PPaperPicks

Guojie Song

Peking University, Beijing, China

18 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Addressing Aggregation-Induced Information Loss in Graph Neural Networks
  2. Context-Value-Action Architecture for Value-Driven Large Language Model Agents
  3. FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
  4. From Pseudo-Balancing to True Specialization: Memory-Aware Routing for Mixture-of-Experts
  5. NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
  6. Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
  7. AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
  8. DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach
  9. EAVIT: Efficient and Accurate Human Value Identification From Text Data via LLMs
  10. Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
  11. Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models
  12. RL4CO: An Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
  13. TransPlace: Transferable Circuit Global Placement via Graph Neural Network
  14. AnchorGT: Efficient and Flexible Attention Architecture for Scalable Graph Transformers
  15. Laner-GNN: Adapting to Long-Tail Degree Distribution with Latent Neighborhood Restorers
  16. ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
  17. RoutePlacer: An End-to-End Routability-Aware Placer with Graph Neural Network
  18. ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models