# Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression

arXiv: https://arxiv.org/abs/2511.18504 · HTML: https://mlsanity.com/paper/2511.18504/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 13 of 13)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [Learned Token Pruning for Transformers](https://mlsanity.com/paper/2107.00910/) (2021)

## Abstract (arXiv)

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal Token Fusion (STTF) and Adaptive Neural Compression (ANC) -- that integrate algorithmic innovations with hardware-aware optimizations. Unlike previous approaches relying on static pruning or uniform scaling, STTF dynamically reuses visual tokens through event-driven change detection, while ANC conditionally activates encoder branches via a learned router, enabling fine-grained adaptation to scene complexity. Our 3B-parameter TinyGPT-STTF achieves CIDEr 131.2, BLEU-4 0.38, METEOR 0.31, and ROUGE-L 0.56 on the COCO 2017 test set, surpassing LLaVA-1.5 7B by 17.6 CIDEr points while using 2.3x fewer parameters and 62x fewer on-device FLOPs. TinyGPT-ANC reaches CIDEr 128.5. On event-based vision tasks, STTF reduces average token count by 84% (from 196 to 31 tokens) while preserving 95.6% accuracy on the DVS128 Gesture dataset, and ANC cuts FLOPs by up to 90% in low-motion scenes. Compared to strong baselines, our models improve accuracy by up to 4.4% and reduce latency by up to 13x. These results enable efficient deployment of capable vision-language models on real-world edge devices.