🔔科技频道[奇诺分享-ccino.org]⚡️
4 天前
量子位
从视觉出发统一多模态！颜水成团队最新研究：不再把图像编解码器塞进LLM｜ICLR'2026
Home
Blog
Discuss
Gsearch
Powered by
BroadcastChannel
&
Sepia
![🔔科技频道[奇诺分享-ccino.org]⚡️](/static/https://cdn5.telesco.pe/file/Q3-c5-Ivq3qGx1QtiLTBWJyXVycuHZkITZ6Y8etxCOuOjc-0EuE6aQUb9we7BKNAkCWi_i-IBjqmPgDPRF2UQWKx5qbMqlOIzf_TSBTus4-_HU0exUMeKg1VaD5ZfJIgaI9Ia9G2DOtQoM4WaWAsQQGNxgpnU6y-ps3fpFuYXg3TtghX081Opqi6wQjT4vmDodZKtjV3boNi1FVWde_PO4jYXReUfubONEAqnkGt9c2EVY8e5e1AUOOUxLbQPGnxzI8408rrY00_FN6OqBbzBq2PVlLomnsvzyoT4Kn9QiNJAOSZhqTnLJwXMe3vl59A522rqKNdhVFPRVChwcecaQ.jpg)
