PPaperPicks

Yi Cai

South China University of Technology, School of Software Engineering, China

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

Venues

Frequent coauthors

Papers

  1. Beyond Maintenance: A Benchmark and Multi-Agent Framework for Repository-Usage Code Generation
  2. CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards
  3. CMIG: Conceptual Metaphor Theory-Inspired Framework for Metaphorical Image Generation
  4. DensityBars: A Space-Efficient Visualization for Event Temporal Distribution
  5. Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing
  6. MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement
  7. Open-ended Structured Question Assessment with Human-LLM Collaboration
  8. SRACG: A Code Generation Framework with Selective Retrieval Augmentation
  9. SeDev: Structured Semantic Exploration for LLM-Driven Code Generation
  10. SpecEdit: A Spectral Approach for Multi-Round Knowledge Editing
  11. Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies
  12. Unlocking Human-Like Visible Logic: How Logic Diagrams Boost Logic Reasoning in Large Language Models?
  13. Ad Hoc Teamwork via Offline Goal-Based Decision Transformers
  14. CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction
  15. Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model
  16. Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction
  17. Content-free Logical Modification of Large Language Model by Disentangling and Modifying Logic Representation
  18. ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments
  19. Explicitly Guided Difficulty-Controllable Visual Question Generation
  20. From Model Diagram to Code: A Benchmark Dataset and Multi-Agent Framework
  21. Ground and Reconstruct: Entity-Region Bidirectional Alignment Pre-Training for Low-Resource GMNER
  22. Look Around Before Locating: Considering Content and Structure Information for Visual Grounding
  23. MTRec: Learning to Align with User Preferences via Mental Reward Models
  24. RBRTI: Retrieval-Based Risk Type Identification from Financial News
  25. RTADev: Intention Aligned Multi-Agent Framework for Software Development
  26. Retrieval-Augmented Classification for Financial User Profiling: A Lightweight Approach
  27. Risk-Aware Automatic Text Summarization with Pre-Identification of Risk Categories and Emphasis
  28. RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models
  29. Sequence Structure Aware Retriever for Procedural Document Retrieval: A New Dataset and Baseline
  30. Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues
  31. The Most Influenced Community Search on Social Networks
  32. Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree
  33. Walk in Others' Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation
  34. Automated Defect Report Generation for Enhanced Industrial Quality Control
  35. Deconfounded Emotion Guidance Sticker Selection with Causal Inference
  36. Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model
  37. Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
  38. PoRank: A Practical Framework for Learning to Rank Policies
  39. Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point
  40. Updating Large Language Models' Memories with Time Constraints