SOURCE-LINKED INTELLIGENCE

Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

The Abstraction and Reasoning Corpus and related benchmarks evaluate whether AI models can solve novel reasoning tasks, but often leave unclear whether success reflects inference of the intended underlying rule or reliance on shortcuts. We address this gap by studying test-time task embeddings in Vision ARC (VARC), a model in which a pre-trained backbone is complemented by a trainable embedding representing the transformation rule. In the original VARC, test-time training (TTT) is jointly applied to the backbone and task embedding. Here we introduce a novel two-step TTT protocol: first finetun

Read original source ↗ Open in workspace

recordType

paper

region

Global