Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding TL;DR: DINO-X Pro: sota model with enhanced perception capabilities for various scenarios; DINO-X Edge: model optimized for faster inference speed and better suited for deployment on edge devices

Alexandre Morgand

2,238 subscribers

60,743 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

8 Comments

Alexandre Morgand1 year ago

Blogpost: Paper: Source code:

UserInterface2 years ago

The Future of IoT Devices: Analog Computing and the Fusion of Analog-Digital Processors #tech #news

Jim Bohnslav1 year ago

If only they had the weights

Kevin Patel1 year ago

Impressive results, but keep in mind that it is an API-only model

Alexandre Morgand1 year ago

Thanks for the clarification!

SajayR1 year ago

Training a for-edge model and then keeping it behind an API is confusing behaviour

Romano Ryan1 year ago

Such a cool mix of speed and perception, really impressive! 🍊

Opeih1 year ago

impressive results

Related Videos

Meet Reka Edge – Our next-generation vision language model for physical AI. Uses 3x fewer input tokens and achieves 65% faster throughput compared to leading 8B models. Image understanding, video analysis, object detection, and tool use. Built for Action. Fast enough for production, deployable anywhere. Read more:

Meet Reka Edge – Our next-generation vision language model for physical AI. Uses 3x fewer input tokens and achieves 65% faster throughput compared to leading 8B models. Image understanding, video analysis, object detection, and tool use. Built for Action. Fast enough for production, deployable anywhere. Read more:

Reka

53,976 views • 5 months ago

NVIDIA Cosmos 3 launches with a full model family — Cosmos Super for highest-accuracy robotics and AV post-training, Cosmos Nano for high-speed video and action reasoning, and Cosmos Edge for real-time edge inference. Read the release ➡️

NVIDIA Cosmos 3 launches with a full model family — Cosmos Super for highest-accuracy robotics and AV post-training, Cosmos Nano for high-speed video and action reasoning, and Cosmos Edge for real-time edge inference. Read the release ➡️

NVIDIA Newsroom

47,079 views • 2 months ago

Thinking with Camera A Unified Multimodal Model for Camera-Centric Understanding and Generation

Thinking with Camera A Unified Multimodal Model for Camera-Centric Understanding and Generation

AK

39,377 views • 10 months ago

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

Google AI Developers

125,226 views • 1 year ago

if this comes across your tl, please drop tags for dino! 🦖 the world is about to know how good of a performer he is!🔥 DINO X EWC TIL MY FINGERS BLEED #디노와_함께하는_2025EWC주제곡 #DINO_TilMyFingersBleed #EWC2025 세븐틴(SEVENTEEN)

if this comes across your tl, please drop tags for dino! 🦖 the world is about to know how good of a performer he is!🔥 DINO X EWC TIL MY FINGERS BLEED #디노와_함께하는_2025EWC주제곡 #DINO_TilMyFingersBleed #EWC2025 세븐틴(SEVENTEEN)

angel saw svt! ⚡️

40,002 views • 1 year ago

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Lior Alexander

186,579 views • 2 years ago

Model deployment and GPU services for AI developers. 🚀 AI Inference Acceleration: On-demand GPU acceleration for AI model and application inference. 📷 Development & Deployment Engine: End-to-end tools for building and deploying AI models. Project Advantages: · Pay-as-you-go · One-click deployment · Dynamic scalability · Unified interface #AIInference #GPUComputing #AIAcceleration #ModelDeployment #AIInfrastructure #EdgeAI #CloudAI #AIDevelopment #AIDeployment #AIDevTools #PayAsYouGo #OneClickDeployment #ScalableAI #UnifiedPlatform #DePIN #AIForDevelopers #MachineLearning #AIModels #AIStartup #AIAgent

Model deployment and GPU services for AI developers. 🚀 AI Inference Acceleration: On-demand GPU acceleration for AI model and application inference. 📷 Development & Deployment Engine: End-to-end tools for building and deploying AI models. Project Advantages: · Pay-as-you-go · One-click deployment · Dynamic scalability · Unified interface #AIInference #GPUComputing #AIAcceleration #ModelDeployment #AIInfrastructure #EdgeAI #CloudAI #AIDevelopment #AIDeployment #AIDevTools #PayAsYouGo #OneClickDeployment #ScalableAI #UnifiedPlatform #DePIN #AIForDevelopers #MachineLearning #AIModels #AIStartup #AIAgent

MetaY

26,164 views • 1 year ago

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

Moo Jin Kim

227,044 views • 2 years ago

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

Tencent Hy

34,317 views • 4 months ago

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

Ettore Di Giacinto

13,972 views • 2 months ago

Zhipu AI just released GLM-4.6V on Hugging Face This new multimodal model achieves SOTA visual understanding, features native function calling for agents, and handles 128k context for documents. Perception to action!

Zhipu AI just released GLM-4.6V on Hugging Face This new multimodal model achieves SOTA visual understanding, features native function calling for agents, and handles 128k context for documents. Perception to action!

DailyPapers

16,629 views • 8 months ago

NVIDIA's LocateAnything is a new vision model for grounding and detection. Very performant and accurate! > 10x faster than Qwen3-VL > 138M queries + 785M boxes > GUI, OCR, docs, dense detection > Free & open source

NVIDIA's LocateAnything is a new vision model for grounding and detection. Very performant and accurate! > 10x faster than Qwen3-VL > 138M queries + 785M boxes > GUI, OCR, docs, dense detection > Free & open source

⚡AI Search⚡

121,429 views • 2 months ago

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 views • 6 months ago

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)

Songyou Peng

287,914 views • 3 months ago

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,374 views • 1 year ago

VideoLLaMA3, latest MLLMs for image and video understanding. 🖐️ 7B models: DocVQA: 94.9, MathVision: 26.2, VideoMME: 66.2/70.3, MLVU: 73.0 🤏 2B models for edge devices: MMMU: 45.3, VideoMME: 59.6/63.4 👊 Frontier-class video model with ONLY 3M video-text pairs

VideoLLaMA3, latest MLLMs for image and video understanding. 🖐️ 7B models: DocVQA: 94.9, MathVision: 26.2, VideoMME: 66.2/70.3, MLVU: 73.0 🤏 2B models for edge devices: MMMU: 45.3, VideoMME: 59.6/63.4 👊 Frontier-class video model with ONLY 3M video-text pairs

Gradio

37,154 views • 1 year ago

We’re diligently improving Grok, building a specialized coding model, improving multi modal capabilities, and developing a strong model for video generation and understanding. Grok on Web: Grok on iOS: Grok on Android: Grok API console:

We’re diligently improving Grok, building a specialized coding model, improving multi modal capabilities, and developing a strong model for video generation and understanding. Grok on Web: Grok on iOS: Grok on Android: Grok API console:

SpaceXAI

176,988 views • 1 year ago

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

Tongyi Lab

164,097 views • 6 months ago

Here's my latest experimental piece I call this one "Lost and Found on Dino Island" 🦖 I used Nano Banana Pro and Topaz in Adobe Firefly boards for the images and Klings new 2.6 Model for the animation. The tools have made a huge jump in quality and consistency it's undeniable.

Here's my latest experimental piece I call this one "Lost and Found on Dino Island" 🦖 I used Nano Banana Pro and Topaz in Adobe Firefly boards for the images and Klings new 2.6 Model for the animation. The tools have made a huge jump in quality and consistency it's undeniable.

Captain HaHaa

24,390 views • 8 months ago