Search papers, labs, and topics across Lattice.
6
0
9
0
Results show that fingertip-aligned visual force representations can be effectively used for force-aware conditioning in VLA-based dexterous hand manipulation.
DCGC corrects flawed reasoning in LLMs by leveraging imperfect drafts, leading to significant accuracy improvements in complex reasoning tasks.
Mechanistic control over data generation reveals hidden model dynamics, leading to more diverse and effective datasets that enhance downstream performance.
RadLoc achieves unprecedented speed and robustness in radar-based global localization, outperforming state-of-the-art methods while using the smallest descriptor size.
Ditch RL's single-solution rut: QFlowNet leverages Generative Flow Networks to discover a diverse set of high-performing quantum circuits for unitary synthesis.
Task-aware attention slashes compute in robot VLA models by adaptively routing visual inputs based on relevance, boosting efficiency without sacrificing control performance.
