🎥 Pre-ICCV Mixer: Bridging Vision, Generation, and Imagination (20 seats)

​📢 SF湾区 Pre-ICCV Mixer，共同交流探讨 多模态 MLLM / VLM / VLA / MediaGen（Image/Video）最新进展与趋势

​主题：【多模态(MLLM/VLM) | MediaGen(Image/Video) | VLA】

​📑 Agenda： 【2–4pm】3–5个 Paper Lightning Talk（已确认3篇） 【4–5pm】自我介绍 & Networking

​

​Confirmed Speaker & Topics：

• ​Enze Xie @Nvidia -【VideoGen】SANA-Video：https://arxiv.org/abs/2509.24695

• ​Zhengzhong Tu @TAMU - 4K Image Agent（4kagent.github.io）

• ​Google DeepMind team - MediaGen Topic (tbd)

​

​（因为名额有限，我们会优先考虑和主题背景更相关的同学）

​

​About the Event

​As the world’s top minds in computer vision gather for ICCV 2025, we’re bringing together a small, hand-picked group of CV Researchers — from ICCV paper award winners to video and image generation experts, and cross-disciplinary creators working at the intersection of AI, art, and design.

​The Pre-ICCV Mixer is an intimate salon for deep conversation, creative exchange, and collaboration. This is not a typical networking event — it’s a convergence of ideas and people shaping the next frontier of visual intelligence.