SpatiaLab is a new test that checks if vision-language models (VLMs) can understand real-world spatial puzzles, like what’s in front, behind, bigger, or reachable.
This paper teaches AI to copy the hidden idea inside a picture (a visual metaphor) and reuse that idea on a brand‑new subject.
The paper introduces M^4olGen, a two-stage system that designs new molecules to match exact numbers for several properties (like QED, LogP, MW, HOMO, LUMO) at the same time.
TourPlanner is a travel-planning system that first gathers the right places, then lets multiple expert ‘voices’ debate plans, and finally polishes the winner with a learning method that follows rules before style.
LongVideoAgent is a team of three AIs that work together to answer questions about hour‑long TV episodes without missing small details.
This paper builds a math problem–solving agent, Intern-S1-MO, that thinks in multiple rounds and remembers proven mini-results called lemmas so it can solve very long, Olympiad-level problems.