Media Coverage

Selected media reports and articles about my research work.

Foundation Models & Vision

1. 全面超越ViT，美团、浙大等提出视觉任务统一架构VisionLLAMA

   VisionLLaMA: A unified architecture for vision tasks that surpasses ViT

2. 端侧实时运行、3B媲美7B！美团、浙大等提出MobileVLM V2：更快、更强的端侧视觉语言模型

   MobileVLM V2: Faster and stronger mobile vision language model

3. 骁龙888实时运行，美团、浙大等打造全流程移动端多模态大模型MobileVLM

   MobileVLM: Real-time multimodal model running on Snapdragon 888

4. 美团提出基于隐式条件位置编码的Transformer，性能优于 ViT 和 DeiT

   Implicit conditional position encoding Transformer outperforming ViT and DeiT

5. Twins：重新思考高效的视觉注意力模型设计

   Twins: Rethinking efficient visual attention model design

Object Detection

1. 更准更快的YOLOv6来了，美团出品并开源

   YOLOv6: Faster and more accurate, open-sourced by Meituan

AutoML & Neural Architecture Search

1. 小米AI实验室成果速递

   Xiaomi AI Lab research highlights

2. 雷军强推:小米造最强超分辨率算法，现已开源

   Lei Jun recommends: Xiaomi’s strongest super-resolution algorithm, now open-sourced

3. 超越MnasNet、Proxyless：小米提出全新神经架构搜索算法FairNAS

   FairNAS: A new NAS algorithm surpassing MnasNet and Proxyless

4. 两个月三项成果，对标谷歌！独家对话小米AutoML团队，如何让模型搜索更公平

   Exclusive interview with Xiaomi AutoML team: Making model search fairer