From 8803ec81112a3b39f7fa7ba619ed527acd0cc07e Mon Sep 17 00:00:00 2001
From: Yankai_Yang <99643270+YourYongKing@users.noreply.github.com>
Date: Mon, 25 May 2026 23:57:17 +0800
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index bd373b8..381e8b0 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@
 ## 🔥 News
 
 
-* **`2026.05.25`** 🌟 We are excited to introduce Keye-VL-2.0-30B-A3B, the latest 30B-class flagship in the Keye series. Powered by DSA for long-video understanding, it delivers nearly lossless reasoning over 256K ultra-long context, tops video benchmarks at its scale, rivals top closed-source models on fine-grained temporal perception, and ships with built-in Agent capabilities across Search, Tool, and Code.
+* **`2026.05.25`** 🌟 We are excited to introduce **Keye-VL-2.0-30B-A3B**, the latest 30B-class flagship in the Keye series. Powered by DSA for long-video understanding, it delivers nearly lossless reasoning over 256K ultra-long context, tops video benchmarks at its scale, rivals top closed-source models on fine-grained temporal perception, and ships with built-in Agent capabilities across Search, Tool, and Code.
 * **`2025.11.20`** 🌟 We are excited to introduce **Keye-VL-671B-A37B**, the most powerful multi-modal language model in the Keye series to date. We further upgraded the data engineering and training strategies for both pre-training and post-training. Keye-VL-671B-A37B demonstrates top-tier and in some cases even leading performance in text understanding and generation, complex visual perception and reasoning, comprehensive video understanding, and Olympic-level mathematical reasoning.
 * **`2025.09.01`** 🌟 **Kwai Keye-VL 1.5 Technical Report** is now available at [arxiv](https://arxiv.org/abs/2509.01563).  
 * **`2025.08.28`** 🌟 We are excited to introduce **Kwai Keye-VL 1.5**, a more powerful version! By incorporating innovative `Slow-Fast Video Encoding strategy`, `new LongCoT Cold-Start data pipeline`, and `advanced RL training strategies`, Keye-VL-1.5 reaches new heights in video understanding, image comprehension, and reasoning capabilities. Plus, it now supports an extended context length of up to **128k** tokens for handling longer conversations and complex tasks. Stay tuned for more groundbreaking innovations!