PPaperPicks

Xinshuai Dong

19 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
  2. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
  3. A Sample Efficient Conditional Independence Test in the Presence of Discretization
  4. Causal Representation Learning from General Environments under Nonparametric Mixing
  5. Latent Variable Causal Discovery under Selection Bias
  6. Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
    ICML 2025 · Xinshuai Dong
  7. Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
  8. Type Information-Assisted Self-Supervised Knowledge Graph Denoising
  9. When Selection Meets Intervention: Additional Complexities in Causal Discovery
  10. A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
    ICLR 2024 · Xinshuai Dong
  11. Causal Temporal Representation Learning with Nonstationary Sparse Transition
  12. Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
  13. Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
  14. Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
  15. On the Parameter Identifiability of Partially Observed Linear Causal Models
    NeurIPS 2024 · Xinshuai Dong
  16. READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
  17. Score-Based Causal Discovery of Latent Variable Causal Models
  18. Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
  19. Topic Modeling as Multi-Objective Contrastive Optimization