Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

Hugging Face Daily Papers Papers

Summary

This survey examines inference-efficiency techniques for video large language models, analyzing cost reductions across frame sampling, encoding, token compression, and language model stages while identifying evaluation gaps.

Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and condition generation on a textual prompt. Their strong performance on captioning, question answering, retrieval and temporal grounding comes at a computation and memory cost that grows with frame count and context length, limiting deployment in real-time, mobile and resource-constrained settings. 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. We analyze bottlenecks across frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding. We organize methods by the pipeline stage at which they act, covering VideoLLMs developed since late 2022 together with earlier frame-sampling and vision-encoder mechanisms that remain components of current pipelines. We assemble literature-reported accuracy--cost comparisons under shared host models and input protocols wherever available, distinguish them from heterogeneous cross-paper evidence, and identify gaps in audiovisual efficiency and standardized evaluation. We maintain a repository at https://github.com/momentslab/awesome-efficient-videollm.
Original Article
View Cached Full Text

Cached at: 09/10/26, 10:10 AM

Paper page - Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

Source: https://huggingface.co/papers/2609.10355

Abstract

This survey examines inference-efficiency techniques for video large language models, analyzing cost reductions across frame sampling, encoding, token compression, and language model stages while identifying evaluation gaps.

Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and condition generation on a textual prompt. Their strong performance on captioning, question answering, retrieval and temporal grounding comes at a computation and memory cost that grows with frame count and context length, limiting deployment in real-time, mobile and resource-constrained settings. This survey coversinference-efficiencymechanisms for visual andaudiovisual VideoLLMsthat report concrete reductions in parameter count,FLOPsper input, latency, memory, or visual and audio token count. We analyze bottlenecks acrossframe sampling,modality encoding,connector-level token reduction, andLLM prefillinganddecoding. We organize methods by the pipeline stage at which they act, coveringVideoLLMsdeveloped since late 2022 together with earlier frame-sampling and vision-encoder mechanisms that remain components of current pipelines. We assemble literature-reported accuracy--cost comparisons under shared host models and input protocols wherever available, distinguish them from heterogeneous cross-paper evidence, and identify gaps in audiovisual efficiency and standardized evaluation. We maintain a repository at https://github.com/momentslab/awesome-efficient-videollm.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2609\.10355

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.10355 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.10355 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.10355 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

LiteFrame Scales Video LLM Efficiency (6 minute read)

TLDR AI

LiteFrame introduces a highly efficient video encoder for Video LLMs that uses Compressed Token Distillation to enable up to 8x more frames and 35% latency reduction while maintaining accuracy, setting a new Pareto frontier for long-form video understanding.

LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?

Hugging Face Daily Papers

This paper introduces LLaVA-UHD v4, which improves visual encoding efficiency in multimodal large language models by using slice-based encoding and intra-ViT early compression. It reduces computational costs by over 55% while maintaining or improving performance on high-resolution image tasks.