Search papers, labs, and topics across Lattice.
2
0
4
This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count, and organize methods by the pipeline stage at which they act.
Stop wasting compute on irrelevant video frames: PEEK distills frame selection smarts into a tiny model that boosts captioning accuracy while barely impacting runtime.
