PPaperPicks

Shijin Wang

iFLYTEK AI Research (Hebei), Langfang, China

37 papers at tracked venues · 29 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-9202-7678 ↗Homepage ↗

Venues

NeurIPS ×8EMNLP ×6AAAI ×5ACL ×5ICML ×5WWW ×3ICLR ×1IJCAI ×1SDM ×1SIGIR ×1SIGKDD ×1

Frequent coauthors

Runxuan Liu
DBLP profile ↗ORCID search ↗
×2
Yan Zhuang
DBLP profile ↗ORCID search ↗
×2
Jiayu Liu
DBLP profile ↗ORCID search ↗
×2
Yuxuan Zhou
DBLP profile ↗ORCID search ↗
×2
Zirui Liu
DBLP profile ↗ORCID search ↗
×2
Yupeng Li
DBLP profile ↗ORCID search ↗
×1
Bichen Wang
DBLP profile ↗ORCID search ↗
×1
Yuhan Chen
DBLP profile ↗ORCID search ↗
×1
Yuxiang Guo
DBLP profile ↗ORCID search ↗
×1
Keyu Zhu
DBLP profile ↗ORCID search ↗
×1
Jiawei Cao
DBLP profile ↗ORCID search ↗
×1
Weixiang Zhao
DBLP profile ↗ORCID search ↗
×1

Papers

  1. BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation
    AAAI 2026 ·
    Yupeng Li
    DBLP profile ↗ORCID search ↗
  2. CARE-Bench: A Benchmark of Diverse Client Simulations Guided by Expert Principles for Evaluating LLMs in Psychological Counseling
    AAAI 2026 ·
    Bichen Wang
    DBLP profile ↗ORCID search ↗
  3. CPT-Agent: A Cognitive Process Theory-driven Framework for Student Simulation in Writing Development
    ACL 2026 ·
    Yuhan Chen
    DBLP profile ↗ORCID search ↗
  4. From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMs
    AAAI 2026 ·
    Yuxiang Guo
    DBLP profile ↗ORCID search ↗
  5. Good Ranks Follow Good Answers: Unsupervised Answer-Driven Reranking for Multimodal Document QA
    SIGIR 2026 ·
    Keyu Zhu
    DBLP profile ↗ORCID search ↗
  6. Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
    ACL 2026 ·
    Runxuan Liu
    DBLP profile ↗ORCID search ↗
  7. Re³: Relevance & Recency Retrieval for Mitigating Temporal Hallucination
    ACL 2026 ·
    Jiawei Cao
    DBLP profile ↗ORCID search ↗
  8. A Closed-Form Solution for Fast and Reliable Adaptive Testing
    NeurIPS 2025 ·
    Yan Zhuang
    DBLP profile ↗ORCID search ↗
  9. Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
    EMNLP 2025 ·
    Weixiang Zhao
    DBLP profile ↗ORCID search ↗
  10. Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation
    EMNLP 2025 ·
    Tianhao Niu
    DBLP profile ↗ORCID search ↗
  11. CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
    ICML 2025 ·
    Jiayu Liu
    DBLP profile ↗ORCID search ↗
  12. ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
    WWW 2025 ·
    Mingyue Cheng
    DBLP profile ↗ORCID search ↗
  13. CursorCore: Assist Programming through Aligning Anything
    ICML 2025 ·
    Hao Jiang
    DBLP profile ↗ORCID search ↗
  14. Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis
    EMNLP 2025 ·
    Yiru Tang
    DBLP profile ↗ORCID search ↗
  15. Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
    ICML 2025 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  16. Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
    ICLR 2025 ·
    Lili Zhao
    DBLP profile ↗ORCID search ↗
  17. FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
    NeurIPS 2025 ·
    Xinxin You
    DBLP profile ↗ORCID search ↗
  18. From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation
    ACL 2025 ·
    Cheng Cheng
    DBLP profile ↗ORCID search ↗
  19. How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
    NeurIPS 2025 ·
    Xin Lu
    DBLP profile ↗ORCID search ↗
  20. Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
    NeurIPS 2025 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  21. MMATH: A Multilingual Benchmark for Mathematical Reasoning
    EMNLP 2025 ·
    Wenyang Luo
    DBLP profile ↗ORCID search ↗
  22. Multi-Perspective Consolidation Enhanced Cognitive Diagnosis via Conditional Diffusion Model
    AAAI 2025 ·
    Guanhao Zhao
    DBLP profile ↗ORCID search ↗
  23. Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
    ACL 2025 ·
    Runxuan Liu
    DBLP profile ↗ORCID search ↗
  24. Position: AI Evaluation Should Learn from How We Test Humans
    ICML 2025 ·
    Yan Zhuang
    DBLP profile ↗ORCID search ↗
  25. am-ELO: A Stable Framework for Arena-based LLM Evaluation
    ICML 2025 ·
    Zirui Liu
    DBLP profile ↗ORCID search ↗
  26. Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
    WWW 2024 ·
    Liyang He
    DBLP profile ↗ORCID search ↗
  27. CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework
    AAAI 2024 ·
    Rui Li
    DBLP profile ↗ORCID search ↗
  28. Computerized Adaptive Testing via Collaborative Ranking
    NeurIPS 2024 ·
    Zirui Liu
    DBLP profile ↗ORCID search ↗
  29. Graph-based Student Knowledge Profile for Online Intelligent Education
    SDM 2024 ·
    Jinze Wu
    DBLP profile ↗ORCID search ↗
  30. Item-Difficulty-Aware Learning Path Recommendation: From a Real Walking Perspective
    SIGKDD 2024 ·
    Haotian Zhang
    DBLP profile ↗ORCID search ↗
  31. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
    NeurIPS 2024 ·
    Kun Zhou
    DBLP profile ↗ORCID search ↗
  32. Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
    IJCAI 2024 ·
    Tong Xiao
    DBLP profile ↗ORCID search ↗
  33. Optimizing Chinese Lexical Simplification Across Word Types: A Hybrid Approach
    EMNLP 2024 ·
    Zihao Xiao
    DBLP profile ↗ORCID search ↗
  34. SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
    NeurIPS 2024 ·
    Jiayu Liu
    DBLP profile ↗ORCID search ↗
  35. SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model
    EMNLP 2024 ·
    Dayong Wu
    DBLP profile ↗ORCID search ↗
  36. Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
    NeurIPS 2024 ·
    Zheng Zhang
    DBLP profile ↗ORCID search ↗
  37. Unified Uncertainty Estimation for Cognitive Diagnosis Models
    WWW 2024 ·
    Fei Wang
    DBLP profile ↗ORCID search ↗