hustvl
/

InfiniteVL

Image-Text-to-Text

feature-extraction

vision-language-model

linear-attention

Model card Files Files and versions

HongyuanTao commited on Dec 6, 2025

Commit

dec35a7

·

verified ·

1 Parent(s): 61c5ab3

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ pipeline_tag: image-text-to-text
 <div align="center">
 <!-- 这里可以放你的Logo，如果没有Logo可以删掉这一行 -->
-<img src="assets/Logo.png" width="500" alt="InfiniteVL Logo">
 <hr>
@@ -51,7 +51,7 @@ Haoran Yin<sup>2</sup>,
 By synergizing **Sliding Window Attention (SWA)** for fine-grained local perception and **Gated DeltaNet** for efficient long-term memory, InfiniteVL achieves a "best of both worlds" balance. It delivers competitive performance on standard benchmarks (comparable to Qwen2.5-VL) while enabling constant-memory inference and high-throughput streaming.
 <div align="center">
-<img src="assets/image1_new_01.png" width="800" alt="InfiniteVL Logo">
 </div>
 ### ✨ Key Highlights

 <div align="center">
 <!-- 这里可以放你的Logo，如果没有Logo可以删掉这一行 -->
+<img src="https://github.com/hustvl/infinitevl/assets/Logo.png" width="500" alt="InfiniteVL Logo">
 <hr>
 By synergizing **Sliding Window Attention (SWA)** for fine-grained local perception and **Gated DeltaNet** for efficient long-term memory, InfiniteVL achieves a "best of both worlds" balance. It delivers competitive performance on standard benchmarks (comparable to Qwen2.5-VL) while enabling constant-memory inference and high-throughput streaming.
 <div align="center">
+<img src="https://github.com/hustvl/infinitevl/assets/image1_new_01.png" width="800" alt="InfiniteVL Logo">
 </div>
 ### ✨ Key Highlights