Loading video...

Video Failed to Load

Go Home

Introducing WildDet3D, a grounding model for monocular 3D object detection in the wild. A question I keep coming back to is: what is the right backbone for robotics foundation models? Should it be a video model, a language model, or perhaps a grounding model? WildDet3D is our first step...

DJiafei's profile picture

Jiafei Duan

5,837 subscribers

12,072 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵
0:57

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵

Ai2

85,267 views • 2 months 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
0:27

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

186,544 views • 2 years ago

WildDet3D Scaling Promptable 3D Detection in the Wild paper:
0:57

WildDet3D Scaling Promptable 3D Detection in the Wild paper:

AK

13,205 views • 1 month ago

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:
2:31

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:

Joseph Nelson

18,231 views • 1 year ago

Dreaming in Blender. Genuinely curious if Is this a 3D model? says this is a 3D model or not
0:26

Dreaming in Blender. Genuinely curious if Is this a 3D model? says this is a 3D model or not

Blue Nile 3D

86,895 views • 8 months ago

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️
0:51

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

AI at Meta

186,324 views • 3 years ago

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:
0:50

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,404 views • 8 months ago

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!
1:08

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,180,014 views • 1 month ago

Embeddings (and how to create them) are, perhaps, the most interesting idea behind Large Language Models. I built a simple model to help you understand embeddings from scratch. Here is a step-by-step video explanation:
51:43

Embeddings (and how to create them) are, perhaps, the most interesting idea behind Large Language Models. I built a simple model to help you understand embeddings from scratch. Here is a step-by-step video explanation:

Santiago

44,107 views • 1 year ago

Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵
0:33

Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵

Ai2

64,231 views • 3 months ago

New 🤗 transformers release includes a very powerful Multimodel Large Language Model (MLLM) by Microsoft called KOSMOS-2! 🤩 The highlight of KOSMOS-2 is grounding, the model is *incredibly* accurate! 🌎 Play with the demo here 👉 But how does this model work? Let's take a look! 👀🧶
0:36

New 🤗 transformers release includes a very powerful Multimodel Large Language Model (MLLM) by Microsoft called KOSMOS-2! 🤩 The highlight of KOSMOS-2 is grounding, the model is *incredibly* accurate! 🌎 Play with the demo here 👉 But how does this model work? Let's take a look! 👀🧶

merve

143,816 views • 2 years ago

You didn’t ask, You didn’t question, But do I care? Not at all! Introducing THE example video for our 2.0 Live2d Scrungle Models! Want a starter model? Perfect! Want to join a family of over 250 Model Kids? Easy Want to have a model mom who will dote over you? Vgen in Bio! ❤️
0:30

Sensitive content

You didn’t ask, You didn’t question, But do I care? Not at all! Introducing THE example video for our 2.0 Live2d Scrungle Models! Want a starter model? Perfect! Want to join a family of over 250 Model Kids? Easy Want to have a model mom who will dote over you? Vgen in Bio! ❤️

Gloomy

80,903 views • 1 year ago

American nurse speaks out about our healthcare system “Let me be the first nurse to tell you that this medical system is not built to make you better. It is not broken. It is literally designed as a business model to keep people sick. And I know this is going to make a lot of nurses and doctors upset. It's the reality. It's what's happening in front of our faces. This is a business model to keep people coming back. It's the fact that we can't be honest with our patients is the reason that this business model is working.” “Their business model is literally keep people sick, keep them on a medication, keep telling them surgery is the answer. I know so many people who are on lifetime medications who've had multiple surgeries and who are not living their life.”
1:43

American nurse speaks out about our healthcare system “Let me be the first nurse to tell you that this medical system is not built to make you better. It is not broken. It is literally designed as a business model to keep people sick. And I know this is going to make a lot of nurses and doctors upset. It's the reality. It's what's happening in front of our faces. This is a business model to keep people coming back. It's the fact that we can't be honest with our patients is the reason that this business model is working.” “Their business model is literally keep people sick, keep them on a medication, keep telling them surgery is the answer. I know so many people who are on lifetime medications who've had multiple surgeries and who are not living their life.”

Wall Street Apes

82,784 views • 3 months ago

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️
0:31

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

Ted Xiao

152,395 views • 1 year ago

BREAKING: Tesla has officially announced that FSD (Supervised) is launching in Australia, marking a huge milestone for the company. The rollout will happen in stages. HW4 Model 3s and Model Ys will get it first. Tesla says it is "very close" to being unlocked in customer cars. It will be available for purchase outright as a $10,100 option, or through a subscription model. Tesla hasn't released the subscription price yet.
2:28

BREAKING: Tesla has officially announced that FSD (Supervised) is launching in Australia, marking a huge milestone for the company. The rollout will happen in stages. HW4 Model 3s and Model Ys will get it first. Tesla says it is "very close" to being unlocked in customer cars. It will be available for purchase outright as a $10,100 option, or through a subscription model. Tesla hasn't released the subscription price yet.

Sawyer Merritt

494,853 views • 9 months ago

Unitree CEO Wang Xingxing: Whoever builds the first Generalized Robotics Foundation Model deserves a Nobel Prize. He also said Unitree is working in that direction too, but the probability of succeeding is currently below 50%.
0:41

Unitree CEO Wang Xingxing: Whoever builds the first Generalized Robotics Foundation Model deserves a Nobel Prize. He also said Unitree is working in that direction too, but the probability of succeeding is currently below 50%.

Eren Chen

25,298 views • 18 days ago

🔷 Introducing Rig3R - our new geometric foundation model for 3D perception in AVs.
1:31

🔷 Introducing Rig3R - our new geometric foundation model for 3D perception in AVs.

Wayve

39,671 views • 7 months ago