• Bio
  • Papers
  • News
  • Experience
  • Projects
  • Teaching
  • Publications
    • Analytic DAG Constraints for Differentiable DAG Learning
    • CLAP: Isolating Content from Style Through Contrastive Learning with Augmented Prompts
    • Generalization of anomaly detection in bridge structures using a vibration‐based Siamese convolutional neural network
    • Identifiable Latent Polynomial Causal Models Through the Lens of Change
    • A Causal Inspired Early-Branching Structure for Domain Generalization
    • Machine Learning Big Data Set Analysis Reveals C–C Electro-Coupling Mechanism
    • Highway Graph to Accelerate Reinforcement Learning
    • InvariantStock: Learning Invariant Features for Mastering the Shifting Market
    • Physics-informed data-driven unsteady Reynolds-averaged Navier–Stokes turbulence modeling for particle-laden jet flows
    • Rapid non-destructive method to phenotype stomatal traits
    • Active-learning accelerated computational screening of A2B@ NG catalysts for CO2 electrochemical reduction
    • Factor graph neural networks
    • Human interaction understanding with consistency-aware learning
    • SharpFormer: Learning local feature preserving global representations for image deblurring
    • A lightweight network for high dynamic range imaging
    • NTIRE 2022 challenge on high dynamic range imaging: Methods and results
    • Truncated matrix power iteration for differentiable dag learning
    • A bidirectional graph neural network for traveling salesman problems on arbitrary symmetric graphs
    • Memory-augmented dynamic neural relational inference
    • Factor graph neural networks
    • Learning deep gradient descent optimization for image deconvolution
    • Multiplicative gaussian particle filter
    • Visual relationship detection with low rank non-negative tensor decomposition
    • Deep graphical feature learning for the feature matching problem
    • An adaptive markov random field for structured compressive sensing
    • Convolutional sequence to sequence model for human dynamics
    • Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching.
    • Solving Constrained Combinatorial Optimisation Problems via MAP Inference without High-Order Penalties
    • Joint probabilistic matching using m-best solutions
    • Pairwise matching through max-weight bipartite belief propagation
    • Real-time correlation filter tracking by efficient dense belief propagation with structure preserving
    • Joint probabilistic data association revisited
    • Learning graph structure for multi-label image classification via clique generation
    • Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations
    • Variable kernel density estimation based robust regression and its applications
    • Generalized Kernel Density Estimation Based Robust Estimator and Its Application
  • Working Papers
    • Rethinking State Disentanglement in Causal Reinforcement Learning
    • Silver Linings: On the Types of Distribution Shifts that Enhance Identifiability in Causal Representation Learning
    • The Quest for Winning Tickets in Low-Rank Adapters
    • I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
    • Decomposing Task Vectors for Refined Model Editing
    • Identifying Weight-Variant Latent Causal Models
  • Blog
    • 🎉 Our Paper "Analytic DAG Constraints for Continuous DAG learning" was accepted to ICLR25
    • 🎉 Congrants to Alireza Ghiasi et. al. on the acceptance of 'Generalization of anomaly detection in bridge structures using a vibration-based Siamese convolutional neural network' to Computer Aided Civil Eng
    • 🎉 Congrants to Yichao et. al. on the acceptance of 'CLAP: Isolating Content from Style Through Contrastive Learning with Augmented Prompts' to ECCV2024
  • Projects
  • Projects
    • Graph Neural Networks
    • AI for Science
    • Latent Causal Discovery in Reinforcement Learning and Large Language Models
    • Advances in Differentiable DAG Learning: Analytic Constraints and Truncated Power Iteration
  • Experience
  • Teaching and Supervision

Rethinking State Disentanglement in Causal Reinforcement Learning

Apr 28, 2025·
Haiyao Cao
,
Zhen Zhang
,
Yuhang Liu
,
Panpan Cai
,
Jinan Zou
,
Ehsan Abbasnejad
,
Biwei Huang
,
Mingming Gong
,
Anton Van Den Hengel
,
Javen Qinfeng Shi
· 0 min read
Last updated on Apr 28, 2025
Silver Linings: On the Types of Distribution Shifts that Enhance Identifiability in Causal Representation Learning Jan 23, 2025 →

© 2025 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.