Search papers, labs, and topics across Lattice.
3
0
5
0
Even the best audio-video generators struggle with basic acoustic principles, revealing a critical gap in their performance.
Zero-robot post-training on high-fidelity UMI data achieves real-world performance that rivals traditional teleoperation methods, revolutionizing data efficiency in robotic manipulation.
Conditional mixup bridges the gap between pseudo-labeling and contrastive learning, setting a new benchmark in sound event detection performance.
