MindTopo reveals VLMs’ spatial reasoning abilities

·Microsoft Research··

At a glance MindTopo is a new benchmark for testing topological reasoning in AI, evaluating whether multimodal models can understand concepts such as connectivity, enclosure, order, separation, and knots. The benchmark measures both reasoning and planning, testing not only whether models can recognize topological relationships in static images but also whether they can preserve and manipulate those relationships through a sequence of actions. Current multimodal models perform much better on stat...

Read full article →

Related Articles

Study: Claude, ChatGPT Offer Different Shopping Prices Based on Wealth
sbulaev · Hacker News · 1h ago
OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 5mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 5mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 5mo ago
OpenAI just dropped 700 preprints of mathematical proofs and counterexamples
tootie · Hacker News · 17h ago