← Back to all news
arXiv Computer Vision By Shicheng Yin, Kaixuan Yin, Yang Liu, Weixing Chen, Liang Lin

DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models

Read the original on arXiv Computer Vision →

DART is a fully differentiable Dynamic Adaptive Region Tokenizer that replaces fixed‑grid tokenizers in vision models. It uses learnable region scores and quantile‑based partitioning to create content‑aware patches of varying sizes, allocating more tokens to information‑rich areas. In experiments, a DART‑equipped DeiT‑Small matches the performance of a larger DeiT‑Base while nearly doubling inference speed, and the approach also benefits dense prediction and video tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Oct 7

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.

By Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang, Jin Xu, Xike Xie
llmsefficiencymultimodalbenchmarks
More like this →
arXiv AI
2d ago

Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers

The paper introduces Split Policy Learned Image Tokenization (SPLIT), a method that learns to allocate token resolution based on the model’s interpretation of task-relevant information rather than raw pixel statistics. SPLIT produces shorter token sequences while matching the accuracy of full-resolution Vision Transformers on classification tasks, and it also achieves competitive performance on dense prediction benchmarks such as COCO and ADE20K.

By Aditya Gupta, Jean Sebastien Dandurand, Kai Qiu, Rohan Choudhury, Laszlo A. Jeni
llmsnlp
More like this →
Hugging Face Trending Papers
Aug 3

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.

llmsmultimodalbenchmarkssafety
More like this →