arXiv Computer Vision
S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
2d ago
SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models
arXiv:2609.01004v1 Announce Type: cross Abstract: Despite their strong multimodal understanding ability, multimodal large language models (MLLMs) incur substantial computational overhead when process...
arXiv Computer Vision
Aug 28
Multi-Image Visual Token Pruning in Large Visual Language Models
The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.
arXiv AI
Aug 25
E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models
arXiv:2608.23253v1 Announce Type: cross Abstract: Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Exi...
arXiv AI
Aug 10
RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
arXiv:2608. 07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive.
arXiv AI
Jun 26
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
arXiv:2606. 27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead.
arXiv Machine Learning
Aug 21
Clustering and Token Denoising for Faster and More Robust VLMs
arXiv:2608. 19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results.