Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,9 @@ tags:
|
|
| 17 |
|
| 18 |
Keye-VL-1.5 is a cutting-edge Multimodal Large Language Model (MLLM) that addresses fundamental challenges in video comprehension. It features a novel Slow-Fast video encoding strategy, a progressive four-stage pre-training methodology to extend context length up to 128K tokens, and a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment. The model demonstrates significant improvements in video understanding tasks and maintains competitive performance on general multimodal benchmarks.
|
| 19 |
|
| 20 |
-
<font size=3><div align='center' >
|
|
|
|
|
|
|
| 21 |
[[π Home Page](https://kwai-keye.github.io/)]
|
| 22 |
[[π Technical Report](https://arxiv.org/abs/2509.01563)]
|
| 23 |
[[π» GitHub Repository](https://github.com/Kwai-Keye/Keye)]
|
|
|
|
| 17 |
|
| 18 |
Keye-VL-1.5 is a cutting-edge Multimodal Large Language Model (MLLM) that addresses fundamental challenges in video comprehension. It features a novel Slow-Fast video encoding strategy, a progressive four-stage pre-training methodology to extend context length up to 128K tokens, and a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment. The model demonstrates significant improvements in video understanding tasks and maintains competitive performance on general multimodal benchmarks.
|
| 19 |
|
| 20 |
+
<font size=3><div align='center' >
|
| 21 |
+
[[π X](https://x.com/KwaiKeye)]
|
| 22 |
+
[[π¬ Discord](https://discord.gg/4Q6AmzxpEK)]
|
| 23 |
[[π Home Page](https://kwai-keye.github.io/)]
|
| 24 |
[[π Technical Report](https://arxiv.org/abs/2509.01563)]
|
| 25 |
[[π» GitHub Repository](https://github.com/Kwai-Keye/Keye)]
|