PPaperPicks

Shixuan Liu

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

Venues

Frequent coauthors

Papers

  1. $L{3}$ C: Leaf-Centric Continuous Codes for Natural Language-Driven Table Discovery
  2. CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction
  3. Detecting Unobserved Confounders: A Kernelized Regression Approach
  4. Invariant Learning on Heterogeneous Graphs via Subgraph Environment Inference
  5. Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
  6. Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
  7. Environment Inference for Learning Generalizable Dynamical System
    NeurIPS 2025 · Shixuan Liu
  8. From Captions to Rewards (CaReVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
  9. MapExplorer: New Content Generation from Low-Dimensional Visualizations
  10. RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
  11. Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
  12. Solving Combinatorial Optimization Problem Over Graph Through QUBO Transformation and Deep Reinforcement Learning
  13. dattri: A Library for Efficient Data Attribution
  14. icsPLMs: Exploring Pre-trained Language Models in Intelligent Customer Service (Student Abstract)
    AAAI 2024 · Shixuan Liu