Loading video...

Video Failed to Load

Go Home

MolmoPoint from Ai2 was a recent foundation model release that feels criminally underrated to me, while not a robotics model it has great potential for various use cases labels are great even for wrist view!

VilleKuosmanen's profile picture

Ville🤖

3,196 subscribers

19,956 views • 3 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

Some great videos from the Gemini VLA release. These kinds of dexterous tasks require tons of coordination and interact with materials that are very hard to model in simulation. Good use of e2e learning and yet more evidence this is the right direction for robotics
0:33

Some great videos from the Gemini VLA release. These kinds of dexterous tasks require tons of coordination and interact with materials that are very hard to model in simulation. Good use of e2e learning and yet more evidence this is the right direction for robotics

Chris Paxton

30,949 views • 1 year ago

It takes great courage for a man to accept pregnancy from a relationship that is not even that long.
1:11

It takes great courage for a man to accept pregnancy from a relationship that is not even that long.

Edochie

101,350 views • 2 months ago

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

12,072 views • 3 months ago

Nemotron 3 Nano runs nicely with mlx-lm on an M4 Max. Could be a great model for local use on Mac: MoE + hybrid attention make it fast even for very long context. Generating in realtime with 4-bit model:
0:29

Nemotron 3 Nano runs nicely with mlx-lm on an M4 Max. Could be a great model for local use on Mac: MoE + hybrid attention make it fast even for very long context. Generating in realtime with 4-bit model:

Awni Hannun

51,070 views • 7 months ago

Had a great turnout at Monticello high school in Charlottesville Virginia today. Just about every top prospect in Virginia was there. Great group of athletes in an underrated state for big-time talent. Even had a couple of potential Americans from Maryland and one from Delaware.
1:15

Had a great turnout at Monticello high school in Charlottesville Virginia today. Just about every top prospect in Virginia was there. Great group of athletes in an underrated state for big-time talent. Even had a couple of potential Americans from Maryland and one from Delaware.

Tom Lemming

41,440 views • 1 year ago

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and
0:50

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and

AK

46,778 views • 2 years ago

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!
1:29

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,773 views • 1 year ago

I got a new 3D model for Catz as a gift from Leodamodeler! This one has better facial controls and just looks more cartooney in general, which is great for me. I made the song; I call it A Bright Spirit.
0:55

I got a new 3D model for Catz as a gift from Leodamodeler! This one has better facial controls and just looks more cartooney in general, which is great for me. I made the song; I call it A Bright Spirit.

LayzuhCatz

246,296 views • 2 years ago

📁 Ben Horowitz says large foundation models are not universal brains. They are infrastructure. Real value comes from combining many models for specific use cases. Cursor proves it by running over 13 models and building its own coding model. The edge is no longer size, but orchestration.
1:49

📁 Ben Horowitz says large foundation models are not universal brains. They are infrastructure. Real value comes from combining many models for specific use cases. Cursor proves it by running over 13 models and building its own coding model. The edge is no longer size, but orchestration.

Jon Hernandez

14,503 views • 6 months ago

America has gone over a cliff. To convict a former president of crimes that are not even specified in the indictment and for which the president was not allowed to defend himself, is a sad day for this great country. November 5th cannot come soon enough.
3:22

America has gone over a cliff. To convict a former president of crimes that are not even specified in the indictment and for which the president was not allowed to defend himself, is a sad day for this great country. November 5th cannot come soon enough.

Jeanine Pirro

365,489 views • 2 years ago

It was our pleasure to attend the 14th Annual “Catwalk for a Cause” last night. It was a great night, supporting a great cause. Special shoutout to Ruby for leading Brittany & I down the Catwalk 🫶 #CatwalkForACause Sherry Strong Foundation | MTJFoundation
0:38

It was our pleasure to attend the 14th Annual “Catwalk for a Cause” last night. It was a great night, supporting a great cause. Special shoutout to Ruby for leading Brittany & I down the Catwalk 🫶 #CatwalkForACause Sherry Strong Foundation | MTJFoundation

Joey Logano

29,445 views • 1 year ago

OpenAI just dropped a completely new kind of model gpt-realtime-translate takes in speech audio from any language and outputs speech in your target language LLMs are great, but you need specialized models for specialized use cases We're running this on our smart glasses
0:42

OpenAI just dropped a completely new kind of model gpt-realtime-translate takes in speech audio from any language and outputs speech in your target language LLMs are great, but you need specialized models for specialized use cases We're running this on our smart glasses

cayden 凯登

100,395 views • 1 month ago

eve torres is criminally underrated! she was the complete package & could do great work with any girl on the roster, that heel run was EVERYTHING. i think eve’s one of the great examples for why the diva’s era should be given a lot more recognition
3:10

eve torres is criminally underrated! she was the complete package & could do great work with any girl on the roster, that heel run was EVERYTHING. i think eve’s one of the great examples for why the diva’s era should be given a lot more recognition

tiff ☀️

38,544 views • 4 months ago

“I was a great admirer of Pandit Nehru. But by the 1960s, it became clear to me that he had adopted the wrong model for India” -Former Singapore PM Lee Kuan Yew The whole world acknowledges just how disastrous Nehru was for India’s development.
0:29

“I was a great admirer of Pandit Nehru. But by the 1960s, it became clear to me that he had adopted the wrong model for India” -Former Singapore PM Lee Kuan Yew The whole world acknowledges just how disastrous Nehru was for India’s development.

Political Kida

43,602 views • 6 months ago

Annamalai has been a great role model for me because he was one of the top IAS officers. He resigned from his job and then came into politics, which, for a middle class family, is a huge decision. After he came to Tamil Nadu, everybody was criticizing that it would not go above a certain percentage. But he was the one who created the idea that we can go into double digits. His courage and bravery are unforgettable. - Latchiya Jananayaga Katchi Founder Jose Charles Martin
0:50

Annamalai has been a great role model for me because he was one of the top IAS officers. He resigned from his job and then came into politics, which, for a middle class family, is a huge decision. After he came to Tamil Nadu, everybody was criticizing that it would not go above a certain percentage. But he was the one who created the idea that we can go into double digits. His courage and bravery are unforgettable. - Latchiya Jananayaga Katchi Founder Jose Charles Martin

Army of Dheeran Annamalai

12,665 views • 3 months ago

Patrick Mahomes is such a great role model for kiddos. We are so lucky to have him here in KC, and so thankful for all the great work he does for our city! ❤️💛
2:08

Patrick Mahomes is such a great role model for kiddos. We are so lucky to have him here in KC, and so thankful for all the great work he does for our city! ❤️💛

Lexi

54,829 views • 1 year ago

Boltz-2 was released recently. It is an Open Source protein-ligand co-folding model, which means it can predict the structure of a protein along with the ligand. It has various applications from drug discovery to protein design. I thought why not make a OSS web app for it.
2:00

Boltz-2 was released recently. It is an Open Source protein-ligand co-folding model, which means it can predict the structure of a protein along with the ligand. It has various applications from drug discovery to protein design. I thought why not make a OSS web app for it.

Ravi Sharma

43,911 views • 1 year ago