Search papers, labs, and topics across Lattice.
3
0
8
Even state-of-the-art VLMs exhibit systematic failures in reasoning about the physical feasibility of actions in 3D environments, despite high semantic confidence.
Retrieval augmentation lets head avatars handle novel expressions better by mixing in similar expressions from a large unlabeled dataset during training, boosting generalization without extra labels or architecture changes.
Test-time training with KV binding isn't memorization, it's secretly a learned linear attention mechanism, unlocking architectural simplifications and parallelization.
