Update README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ MMDocRAG is built for (i) multimodal document retrieval and (ii) retrieval-augme
|
|
27 |
|
28 |
|
29 |
|
30 |
-
|
31 |
<p align="center">
|
32 |
<h2 align="center">MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents</h2>
|
33 |
<p align="center">
|
@@ -64,13 +64,13 @@ both training and evaluation. Through rigorous experiments, we demonstrate that
|
|
64 |
|
65 |
|
66 |
|
67 |
-
|
68 |
<p align="center">
|
69 |
<h2 align="center">MMDocRAG: Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering</h2>
|
70 |
<p align="center">
|
71 |
-
<strong>Kuicai Dong
|
72 |
路
|
73 |
-
<strong>Yujing Chang
|
74 |
路
|
75 |
<strong>Shijie Huang</strong>
|
76 |
路
|
@@ -95,7 +95,7 @@ moderate advantages over text-only models, while open-source alternatives trail
|
|
95 |
</a>
|
96 |
<br>
|
97 |
|
98 |
-
|
99 |
|
100 |
|
101 |
|
|
|
27 |
|
28 |
|
29 |
|
30 |
+
---
|
31 |
<p align="center">
|
32 |
<h2 align="center">MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents</h2>
|
33 |
<p align="center">
|
|
|
64 |
|
65 |
|
66 |
|
67 |
+
---
|
68 |
<p align="center">
|
69 |
<h2 align="center">MMDocRAG: Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering</h2>
|
70 |
<p align="center">
|
71 |
+
<strong>Kuicai Dong*</strong></a>
|
72 |
路
|
73 |
+
<strong>Yujing Chang*</strong>
|
74 |
路
|
75 |
<strong>Shijie Huang</strong>
|
76 |
路
|
|
|
95 |
</a>
|
96 |
<br>
|
97 |
|
98 |
+
---
|
99 |
|
100 |
|
101 |
|