pith. sign in

Mind’s eye of llms: Visualization-of-thought elicits spatial reasoning in large language models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Grounded Reinforcement Learning for Visual Reasoning

cs.CV · 2025-05-29 · unverdicted · novelty 6.0

ViGoRL introduces visually grounded RL that anchors reasoning steps to image coordinates and uses multi-turn zooming to outperform standard RL and supervised baselines on spatial and GUI reasoning benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Grounded Reinforcement Learning for Visual Reasoning cs.CV · 2025-05-29 · unverdicted · none · ref 71

    ViGoRL introduces visually grounded RL that anchors reasoning steps to image coordinates and uses multi-turn zooming to outperform standard RL and supervised baselines on spatial and GUI reasoning benchmarks.