Allen Institute for AI (AI2)

SC3-Eval achieves a remarkable 0.929 Pearson correlation in evaluating robot policies, revealing critical insights into their real-world performance.

Torque Adaptation Module enables zero-shot robust manipulation across different robots without the need for extensive retraining or domain randomization.

Today's robot policies and VLAs fall apart when faced with unexpected challenges requiring reasoning, strategy adaptation, and robustness, even after fine-tuning on similar tasks.

Forget training on closed sets: WildDet3D leverages geometric cues and diverse prompts to achieve SOTA 3D object detection across 13.5K categories in the wild.

Forget expensive real-world data collection: a massive, diverse synthetic dataset enables surprisingly effective zero-shot transfer for robotic manipulation.

Forget synthetic benchmarks that don't translate: MolmoSpaces offers 230k diverse, simulator-agnostic environments with 130k annotated objects, showing a remarkable 0.96 sim-to-real correlation for robot policies.

Robot foundation models can achieve state-of-the-art performance by explicitly reasoning about spatial plans as editable trajectory traces, rather than directly mapping perception to control.