Replies: 10 comments
-
2024-07-07 Holmes-VAD:一种新的视频异常检测框架,能够精确定位并解释检测到的异常
媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-12 新加坡国立大学、南洋理工大学提出视频思维链推理框架Video-of-Thought(VoT),旨在提升视频理解和推理能力
论文链接: https://openreview.net/pdf?id=fO31YAyNbI 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-12 AMD斥资6.65美元收购欧洲 AI 实验室 Silo AI
silo博客:https://www.silo.ai/blog/amd-to-acquire-silo-ai-to-expand-enterprise-ai-solutions-globally 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-09 Stephen Wolfram进行了一场与机器人的直播采访,期间机器人对30多个问题对答如流
原视频地址:https://www.youtube.com/live/co0zh76VMc8 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-08 微软和萨里大学的研究者提出MInference方法,显著加速大语言模型(LLM)的长上下文处理能力
媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-09 ControlNet作者Lvmin Zhang推出PaintsUndo新项目,一张图生成绘画全过程
Github地址:https://github.com/lllyasviel/Paints-UNDO 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-11 蚂蚁集团开源了EchoMimic,一个逼真的音频驱动人像动画框架EchoMimic能够通过音频文件和一张静态面部标志点图像生成数字人像视频。与传统方法相比,EchoMimic结合音频和面部标志点,生成更逼真和自然的动画。 345400814-c8b5c59f-0483-42ef-b3ee-4cffae6c7a52.mp4 |
Beta Was this translation helpful? Give feedback.
-
2024-07-13 谷歌的Gemini 1.5 Pro被应用于机器人训练机器人导航和完成任务
论文链接:Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-13 Meta、英伟达和Together AI等机构的研究者推出了新一代FlashAttention算法,旨在加速大语言模型(LLM)的注意力计算
Github地址:https://github.com/Dao-AILab/flash-attention 媒体文章: |
Beta Was this translation helpful? Give feedback.
-
2024-07-17 普林斯顿大学研究人员分析了Transformer模型和人类大脑在语言处理中的相似性
媒体文章: |
Beta Was this translation helpful? Give feedback.
-
AI新闻动态(2024-07-07到2024-07-13)
目录
机器人
AI研究
AI投资
Beta Was this translation helpful? Give feedback.
All reactions