Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking.
arXiv:2609.38823v1 Announce Type: new
Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becau...
By Xudong Tan, Peng Ye, Ming Xie, Chenyu Huang, Yaoxin Yang, Jiayuan Fan, Tao Chen
arXiv:2609.38090v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
By Sanjali Yadav, Bahar Asgari
arXiv:2607. 08029v1 Announce Type: new Abstract: The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence.
By Hyeju Shin, Chorwon Kim, Ryangsoo Kim, Hark Yoo, Jaein Kim
The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.
By David Poblaci\'on-Criado, Dario Garcia-Gasulla, Eduardo Quinones
arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.
By Jusheng Zhang, Xiaoyang Guo, Tongyu Mo, Qinhan Lv, Wenhao Chai, Jian Wang, Keze Wang, Liang Lin
The paper introduces TopoCompress, a token compression framework designed for distributed edge Mixture-of-Experts (MoE) inference. It jointly optimizes token compression, expert deployment, GPU-CPU residency, and routing to reduce cross-server communication and resource usage. The method uses a two-timescale alternating optimization, with an online loop compressing low-importance tokens and an offline loop updating expert placement based on accumulated traffic.
By Ning Li, Xinyu Wang, Xin Yuan, Wenchao Xu, Athanasios V. Vasilakos, Song Guo, Haijun Zhang
The paper introduces Q-TOFC, a query‑guided task‑oriented visual feature compression method that uses residual vector quantization to encode merged features as compact codebook index sequences. By incorporating query relevance into feature aggregation and adding a quantization error compensation adapter, Q‑TOFC reduces visual payload by 53.6% compared to previous TOFC while preserving task performance. Experiments across seven multimodal benchmarks and latency tests confirm its effectiveness under bandwidth‑constrained uplinks.
By Luning Pang, Cheng Yuan, Jiawei Shao, Mingtao Huang, Yuan Shen
arXiv:2608.29291v1 Announce Type: new
Abstract: Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generati...
By Wengyi Zhan, Chenqian Yan, Songwei Liu, Mingbao Lin, Rongrong Ji
arXiv:2606. 17118v1 Announce Type: cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE-MLLMs) offer remarkable performance but incur prohibitive GPU memory costs, making compression essential.
By Yuanteng Chen, Peisong Wang, Zhilei Liu, Nanxin Zeng, Yuantian Shao, Shiqiang Lang, Tao Liu, Chuangyi Li, Qinghao Hu, Gang Li, Jing Liu, Jian Cheng
arXiv:2609.37831v1 Announce Type: new
Abstract: Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise gene...
By Xijun Wang, Xin Li, Suhang Yao, Zirui Lang, Bingchen Li, Zhibo Chen
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...