Search papers, labs, and topics across Lattice.
5
0
6
Natural-language instructions can now handle both zero-shot speech synthesis and surgical acoustic editing within a single unified model, operating at 4-step distilled inference speeds without classifier-free guidance.
Achieving a 3.36-fold speedup in action generation, DriftingVLA eliminates the need for iterative refinement while maintaining high performance in robot control tasks.
Scope3Trace achieves high accuracy in extracting Scope 3 emissions data while providing transparent evidence grounding, revolutionizing how we analyze corporate carbon footprints.
HoliDubber revolutionizes video dubbing by seamlessly integrating speech and sound effects from a single text prompt, outperforming traditional methods in quality and synchronization.
Recovering static 3D scenes from monocular video with dynamic objects gets a boost: GA-GS leverages diffusion models to inpaint occluded regions, outperforming existing methods, especially in scenarios with large-scale occlusions.
