Search papers, labs, and topics across Lattice.
5
1
6
4
FlashDrive slashes VLA inference latency by 4.7x while maintaining accuracy, making real-time autonomous driving feasible with a single GPU.
IDNet not only sets a new benchmark for IHD screening but also reveals that effective fusion of multimodal data can dramatically enhance diagnostic performance.
OmniCoT recalibrates the challenges of panoramic reasoning, enabling MLLMs to leverage global evidence for complex multi-step inference.
Existing affordance prediction models fall flat when confronted with the wide-angle, distorted reality of panoramic vision, but a new training-free pipeline called PAP rises to the challenge.
Pre-trained video diffusion models can be deterministically adapted into state-of-the-art zero-shot depth estimators, sidestepping the need for massive labeled datasets.
