PPaperPicks

Zhenya Huang

53 papers at tracked venues · 45 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees
  2. From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMs
  3. Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA
  4. LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring
  5. One LLM Does Not Simulate All Students: Ability-Aware Student Simulation via Cognitive Diagnosis Guided LLM Assignment
  6. SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?
  7. Swen: A Cross-Platform Desktop Assistant for Instant and Personalized Large-Language-Model Interaction
  8. Themis: Automated Constraint-Aware Test Synthesis Framework for Code Reinforcement Learning
  9. TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting
  10. A Closed-Form Solution for Fast and Reliable Adaptive Testing
  11. Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
  12. Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems
  13. Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning
  14. BoxCD: Leveraging Contrastive Probabilistic Box Embedding for Effective and Efficient Learner Modeling
  15. CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval
  16. Can LLMs Solve Longer Math Word Problems Better?
  17. CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models
  18. CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
  19. Combining Denoised Neural Network and Genetic Symbolic Regression for Memory Behavior Modeling via Dynamic Asynchronous Optimization
  20. Distribution-Driven Dense Retrieval: Modeling Many-to-One Query-Document Relationship
  21. Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
  22. Enhancing Code Search Intent with Programming Context Exploration
  23. Explore What LLM Does Not Know in Complex Question Answering
  24. From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation
  25. IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
  26. MGS3: A Multi-Granularity Self-Supervised Code Search Framework
  27. Multi-Perspective Consolidation Enhanced Cognitive Diagnosis via Conditional Diffusion Model
  28. Position: AI Evaluation Should Learn from How We Test Humans
  29. Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
  30. TestAgent: An Adaptive and Intelligent Expert for Human Assessment
  31. Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
  32. What Makes In-context Learning Effective for Mathematical Reasoning
  33. A Knowledge-Injected Curriculum Pretraining Framework for Question Answering
  34. A Unified Adaptive Testing System Enabled by Hierarchical Structure Search
  35. Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
  36. CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework
  37. Computerized Adaptive Testing via Collaborative Ranking
  38. Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle
  39. Enhancing Fairness in Meta-learned User Modeling via Adaptive Sampling
  40. Enhancing the Completeness of Rationales for Multi-Step Question Answering
  41. Graph-based Student Knowledge Profile for Online Intelligent Education
  42. Item-Difficulty-Aware Learning Path Recommendation: From a Real Walking Perspective
  43. Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
  44. Mitigating Cold-Start Problems in Knowledge Tracing with Large Language Models: An Attribute-aware Approach
  45. One-bit Deep Hashing: Towards Resource-Efficient Hashing Model with Binary Neural Network
  46. Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models
  47. RePair: Automated Program Repair with Process-based Feedback
  48. SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
  49. Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
  50. Towards Explainable Computerized Adaptive Testing with Large Language Model
  51. Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
  52. Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm
  53. Unified Uncertainty Estimation for Cognitive Diagnosis Models