Search papers, labs, and topics across Lattice.
Institute of Information Engineering, Chinese Academy of Sciences;
3
0
4
Compact evidence masks can achieve up to 96% repair rates in MLLM tasks, proving that less can be more in visual attribution.
PhaseWin slashes the computational cost of visual attribution from quadratic to linear while preserving high faithfulness, revolutionizing how we interpret model decisions.
By harnessing rotational symmetry, this method achieves pose estimation accuracy comparable to traditional techniques, even in the absence of 3D models.
