Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
7
0
11
5
Mobile robots can now dynamically place and scale augmented reality projections in real-world environments based solely on language instructions, achieving over 57% success in unseen tasks.
Model selection for scientific forecasting is fundamentally protocol-dependent, with optimal choices reversing based on dataset size, system complexity, and evaluation metrics like state refresh versus closed-loop performance.
Physics-constrained generation now achieves comparable fidelity to multi-step methods in a single neural transport evaluation.
Instruction leakage can lead to misleadingly high accuracy in spatial relation tasks, revealing a critical flaw in goal-conditioned models that could misguide future research.
Achieve comparable or better novel view synthesis with 8x fewer Gaussians by intelligently redistributing points in space.
Project images onto any surface, under any lighting, from any angle, without recalibrating your projector – SIComp just works.
VLMs get confused by spatial augmented reality, but ProCap's two-stage decoupling pipeline and new RGBP dataset could finally let them tell the difference between real and projected objects.