PPaperPicks

Ge Li

Peking University, Key Laboratory of High Confidence Software Technologies, Bejing, China

26 papers at tracked venues · 26 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-5828-0186 ↗Homepage ↗

Venues

ACL ×17NeurIPS ×5AAAI ×3ICML ×1

Frequent coauthors

Yihong Dong
DBLP profile ↗ORCID search ↗
×7
Kechi Zhang
DBLP profile ↗ORCID search ↗
×5
Xue Jiang
DBLP profile ↗ORCID search ↗
×3
Huanyu Liu
DBLP profile ↗ORCID search ↗
×2
Jia Li
DBLP profile ↗ORCID search ↗
×2
Yitong Zhang
DBLP profile ↗ORCID search ↗
×1
Zheng Fang
DBLP profile ↗ORCID search ↗
×1
Ziliang Wang
DBLP profile ↗ORCID search ↗
×1
Jia Li
DBLP profile ↗ORCID search ↗
×1
Kaibo Liu
DBLP profile ↗ORCID search ↗
×1
Yuqi Zhu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
    ACL 2026 ·
    Xue Jiang
    DBLP profile ↗ORCID search ↗
  2. DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
    AAAI 2026 ·
    Yitong Zhang
    DBLP profile ↗ORCID search ↗
  3. EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs
    ACL 2026 ·
    Huanyu Liu
    DBLP profile ↗ORCID search ↗
  4. IntentCoding: Amplifying User Intent in Code Generation
    ACL 2026 ·
    Zheng Fang
    DBLP profile ↗ORCID search ↗
  5. KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development?
    ACL 2026 ·
    Xue Jiang
    DBLP profile ↗ORCID search ↗
  6. Large Language Model Unlearning for Source Code
    AAAI 2026 ·
    Xue Jiang
    DBLP profile ↗ORCID search ↗
  7. RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
    ACL 2026 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  8. Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation
    ACL 2026 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  9. VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection
    ACL 2026 ·
    Ziliang Wang
    DBLP profile ↗ORCID search ↗
  10. Benchmarking Long-Context Language Models on Long Code Understanding
    ACL 2025 ·
    Jia Li
    DBLP profile ↗ORCID search ↗
  11. CodeDPO: Aligning Code Models with Self Generated and Verified Source Code
    ACL 2025 ·
    Kechi Zhang
    DBLP profile ↗ORCID search ↗
  12. Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
    ICML 2025 · Ge Li
  13. FAN: Fourier Analysis Networks
    NeurIPS 2025 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  14. Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points
    ACL 2025 ·
    Kechi Zhang
    DBLP profile ↗ORCID search ↗
  15. LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs
    ACL 2025 ·
    Kaibo Liu
    DBLP profile ↗ORCID search ↗
  16. Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
    NeurIPS 2025 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  17. Recursive Transformer: Boosting Reasoning Ability with State Stack
    NeurIPS 2025 ·
    Kechi Zhang
    DBLP profile ↗ORCID search ↗
  18. Rethinking Repetition Problems of LLMs in Code Generation
    ACL 2025 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  19. SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
    NeurIPS 2025 ·
    Huanyu Liu
    DBLP profile ↗ORCID search ↗
  20. CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
    ACL 2024 ·
    Kechi Zhang
    DBLP profile ↗ORCID search ↗
  21. DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
    ACL 2024 ·
    Jia Li
    DBLP profile ↗ORCID search ↗
  22. EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
    NeurIPS 2024 ·
    Jia Li
    DBLP profile ↗ORCID search ↗
  23. Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
    ACL 2024 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗
  24. HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position
    ACL 2024 ·
    Kechi Zhang
    DBLP profile ↗ORCID search ↗
  25. Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
    AAAI 2024 ·
    Yuqi Zhu
    DBLP profile ↗ORCID search ↗
  26. PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
    ACL 2024 ·
    Yihong Dong
    DBLP profile ↗ORCID search ↗