Loading video...

Video Failed to Load

Go Home

Introducing Cambrian-S it’s a position, a dataset, a benchmark, and a model but above all, it represents our first steps toward exploring spatial supersensing in video. 🧶

sainingxie's profile picture

Saining Xie

40,761 subscribers

259,810 views • 10 months ago •via X (Twitter)

ArtsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 in exploring that direction.
2:10

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 in exploring that direction.

Jiafei Duan

12,137 views • 5 months ago

Today we’re announcing two new updates in our computer vision work — a new, expanded license for our DINOv2 model and the release of FACET, a comprehensive new benchmark dataset to help evaluate and improve fairness in vision models. More details ➡️ 🧵
0:27

Today we’re announcing two new updates in our computer vision work — a new, expanded license for our DINOv2 model and the release of FACET, a comprehensive new benchmark dataset to help evaluate and improve fairness in vision models. More details ➡️ 🧵

AI at Meta

454,030 views • 3 years ago

Deployment is only the first step. You need to learn from it and take the next steps toward positive ROI. Our journey: Step 1. Nine month ago, our robot already assembled a complex real product for our customer, from start to finish. But it wasn’t reliable. Step 2. Our robot performed a complex benchmark task reliably 100 times in a row. Step 3. (Completing) Our robot assembling a complex real product from start to finish 100+ times in a row.
3:07

Deployment is only the first step. You need to learn from it and take the next steps toward positive ROI. Our journey: Step 1. Nine month ago, our robot already assembled a complex real product for our customer, from start to finish. But it wasn’t reliable. Step 2. Our robot performed a complex benchmark task reliably 100 times in a row. Step 3. (Completing) Our robot assembling a complex real product from start to finish 100+ times in a row.

Igor Kulakov (MicroFactory)

11,428 views • 1 month ago

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI
3:58

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,610 views • 1 year ago

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:
0:25

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:

Xingang Pan

15,946 views • 8 months ago

Introducing MedOS — The first AI × XR World Model for medicine We are closing the loop between clinical reasoning and physical intervention. It’s not just a tool; it’s spatial intelligence for medicine. A Stanford Medicine & Princeton University joint effort. Read👇
0:56

Introducing MedOS — The first AI × XR World Model for medicine We are closing the loop between clinical reasoning and physical intervention. It’s not just a tool; it’s spatial intelligence for medicine. A Stanford Medicine & Princeton University joint effort. Read👇

Charles Wu 吴英成AI🦞

26,421 views • 7 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

2,186,452 views • 4 months ago

Introducing our first game in development, code-named Project Loki. It’s a group adventure, a competitive sandbox and a highlights factory, all at once. It’s a blend of genres players have described as “League meets Apex meets Smash.” PLAYTEST SIGNUP @
4:33

Introducing our first game in development, code-named Project Loki. It’s a group adventure, a competitive sandbox and a highlights factory, all at once. It’s a blend of genres players have described as “League meets Apex meets Smash.” PLAYTEST SIGNUP @

Theorycraft Games

2,688,319 views • 3 years ago

$SERP The first perpetual trading platform on #shibarium is live on test net! This video demonstrates the steps required to initiate a position in Shibarium perpetuals Specifically,it provides guidance on taking a long position, reflecting our bullish sentiment #SHIB #shibaarmy
2:18

$SERP The first perpetual trading platform on #shibarium is live on test net! This video demonstrates the steps required to initiate a position in Shibarium perpetuals Specifically,it provides guidance on taking a long position, reflecting our bullish sentiment #SHIB #shibaarmy

Shibarium Perpetuals

101,017 views • 3 years ago

Introducing Sparrow-1, a conversational-flow control model built for real-time conversational video that sets the benchmark for human-level conversational timing and understanding in real-time AI.
3:32

Introducing Sparrow-1, a conversational-flow control model built for real-time conversational video that sets the benchmark for human-level conversational timing and understanding in real-time AI.

Tavus

47,995 views • 7 months ago

Introducing Meta Locate 3D: a model for accurate object localization in 3D environments. Learn how Meta Locate 3D can help robots accurately understand their surroundings and interact more naturally with humans. You can download the model and dataset, read our research paper, and even try a demo!
1:02

Introducing Meta Locate 3D: a model for accurate object localization in 3D environments. Learn how Meta Locate 3D can help robots accurately understand their surroundings and interact more naturally with humans. You can download the model and dataset, read our research paper, and even try a demo!

AI at Meta

81,465 views • 1 year ago

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.
0:42

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Matt Shumer

383,243 views • 2 years ago

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:
1:01

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,464 views • 3 years ago

Meta PARTNR is a research framework supporting seamless human-robot collaboration. Building on our research with Habitat, we’re open sourcing a large-scale benchmark, dataset and large planning model that we hope will enable the community to effectively train social robots.
2:46

Meta PARTNR is a research framework supporting seamless human-robot collaboration. Building on our research with Habitat, we’re open sourcing a large-scale benchmark, dataset and large planning model that we hope will enable the community to effectively train social robots.

AI at Meta

107,046 views • 1 year ago

A billion people produce the most valuable dataset in the world every day – and delete it every night. We’re recording it. Introducing @AttentionInc
0:50

A billion people produce the most valuable dataset in the world every day – and delete it every night. We’re recording it. Introducing @AttentionInc

Aidan Guo

1,857,714 views • 1 month ago

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️
1:01

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

AI at Meta

20,244 views • 1 year ago

What if a foundation model could align histology, spatial biology & clinical data to reveal latent biomedical insights? 🚀 Introducing Haiku — a tri-modal foundation model trained on 26.7M+ spatial proteomics patches with matched H&E and clinical text, aligned in one shared embedding space. 📄 🧵👇
1:10

What if a foundation model could align histology, spatial biology & clinical data to reveal latent biomedical insights? 🚀 Introducing Haiku — a tri-modal foundation model trained on 26.7M+ spatial proteomics patches with matched H&E and clinical text, aligned in one shared embedding space. 📄 🧵👇

Zhi Huang

13,358 views • 4 months ago