MLn Club (ML Reading Group) #3: Tiny Recursive Models

​Week 3: Tiny Recursive Model

​Less is More: Recursive Reasoning with Tiny Networks

​This paper introduces Tiny Recursive Models (TRM), which drastically simplifies previous hierarchical reasoning approaches while achieving better performance on puzzle tasks like Sudoku and ARC-AGI. Using just a single 2-layer network with 7M parameters, TRM outperforms much larger language models by recursively refining both its current answer and internal reasoning state.

​The work challenges conventional scaling wisdom by showing that smaller networks with deeper recursion can outperform larger models, offering a parameter-efficient approach to complex reasoning tasks that's particularly relevant for practitioners interested in efficient architectures and the role of iterative refinement in problem-solving.

​Optional, but recommended blog post: The Hidden Drivers of HRM's Performance on ARC-AGI

​Join us at CASI to explore:

- Artificial reasoning - Think again vs think bigger?

- What if we've been scaling AI models in completely the wrong direction?

​Discussion at 20:00, (optional) quiet reading from 19:00.