Search papers, labs, and topics across Lattice.
Affiliation:
5
0
9
Achieving rapid earthquake magnitude estimation with a single station, SeisMamba outperforms traditional models in both speed and accuracy, even in unseen regions.
Iterative reinforcement learning with human feedback transforms robot gestures from stiff and unnatural to fluid and expressive, revolutionizing human-robot communication.
Unlock zero-shot human motion understanding across diverse wearable IMU setups with AnyMo, a geometry-aware framework that bridges the gap between synthetic data and real-world deployment.
Continuous-depth transformers, augmented with physics-informed loss, can significantly improve short-term weather forecasting, suggesting a promising path for hybrid physics-aware AI models.
General-purpose LLMs stumble on domain-specific RAG, but a model trained on just 6.5K synthetic examples closes the gap and slashes hallucinations almost in half.
