arXiv AI
E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
2d ago
Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More
The paper shows that only a small subset of attention heads in vision-language models is responsible for selecting critical visual tokens. By pruning tokens based on similarity before LLM reasoning and then applying head‑aware pruning during reasoning, the proposed ProViP framework achieves high task performance with significant speedups. Experiments on LLaVA‑1.5‑7B demonstrate 95.9% performance retention and a 1.62× inference speedup at an 88.9% pruning ratio.
arXiv Computer Vision
1d ago
Multi-Image Visual Token Pruning in Large Visual Language Models
arXiv:2608.26806v1 Announce Type: new Abstract: With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitiga...
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 Computation and Language
1d ago
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
ET‑Prune is a training‑free framework that dynamically allocates visual token budgets in multimodal large language models based on question‑conditioned evidence. It protects text‑like spatial regions, converts evidence uncertainty into a token floor, and progressively prunes concentrated evidence while retaining diffuse or text‑dense tokens. In six backbone‑benchmark comparisons, ET‑Prune matches or outperforms other pruned methods while keeping roughly half the visual tokens, achieving notable gains on OCRBench‑v2 and MMBench v1.1.
arXiv AI
1d ago
PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.
arXiv AI
Jul 9
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
arXiv:2607. 07033v1 Announce Type: cross Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query.