Generation