Search papers, labs, and topics across Lattice.
Affiliation:
2
0
6
This work proposes Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework that turns visual access into a first-class, query-conditioned cost, capping per-query frame consumption regardless of video length.
By stitching together the best reasoning steps from multiple diffusion-generated trajectories, this method achieves significant accuracy gains and latency reductions in math and coding tasks, outperforming traditional diffusion models and unified architectures.
