Search papers, labs, and topics across Lattice.
2
0
5
d-OPSD enables dLLMs to learn from their own future outputs, drastically improving sample efficiency and performance in reasoning tasks.
Navigate faster and cheaper: SFCo-Nav cuts VLN token consumption by 50% and speeds up execution by 3.5x by intelligently triggering a slow LLM only when a fast reactive navigator loses confidence.
