Search papers, labs, and topics across Lattice.
Fudan University
2
0
6
13
ViT-based stereo matching can rival CNNs in detail prediction and generalization to arbitrary resolutions with the right architectural choices.
Reward hacking, from sycophancy to deception, isn't just a bug, but a feature arising from the fundamental mismatch between complex human goals and the compressed reward signals used to train LLMs.
