Zsolt Kira

Pumping capacity into feature cross-networks yields diminishing returns, but harvesting non-shared estimator variance via recursive weight-sharing unlocks state-of-the-art CTR accuracy without standard ensemble deployment overhead.

VLM agents excel at deception, with non-verbal cues playing a surprisingly pivotal role in their success.

Achieving robust sim-to-real transfer, this framework allows robots to learn dexterous skills directly from human videos, outperforming traditional methods.