Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems

arXiv:2605.13470 · cs.LG · Submitted 2026-05-13 · Read on arXiv

cs.LG

Submitted: 2026-05-13

Updated: 2026-10-02

Code: https://github.com/arkady-gonoskov/twincher

Terminology

• Representation Learning — 2× in this paper · explained in 2 episodes
• Adversarial Training — 1× in this paper · explained in 1 episode
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Deep Convolutional Inverse Graphics Network
• Deep Learning Techniques for Inverse Problems in Imaging
• BayesFlow: Learning complex stochastic models with invertible neural networks
• Deep Learning Scaling is Predictable, Empirically
• A Neural Scaling Law from the Dimension of the Data Manifold
• DeepIM: Deep Iterative Matching for 6D Pose Estimation
• Application of the Wasserstein metric to seismic signals
• Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• NICE: Non-linear Independent Components Estimation
• World Models
• Model-based Reinforcement Learning: A Survey
• High-Accuracy Model-Based Reinforcement Learning, a Survey
• Understanding World or Predicting Future? A Comprehensive Survey of World Models
• World Models for Autonomous Driving: An Initial Survey
• World Model for Robot Learning: A Comprehensive Survey
• Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision
• Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
• Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
• Interactive Imitation Learning in Robotics: A Survey

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks