Search papers, labs, and topics across Lattice.
AInnovation Co. Ltd.
5
1
8
5
Dynamically adjusting visual importance at test time can significantly enhance action prediction accuracy in VLA models.
Cultural competence in language models is more about pre-training exposure than multilingual fluency, revealing a critical gap in AI's understanding of cultural nuances.
Current AI agents struggle with long-horizon professional tasks, achieving only 30% success in complex GUI workflows, revealing critical gaps in their capabilities.
Humanoid robots can now learn complex loco-manipulation skills in diverse real-world environments by watching humans, achieving a 51% performance boost over robot-only training.
Achieve 2.5x higher success in long-horizon robotic manipulation with 90% less data and compute by explicitly aligning training and deployment distributions.
