Search papers, labs, and topics across Lattice.
3
0
9
2
Stop wasting compute on suboptimal HLS design space exploration: SoberDSE learns to pick the best algorithm for your specific hardware architecture problem, boosting performance by up to 5.7x.
Diffusion models can learn surprisingly generalizable anatomical representations from unlabeled MRI data, enabling accurate multi-task diagnosis and segmentation across different joints and imaging conditions, even with limited labeled data.
Forget static agent communication graphs: AgentConductor uses RL to dynamically rewire agent interactions based on task difficulty, slashing token costs by up to 68% while boosting code generation accuracy.
