Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
6
0
5
14
Machine-learned "biological age clocks" may be tracking statistical artifacts rather than actual physiological decline, as regression to the mean skews systematically stronger in unhealthy individuals.
Achieving fully supervised segmentation accuracy with only 0.7% of the training data labeled could revolutionize OCT image analysis.
Evaluator quality for robotic policies hinges more on long-horizon consistency than on short-term visual fidelity, reshaping our approach to world model design.
Treating raw visual images as action representations revolutionizes embodied control, outperforming traditional methods in accuracy and generalization.
Even with partial observability from manipulator truncation, StableIDM recovers stable action predictions, boosting downstream VLA real-robot success by 17.6%.