Publication Radar · Source metadata
Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First announced by arXiv: 2026-10-28 · Indexed by Pub-AI: 2026-10-28 UTC
Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation
First announced by arXiv: 2026-10-28 · Original record ↗
- arxiv
- 2610.36327
Explicit source versions (1)
- v1 · Date not supplied
- Preprint available
Source date: 2026-10-28 · First detected: 2026-10-28 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · RSS guid=oai:arXiv.org:2610.36327v1; arxiv:announce_type=new; item pubDate (official metadata)
Abstract · arxiv
Video Large Language Models (VLMs) have demonstrated strong capabilities in video understanding and reasoning, but processing long visual sequences incurs substantial computational, latency, and memory overhead. This survey examines training-free inference acceleration, focusing on reducing inference costs while preserving task-relevant spatiotemporal evidence. We organize existing methods by their intervention stages in the inference pipeline, covering input, visual encoding, projector, prefill, and decoding. Post-training quantization (PTQ) is discussed separately as a cross-stage extension with varying calibration requirements. We analyze how intervention position affects evidence preservation and computational savings, and why local efficiency improvements may not translate into end-to-end acceleration. We complement this analysis with quantitative evidence from prior studies and our own experiments under a shared evaluation setting to assess accuracy-latency trade-offs.