3d-reasoning

Introduces SpaR3D-MoE, an end-to-end framework for adaptive 3D spatial reasoning from sparse RGB views, using manifold sampling and geometry-inductive mixture-of-experts to achieve state-of-the-art performance on VSI-Bench, ScanQA, and SQA3D.

GauntletBench is a new web-based benchmark that evaluates AI agents on challenging scenarios focusing on temporal perception, graphical understanding, and 3D reasoning. Results show state-of-the-art agents achieve only 19.1% success rate compared to over 80% for non-expert humans, highlighting significant limitations in current agentic systems.

DR-MV3D presents a map-grounded learning framework with dense rewards to improve multi-view 3D visual question answering through global map construction, view-trajectory planning, and egocentric grounding.

The Geometric Action Model (GAM) repurposes a pretrained geometric foundation model (GFM) as a unified backbone for language-conditioned robot manipulation, achieving higher accuracy, robustness, and efficiency than existing foundation-model-scale baselines across simulation and real-world benchmarks.

SpatialClaw is a training-free framework that uses code as an action interface to enable flexible, stateful spatial reasoning in vision-language models, achieving superior performance across diverse 3D/4D spatial reasoning tasks.

MolmoAct 2 is an open robotics model that reasons in 3D space before taking actions, developed by the Allen Institute for Artificial Intelligence.