Search papers, labs, and topics across Lattice.
5
0
6
1
Personalizing image enhancement without sharing user photos is now feasible, thanks to a federated approach that balances aesthetic preferences and image fidelity.
SciFigAlign achieves a remarkable 59% reduction in error over traditional LLM-based scoring methods by grounding figure assessments in manuscript context.
Achieving a 22.3% word error rate with just 240 ms latency, LipsFlow redefines the capabilities of Visual Speech Recognition in challenging multi-speaker environments.
FracEvent achieves superior event timing and downstream performance by accurately modeling pixel dynamics, outperforming traditional simulators.
Neuromorphic event cameras can unlock a new level of expressiveness in speech generation, capturing subtle emotional nuances missed by traditional RGB-based methods.
