PPaperPicks

Qi Liu

University of Science and Technology of China, School of Artifical Intelligence and Data Science, State Key Laboratory of Cognitive Intelligence, Hefei, China

106 papers at tracked venues · 76 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?
  2. Can Slow-Thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
  3. Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees
  4. Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning
  5. DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors
  6. Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning
  7. From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMs
  8. Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA
  9. LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring
  10. Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
  11. MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
  12. One LLM Does Not Simulate All Students: Ability-Aware Student Simulation via Cognitive Diagnosis Guided LLM Assignment
  13. Swen: A Cross-Platform Desktop Assistant for Instant and Personalized Large-Language-Model Interaction
  14. TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning
  15. Themis: Automated Constraint-Aware Test Synthesis Framework for Code Reinforcement Learning
  16. TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
  17. A Closed-Form Solution for Fast and Reliable Adaptive Testing
  18. AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
    ACL 2025 · Qi Liu
  19. Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems
  20. BoxCD: Leveraging Contrastive Probabilistic Box Embedding for Effective and Efficient Learner Modeling
  21. CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval
  22. CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
  23. CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework
  24. CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models
  25. CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
  26. ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
  27. Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
  28. CursorCore: Assist Programming through Aligning Anything
  29. Deep Multiple Quantization Network on Long Behavior Sequence for Click-Through Rate Prediction
  30. Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor
  31. DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models
  32. Distribution-Driven Dense Retrieval: Modeling Many-to-One Query-Document Relationship
  33. Empowering Federated Graph Rationale Learning with Latent Environments
  34. Enhancing Code Search Intent with Programming Context Exploration
  35. Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
  36. GenAL: Generative Agent for Adaptive Learning
  37. GraphPrompter: Multi-Stage Adaptive Prompt Optimization for Graph In-Context Learning
  38. HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation
  39. Improving Time Series Forecasting via Instance-aware Post-hoc Revision
  40. InstrucTime: Advancing Time Series Classification with Multimodal Language Modeling
  41. Intelligent Interaction Platform for Personalized Digital Tutor: Advancing Empathetic and Adaptive Learning Experiences
  42. MGS3: A Multi-Granularity Self-Supervised Code Search Framework
  43. Making Transformer Decoders Better Differentiable Indexers
  44. MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality
  45. Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
  46. PQR: Improving Dense Retrieval via Potential Query Modeling
  47. Personalized Visual Content Generation in Conversational Systems
  48. Position: AI Evaluation Should Learn from How We Test Humans
  49. ProCC: Programmatic Reinforcement Learning for Efficient and Transparent TCP Congestion Control
  50. ReAL: How Can LLMs Simulate the Real Teacher? Retrieval-enhanced Agent for Adaptive Learning
  51. RecFlow: An Industrial Full Flow Recommendation Dataset
    ICLR 2025 · Qi Liu
  52. SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification
  53. Stepwise Reasoning Disruption Attack of LLMs
  54. TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models
  55. TestAgent: An Adaptive and Intelligent Expert for Human Assessment
  56. Think and Recall: Layer-Level Prompting for Lifelong Model Editing
  57. TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
  58. UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation
  59. Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
  60. VERSE: Verification-based Self-Play for Code Instructions
  61. WDMIR: Wavelet-Driven Multimodal Intent Recognition
  62. am-ELO: A Stable Framework for Arena-based LLM Evaluation
  63. A Unified Adaptive Testing System Enabled by Hierarchical Structure Search
  64. AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction
    AAAI 2024 · Qi Liu
  65. AdaRD: An Adaptive Response Denoising Framework for Robust Learner Modeling
  66. COMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks
  67. CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework
  68. Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
  69. Computerized Adaptive Testing via Collaborative Ranking
  70. Cooperative Classification and Rationalization for Graph Generalization
  71. Cross-reconstructed Augmentation for Dual-target Cross-domain Recommendation
  72. Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle
  73. DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
  74. Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
  75. Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis
  76. Enhancing Fairness in Meta-learned User Modeling via Adaptive Sampling
  77. Enhancing the Completeness of Rationales for Multi-Step Question Answering
  78. Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models
  79. Federated Self-Explaining GNNs with Anti-shortcut Augmentations
  80. FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
  81. GAP: A Grammar and Position-Aware Framework for Efficient Recognition of Multi-Line Mathematical Formulas
  82. Generalized Protein Pocket Generation with Prior-Informed Flow Matching
  83. Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding
  84. Graph-based Student Knowledge Profile for Online Intelligent Education
  85. HeckmanCD: Exploiting Selection Bias in Cognitive Diagnosis
  86. I-AM-G: Interest Augmented Multimodal Generator for Item Personalization
  87. Learning the Dynamics in Sequential Recommendation by Exploiting Real-time Information
  88. Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization
  89. Making LLMs as Fine-Grained Relation Extraction Data Augmentor
  90. Mitigating Cold-Start Problems in Knowledge Tracing with Large Language Models: An Attribute-aware Approach
  91. One-bit Deep Hashing: Towards Resource-Efficient Hashing Model with Binary Neural Network
  92. OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting
  93. Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models
  94. PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
  95. RePair: Automated Program Repair with Process-based Feedback
  96. SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
  97. Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
  98. Towards Explainable Computerized Adaptive Testing with Large Language Model
  99. Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
  100. Towards Few-Shot Self-explaining Graph Neural Networks
  101. Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
  102. Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm
  103. UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models
    CIKM 2024 · Qi Liu
  104. Unified Uncertainty Estimation for Cognitive Diagnosis Models
  105. Zero-1-to-3: Domain-Level Zero-Shot Cognitive Diagnosis via One Batch of Early-Bird Students towards Three Diagnostic Objectives
  106. π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control