Modern vision models have achieved remarkable success in benchmarks where local features provide critical information about the target. There is now a growing interest in tackling tasks requiring more global reasoning, where local features do not provide significant information. Minsky and Papert put forward such tasks in 1969 with their connectivity study, exposing the limitations of the perceptron model. In this paper, we introduce an expanded set of global visual datasets involving graphs, strings, mazes, and image grids. We show that large vision models still struggle to learn these tasks… Read More
Chain-of-Sketch: Enabling Global Visual Reasoning
Modern vision models have achieved remarkable success in benchmarks where local features provide critical information about the target. There is now a growing interest in tackling tasks requiring more global reasoning, where local features do not provide significant information. Minsky and Papert put forward such tasks in 1969 with their connectivity study, exposing the limitations of the perceptron model. In this paper, we introduce an expanded set of global visual datasets involving graphs, strings, mazes, and image grids. We show that large vision models still struggle to learn these tasks…
Related Posts
Switchboard-Affect: Emotion Perception Labels from Conversational Speech
Understanding the nuances of speech emotion dataset curation and labeling is essential for assessing speech…
Top 5 Agentic AI LLM Models
In 2025, “using AI” no longer just means chatting with a model, and you’ve probably…
FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models
Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token…