pith. sign in

Seq2seq models reconstruct visual jigsaw puzzles without seeing them

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.CV 2

years

2026 2

roles

background 2

polarities

background 2

representative citing papers

Do multimodal models imagine electric sheep?

cs.CV · 2026-05-10 · conditional · novelty 6.0

Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.

citing papers explorer

Showing 2 of 2 citing papers.