TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.
Zico Kolter , title =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
FPRM is a Transformer-based model using fixed-point convergence for adaptive halting in looped architectures, claimed effective on Sudoku, Maze, state-tracking, and ARC-AGI benchmarks.
VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.
citing papers explorer
-
Less is More: Recursive Reasoning with Tiny Networks
TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.