Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation
Read the original on arXiv Computer Vision →The paper surveys training‑free methods to accelerate inference in Video Large Language Models (VLMs), aiming to reduce computational, latency, and memory costs while retaining task‑relevant spatiotemporal evidence. It categorizes techniques by their intervention points in the inference pipeline—input, visual encoding, projector, prefill, and decoding—and discusses post‑training quantization as a cross‑stage approach. The authors analyze how the position of each intervention influences evidence preservation and computational savings, noting that local efficiency gains may not lead to overall acceleration, and they provide quantitative comparisons from prior work and new experiments to evaluate accuracy‑latency trade‑offs.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.