Search papers, labs, and topics across Lattice.
4
0
5
2
Humanoid robots can now execute sign language with reduced collisions and enhanced motion fidelity, thanks to innovative collision-mitigation techniques and vision-language integration.
Joint residual reweighting allows for enhanced speaker fidelity in zero-shot TTS while maintaining text accuracy, challenging the conventional trade-offs in guidance methods.
Fast-SDE achieves accurate sound source distance estimation using just a single microphone, overcoming the limitations of traditional multi-microphone setups.
Forget federated learning, bioacoustic classifiers can be unified across 661 species by simply averaging independently trained task vectors, unlocking a collaborative, privacy-preserving paradigm.
