Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
By: Tianfan Peng , Yuntao Du , Pengzhou Ji and more
Potential Business Impact:
Makes AI understand pictures faster and better.
Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in reducing redundancy, their evaluation remains fragmented and inconsistent. In this work, we present UniPruneBench, a unified and extensible benchmark for visual token pruning in multimodal LLMs. UniPruneBench provides standardized protocols across six ability dimensions and ten datasets, covering ten representative compression algorithms and three families of LMMs (LLaVA-v1.5, Intern-VL3, and Qwen2.5-VL). Beyond task accuracy, it incorporates system-level metrics such as runtime and prefilling latency to provide a holistic view. Our experiments uncover several key findings: (1) random pruning is a surprisingly strong baseline, (2) no single method consistently outperforms others across scenarios, (3) pruning sensitivity varies significantly across tasks, with OCR being most vulnerable, and (4) pruning ratio is the dominant factor governing performance degradation. We believe UniPruneBench will serve as a reliable foundation for future research on efficient multimodal modeling.
Similar Papers
Towards Adaptive Visual Token Pruning for Large Multimodal Models
CV and Pattern Recognition
Makes AI understand pictures faster and cheaper.
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
CV and Pattern Recognition
Cuts 93% image junk to keep AI sharp
Towards Lossless Ultimate Vision Token Compression for VLMs
CV and Pattern Recognition
Makes AI understand pictures much faster.