An all-transistor physical-learning transformer can be trained to perform in-context learning

arXiv:2610.12571 · cs.LG, cond-mat.soft · Submitted 2026-10-08 · Read on arXiv

cs.LG, cond-mat.soft

Submitted: 2026-10-08

Updated: 2026-10-08

Comments: 18 pages, 11 figures, plus appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• In-Context Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
• A universal approximation theorem for nonlinear resistive networks
• Attention Is All You Need
• Equilibrium Propagation for Non-Conservative Systems
• Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
• Neural Machine Translation by Jointly Learning to Align and Translate
• Adam: A Method for Stochastic Optimization
• Symbolic Discovery of Optimization Algorithms
• Data Distributional Properties Drive Emergent In-Context Learning in Transformers
• The mechanistic basis of data dependence and abrupt learning in an in-context classification task
• In-context Learning and Induction Heads
• Training End-to-End Analog Neural Networks with Equilibrium Propagation
• Supervised learning in physical networks: From machine learning to learning machines
• Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons
• Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
• Training a Predictive Coding Network on ImageNet using Equilibrium Propagation
• Analog Implementation of the Softmax Function
• Understanding and Embracing Imperfection in Physical Learning Networks
• Language Models are Few-Shot Learners
• Using Fast Weights to Attend to the Recent Past

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