Загрузка видео...

Не удалось загрузить видео

На главную

SOTA object detection with powerful visual reasoning: "skateboarder wearing checkered shirt".

moondreamai's profile picture

moondream

8,817 subscribers

60,524 просмотров • 9 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation
0:13

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation

vik

84,013 просмотров • 1 год назад

Gemini 3.1 is SOTA at 3D spatial reasoning
0:14

Gemini 3.1 is SOTA at 3D spatial reasoning

Zach Dive

196,253 просмотров • 4 месяцев назад

Awesome week for computer vision Hugging Face🔥 Besides DINOv3 we added support for LLMDet, the SOTA for zero-shot object detection (#CVPR2025 '25 highlight) Detect instances in scenes just via prompting, no training involved.
0:11

Awesome week for computer vision Hugging Face🔥 Besides DINOv3 we added support for LLMDet, the SOTA for zero-shot object detection (#CVPR2025 '25 highlight) Detect instances in scenes just via prompting, no training involved.

Niels Rogge

73,865 просмотров • 11 месяцев назад

Real-time DEtection Transformer (RT-DETR) landed in Hugging Face transformers 🤩 with Apache 2.0 license 😍 do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀
0:18

Real-time DEtection Transformer (RT-DETR) landed in Hugging Face transformers 🤩 with Apache 2.0 license 😍 do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀

merve

155,222 просмотров • 2 лет назад

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.
0:15

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.

Akshay 🚀

31,412 просмотров • 7 месяцев назад

who wants visual, instant AI slop design detection on your live codebase/site? - coming to Impeccable 2.0 (sneak peek) - deterministic, LLM not required - ships with a powerful cli companion (works in ci/cd etc = automatic slop revention)
0:18

who wants visual, instant AI slop design detection on your live codebase/site? - coming to Impeccable 2.0 (sneak peek) - deterministic, LLM not required - ships with a powerful cli companion (works in ci/cd etc = automatic slop revention)

Paul Bakaus

17,009 просмотров • 3 месяцев назад

We just released an open-source framework that makes it easy to build visual reasoning agents (with GRPO).
0:14

We just released an open-source framework that makes it easy to build visual reasoning agents (with GRPO).

sunil kumar

108,539 просмотров • 1 год назад

Moondream 3: world's best open-vocab object detection, packed in a fast, open model.
0:11

Moondream 3: world's best open-vocab object detection, packed in a fast, open model.

moondream

52,595 просмотров • 9 месяцев назад

Object detection on 3D Gaussian Splats. Accurate bounding boxes per detection, runs locally. Nigel Hartman ᯅ really cooked here SensAI Hackademy is hosting a lecture with Ian Curtis from World Labs on the 8th on this:
0:11

Object detection on 3D Gaussian Splats. Accurate bounding boxes per detection, runs locally. Nigel Hartman ᯅ really cooked here SensAI Hackademy is hosting a lecture with Ian Curtis from World Labs on the 8th on this:

Johannes Tscharn

35,105 просмотров • 18 дней назад

wow.. this new object detection AI tool is incredible and open sourced link in comment
0:14

wow.. this new object detection AI tool is incredible and open sourced link in comment

el.cine

214,745 просмотров • 1 год назад

max is wearing his qsmp shirt AGAIN because he thinks ppl wont remember him if hes not wearing his qsmp shirt LMAOOO
0:18

max is wearing his qsmp shirt AGAIN because he thinks ppl wont remember him if hes not wearing his qsmp shirt LMAOOO

🇧🇷 BOBOnils𖦹n 土 QSMP2 .ᐟ

43,642 просмотров • 18 дней назад

*sana saw once wearing a betty boop t-shirt* “t-shirt… 🫵🏻 🥺 t-shirt… 🥹 i want that t-shirt!~~~”
0:12

*sana saw once wearing a betty boop t-shirt* “t-shirt… 🫵🏻 🥺 t-shirt… 🥹 i want that t-shirt!~~~”

ฅ^•ﻌ•^ฅ

327,022 просмотров • 23 дней назад

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵
0:14

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵

Bespoke Labs

19,871 просмотров • 1 год назад

Fox News He is also wearing a shirt with the same design as Charlie Kirk's assassin.
0:17

Fox News He is also wearing a shirt with the same design as Charlie Kirk's assassin.

Brick Suit

98,105 просмотров • 10 месяцев назад

Founder of Maxhosa Africa; Laduma Ngxokolo wearing a golf t-shirt under a shirt.
0:16

Founder of Maxhosa Africa; Laduma Ngxokolo wearing a golf t-shirt under a shirt.

Musa Khawula

530,872 просмотров • 1 год назад

Jonathan Bailey wearing this slutty ass shirt
0:18

Sensitive content

Jonathan Bailey wearing this slutty ass shirt

Holekage of the Hidden Bussy Village

319,022 просмотров • 8 месяцев назад

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025
0:11

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025

Qingqing Zhao

48,207 просмотров • 1 год назад