TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
The Abstraction and Reasoning Corpus (ARC) tests whether a model can infer an unseen transformation from a few input-output examples and apply it to a new grid. Looped visual reasoners refine predictions over multiple iterations, but conventional training constrains only the final output, leaving intermediate refinements unconstrained. We propose that these refinements should instead follow the transformation step by step. We introduce TraceViT, a looped visual reasoner trained with semantically monotonic transformation chains. We obtain these chains by rewriting and verifying programmatic task implementations, decomposing each solution into intermediate grid states. Each iteration is gro...
| Authors | Binnan Liu, Yechi Ma, Tian Xie et al. |
|---|---|
| Primary category | cs.CV |
| Published | 31 July 2026 |
| Last updated at source | 31 July 2026 |
Connected in the knowledge graph
- lbn32/arc-stepsDataset · cited by
Models and datasets referencing this paper
- lbn32/arc-stepsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.