Search papers, labs, and topics across Lattice.
Renmin University of China, Beijing Academy of Artificial Intelligence
2
0
4
Dedicated memory architectures for VLAs are largely obsolete: feeding intact video history directly into modern backbones beats complex retrieval and compression mechanisms by a wide margin while prefix caching keeps latency at single-frame speeds.
LLM agents are stuck in local adjustment loops, unable to adapt their training strategies despite having the resources to do so.
