Search papers, labs, and topics across Lattice.
University of East Anglia
4
0
7
Embedding equivariance in hyperbolic networks can drastically accelerate convergence and reduce parameter redundancy, reshaping how we approach visual representation learning.
Negation sensitivity in VLMs can be dramatically improved without sacrificing performance on standard tasks, thanks to a novel geometric approach.
Confidence-based filtering can cut prediction error by over 65%, revealing a new approach to managing uncertainty in emissions monitoring for gas turbines.
Forget complex, multi-stage pruning pipelines: HiAP slashes Vision Transformer size with a single, end-to-end training pass that optimizes sparsity at multiple granularities.
