Search papers, labs, and topics across Lattice.
Affiliation:
2
0
6
Instead of forcing entire videos into a single, lossy feed-forward context, training an agent to actively read and write temporal memory yields 78.8% accuracy on MINERVA with virtually zero performance drop on long-duration clips.
A novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment, and substantially improves safe success rates compared to state-of-the-art VLM-driven task planners.
