Search papers, labs, and topics across Lattice.
3
0
6
12
HarnessWAM allows robots to recover from failures and maintain knowledge across tasks, achieving unprecedented success rates in complex embodied environments.
Retaining nearly all of a model's capability while slashing visual token usage by over 80% reveals a transformative approach to VLM compression.
Decoupling masked reconstruction and contrastive alignment in audio-visual representation learning yields surprisingly large gains in zero-shot retrieval, outperforming SOTA by a significant margin.
