Ranjay Krishna

Current vision-language models fail to achieve embodied self-awareness, with none surpassing a 16.8% success rate in real-world interaction tasks.

Achieving state-of-the-art performance in 3D motion forecasting, MolmoMotion reveals that language instructions can significantly enhance trajectory predictions across various object categories and motion types.

Open-sourcing a VLA model that beats closed-source giants on embodied reasoning tasks could finally make real-world robot deployment practical.

Open-source web agents can now outperform GPT-4o on key web navigation tasks, thanks to a new dataset and model family that levels the playing field.

Pruning vision tokens across both the ViT and LLM can yield a 62% efficiency boost in video VLMs with minimal performance loss, and without complex text conditioning.

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

Unlock robot learning with hidden knowledge: TOPReward extracts surprisingly accurate task progress signals directly from VLM token probabilities, bypassing the need for explicit reward engineering.

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.