PPaperPicks

Kun Zhang

Carnegie Mellon University, Department of Philosophy, Pittsburgh, PA, USA

81 papers at tracked venues · 75 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
  2. Horizontal and Vertical Federated Causal Structure Learning via Higher-order Cumulants
  3. Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders
  4. Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and Beyond
  5. Text Embedding as Treatment: A Meta Causal Approach for Robust Sentiment Classification
  6. A General Representation-Based Approach to Multi-Source Domain Adaptation
  7. A Robust Method to Discover Causal or Anticausal Relation
  8. A Sample Efficient Conditional Independence Test in the Presence of Discretization
  9. A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery
  10. Analytic DAG Constraints for Differentiable DAG Learning
  11. Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference
  12. Causal Representation Learning from General Environments under Nonparametric Mixing
  13. Causal Representation Learning from Multimodal Biomedical Observations
  14. CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
  15. Classifying Treatment Responders: Bounds and Algorithms
  16. Detecting Generated Images by Fitting Natural Image Distributions
  17. Differentiable Causal Discovery for Latent Hierarchical Causal Models
    ICLR 2025 ·
    Parjanya Prajakta Prashant
  18. Empowering LLMs with Logical Reasoning: A Comprehensive Survey
  19. Extracting Rare Dependence Patterns via Adaptive Sample Reweighting
  20. Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness
  21. Flow: Modularized Agentic Workflow Automation
  22. Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders
  23. Identification of Intermittent Temporal Latent Process
  24. Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations
  25. LLM Interpretability with Identifiable Temporal-Instantaneous Representation
  26. Latent Variable Causal Discovery under Selection Bias
  27. Learning Counterfactual Outcomes Under Rank Preservation
  28. Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
  29. Learning Graph Invariance by Harnessing Spuriosity
  30. Learning Vision and Language Concepts for Controllable Image Generation
  31. Noisy Test-Time Adaptation in Vision-Language Models
  32. Nonparametric Factor Analysis and Beyond
  33. Nonparametric Identification of Latent Concepts
  34. OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad
  35. On the Identification of Temporal Causal Representation with Instantaneous Dependence
  36. Online Time Series Forecasting with Theoretical Guarantees
  37. Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
  38. Practical Kernel Selection for Kernel-based Conditional Independence Test
  39. Prompting Fairness: Integrating Causality to Debias Large Language Models
  40. Reflection-Window Decoding: Text Generation with Selective Refinement
  41. SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
  42. Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
  43. The third pillar of causal analysis? A measurement perspective on causal representations
  44. Thought Communication in Multiagent Collaboration
  45. Towards Accurate Time Series Forecasting via Implicit Decoding
  46. Towards Identifiability of Hierarchical Temporal Causal Representation Learning
  47. Towards Self-Refinement of Vision-Language Models with Triangular Consistency
  48. Type Information-Assisted Self-Supervised Knowledge Graph Denoising
  49. When Selection Meets Intervention: Additional Complexities in Causal Discovery
  50. A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
  51. ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation
  52. CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
  53. Causal Representation Learning from Multiple Distributions: A General Setting
    ICML 2024 · Kun Zhang
  54. Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions
  55. Causal Temporal Representation Learning with Nonstationary Sparse Transition
  56. Detecting and Identifying Selection Structure in Sequential Data
  57. Discovery of the Hidden World with Large Language Models
  58. Empowering Graph Invariance Learning with Deep Spurious Infomax
  59. Federated Causal Discovery from Heterogeneous Data
  60. Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View
  61. IEEE International Conference on Data Mining, ICDM 2024, Abu Dhabi, United Arab Emirates, December 9-12, 2024
  62. Identifiable Latent Polynomial Causal Models through the Lens of Change
  63. Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants
  64. Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
  65. Identifying Selections for Unsupervised Subtask Discovery
  66. LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
  67. Learning Discrete Concepts in Latent Hierarchical Models
  68. Learning Discrete Latent Variable Structures with Tensor Rank Conditions
  69. Local Causal Discovery with Linear non-Gaussian Cyclic Models
  70. MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
  71. Natural Counterfactuals With Necessary Backtracking
  72. Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
  73. On Causal Discovery in the Presence of Deterministic Relations
  74. On the Parameter Identifiability of Partially Observed Linear Causal Models
  75. On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data
  76. Optimal Kernel Choice for Score Function-based Causal Discovery
  77. Procedural Fairness Through Decoupling Objectionable Data Generating Components
  78. S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
  79. Score-Based Causal Discovery of Latent Variable Causal Models
  80. Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
  81. Towards Understanding Extrapolation: a Causal Lens