Jan Kautz

Switching between autoregressive and diffusion modes allows Nemotron-Labs-Diffusion to achieve unprecedented throughput and efficiency in language modeling.

Dynamic token editing in image synthesis could redefine how we approach high-resolution generative models.

A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.

SR-REAL's dual-path reasoning framework allows spatial VLMs to excel in both linguistic deduction and 3D geometric inference, significantly enhancing performance on complex spatial reasoning tasks.

Fine-tuning on the new ProCUA-SFT dataset boosts UI-TARS 7B's performance from a dismal 8-10% to an impressive 45.0% on OSWorld tasks, highlighting the critical role of high-quality training data.

Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.

GRAIL achieves an impressive 84% success rate in real-world object pick-up tasks using only synthetic data, revolutionizing humanoid robot training.

Grounding boosts spatial reasoning in VLMs: explicitly linking language to 2D and 3D scene elements lets models decompose complex spatial problems and improve performance even on non-grounded tasks.

MLLMs can now handle 4K videos up to 100x faster thanks to AutoGaze, which selectively attends to only the most informative patches.