REI
ADAPT-1 // MACHINAREI // RESEARCH

Adapt-1 Machina: Learning Continuous Control Sequences

Simulation records of Adapt-1 learning control sequences from outcome feedback, including robotic manipulation and contextual control.

5:26 PM | Sep 21, 2026
READ MORE →
Adapt-1 Machina: Learning Continuous Control Sequences
Adapt-1 / DiscoveryREI // RESEARCH

Emergence: Toward Autonomous Structure Discovery in Adapt-1

Today we are releasing Discovery (Beta) for Adapt-1. Discovery is what happens when the authored learner ontology is removed and the substrate has to build its own model of interaction.

4:54 PM | Aug 27, 2026
READ MORE →
Emergence: Toward Autonomous Structure Discovery in Adapt-1
Adapt-1 / PreviewREI // RESEARCH

Unlocking Plasticity Rules

Temporal Context Projection and Counterfactual Utility Plasticity are live in the Adapt-1 Preview API today. What each rule changes, and what the current evidence establishes.

4:54 PM | Aug 20, 2026
READ MORE →
Unlocking Plasticity Rules
Adapt-1 / Open BetaREI // RESEARCH

The Dynamics of, Sequential, Transitional and Contextual Online Learning

Adapt-1 is available in open beta through the Adapt-1 app. This article shows five learning procedures across Symbolic Alchemy, ALFWorld, CausaLab, BOP-Ask, and a transition mini sim.

6:30 PM | Aug 12, 2026
READ MORE →
The Dynamics of, Sequential, Transitional and Contextual Online Learning
ADAPT-1 // PREVIEWREI // RESEARCH

Introducing Adapt-1 Preview: A Pretraining-Free Substrate for Test-Time Learning

Adapt-1 Preview is a pretraining-free substrate for test-time learning, a research release of ADAPT from Rei Labs.

4:51 PM | Aug 6, 2026
READ MORE →
Introducing Adapt-1 Preview: A Pretraining-Free Substrate for Test-Time Learning
ADAPT SERIES // PART IREI // RESEARCH

Adaptive State from Partially Observed Streams

Part I: Adaptive State, Hybrid Representation, and Relational Hopfield Memory

4:30 PM | Jul 31, 2026
READ MORE →
Adaptive State from Partially Observed Streams

Archive

Browse previous articles