Search papers, labs, and topics across Lattice.
3
0
6
Achieve state-of-the-art character consistency in story visualization with a surprisingly lightweight framework that adds only 149K parameters.
Attention weights in VLMs can fool you: Simpson's paradox hides the true signals of object hallucination, but a new Bayesian method, HaloProbe, can see through the noise.
Forget tedious hyperparameter tuning: this spectral approach lets you transfer learning rates across model sizes for optimizers like AdamW and LAMB, making large-scale training far more efficient.
