PPaperPicks

Changwen Zheng

23 papers at tracked venues · 19 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
  2. Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning
  3. Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration
  4. Group Causal Policy Optimization for Post-Training Large Language Models
  5. HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
  6. TMAE: Learning Targeted Multi-Agent Exploration via Causal Inference
  7. Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection
  8. Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach
  9. LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
  10. Learn to Think: Bootstrapping LLM Logic Through Graph Representation Learning
  11. Learning Invariant Causal Mechanism from Vision-Language Models
  12. Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
  13. Loss of Plasticity: A New Perspective on Solving Multi-Agent Exploration for Sparse Reward Tasks
  14. On the Out-of-Distribution Generalization of Self-Supervised Learning
  15. Revisiting Communication Efficiency in Multi-Agent Reinforcement Learning from the Dimensional Analysis Perspective
  16. Towards the Causal Complete Cause of Multi-Modal Representation Learning
  17. BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
  18. Hacking Task Confounder in Meta-Learning
  19. Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning
  20. Not All Frequencies Are Created Equal: Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting
  21. Rethinking Causal Relationships Learning in Graph Neural Networks
  22. Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
  23. T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration