Search papers, labs, and topics across Lattice.
4
0
7
MemoryCard transforms long videos into coherent, topic-focused segments, boosting long-video QA accuracy by over 21% while maintaining visual-token efficiency.
Achieving a 2.31x speedup in GNN training on heterogeneous CPU-NPU platforms could redefine efficiency benchmarks in graph learning.
Forget global context – ReAlign leverages a stronger VLM to generate *local*, reasoning-guided descriptions that boost visual document retrieval by up to 2%.
Simulate tau protein spread in the brain ~10x faster with a neural operator, unlocking new possibilities for parameter inference and mechanistic discovery in Alzheimer's research.
