PPaperPicks

Lan-Zhe Guo

20 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
  2. Multi-field Balance-aware Calibration of Predictions in Online Advertising
  3. Step Back to Leap Forward: Self-Backtracking for Symbolic Reasoning and Planning in Language Models
  4. TabularMath: Understanding Math Reasoning over Tables with Large Language Models
  5. A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
  6. BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
  7. Breaking the Self-Evaluation Barrier: Reinforced Neuro-Symbolic Planning with Large Language Models
  8. CGI: Identifying Conditional Generative Models with Example Images
  9. Curriculum Abductive Learning for Mitigating Reasoning Shortcuts
  10. D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
  11. Fully Test-Time Adaptation for Feature Decrement in Tabular Data
  12. Fully Test-time Adaptation for Tabular Data
  13. Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
  14. TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments
  15. VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
  16. Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
  17. Vision-Language Model Selection and Reuse for Downstream Adaptation
  18. DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
  19. Offline Imitation Learning with Model-based Reverse Augmentation
  20. Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments