Search papers, labs, and topics across Lattice.
University of Toronto and Vector Institute, University of Hong Kong
2
0
2
Black-box optimization can now safely leverage noisy, low-cost gradient approximations to bridge the gap between $O(d/T)$ zeroth-order and $O(1/T)$ first-order rates without stalling when guidance fails.
Minimizing distortion, not maximizing codebook utilization, is the key to achieving superior reconstruction fidelity in visual tokenization.
