Search papers, labs, and topics across Lattice.
4
0
8
3
SR-JEPA reveals that a predictive pathway can infer missing entity representations in 3D scenes with remarkable accuracy, transforming how we approach latent state learning.
Larger sliding-window attention can paradoxically slow down the formation of critical retrieval mechanisms in language models, challenging conventional design assumptions.
LLMs can significantly enhance their collaborative performance, achieving over 24% better engagement with human partners when trained in realistic game scenarios.
Making interactive video world models real-time just got easier: minWM offers a full-stack, open-source pipeline to convert existing diffusion models into controllable, low-latency generators.
