Search papers, labs, and topics across Lattice.
7
0
7
Physics-informed priors in reinforcement learning can drastically enhance the robustness of in-hand manipulation, leading to more efficient and stable robotic control.
CuRe transforms video captioning reward design by shifting from holistic evaluations to precise claim-level verification, significantly boosting factual accuracy and diversity in generated captions.
Embedding geometric intelligence into segmentation models can dramatically enhance the recovery of small vascular structures and improve overall topology fidelity.
Achieving state-of-the-art identity fidelity and temporal stability, TIGER redefines the standards for high-quality face video restoration.
Top algorithms in the HECKTOR 2025 challenge achieved impressive segmentation and survival prediction metrics, showcasing the power of multimodal imaging in oncology.
Skill-augmented AI agents may enhance the quality of biomedical research outputs, but the improvement is subtle and requires further validation.
Achieve verifiable clinical interpretation by grounding radiology reports to 3D CT volumes with a novel graph-guided lesion grounding framework that outperforms existing multimodal foundation models.
