paper-with-me

Papers

Inference Compute-Optimal Video Vision Language Models

2025-05-24 · Peiqi Wang, Shengyun Peng, Xuewen Zhang, Hanchao Yu, Yibo Yang, Lifu Huang, Fujun Liu, Qifan Wang

This work investigates the optimal allocation of inference compute across three key scaling factors in video vision language models: language model size, frame count, and the number of visual tokens per frame. While prior works typically focuses on optimizing model efficiency or improving performance without considering resource constraints, we instead identify optimal model configuration under fixed inference compute budgets. We conduct large-scale training sweeps and careful parametric modeling of task performance to identify the inference compute-optimal frontier. Our experiments reveal how task performance depends on scaling factors and finetuning data size, as well as how changes in data size shift the compute-optimal frontier. These findings translate to practical tips for selecting these scaling factors.

📄 PDF Abstract BibTeX arXiv:2505.18855

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Towards Precise Scaling Laws for Video Diffusion Transformers

2024-11-25 · CVPR 2025 1 · Yuanyang Yin, Yaqi Zhao, Mingwu Zheng, Ke Lin 외

Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training …

Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models

2026-08-17 · Ruchen Liu, Yi Yang, Yiming Xu, Michael Ying Yang 외 arxiv

LLaVA-style Vision-Language Models (VLMs) pass visual tokens from a fixed late layer of the vision backbone, typically the penultimate one, to the language model. We first show that this hidden convention is fragile: acr…

Task Oriented Video Coding: A Survey

2022-08-15 · Daniel Wood

Video coding technology has been continuously improved for higher compression ratio with higher resolution. However, the state-of-the-art video coding standards, such as H.265/HEVC and Versatile Video Coding, are still d…

Survey

Breaking the Encoder Barrier for Seamless Video-Language Understanding

2025-03-24 · Handong Li, Yiyuan Zhang, Longteng Guo, Xiangyu Yue 외

Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational c…

DecoderLanguage ModelingLanguage ModellingRepresentation Learning+1

Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks

2021-09-27 · Abhinav Goel, Caleb Tung, Xiao Hu, George K. Thiruvathukal 외

Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on lo…