Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Capturing every combination of human-object interaction is not feasible. We need compositionally. Most interactions are local. A hand holds a cup, a chair supports the pelvis, while much of the body remains free. COSMI, by Daniel Escandar Ilya Petrov builds on this observation to compose existing single-object datasets into... 222k multi-object sequences, totaling 275 hours, with up to 5 objects per sequence. LLM reasoning and geometric checks ensure the compositions remain plausible. On this data, we train a single diffusion transformer for interactions with 1 to 5 objects, predicting each object relative to its interacting body part and generalizing to unseen objects and combinations. Data and code will be made available: 🌐show more

Gerard Pons-Moll

6,359 subscribers

20,393 Aufrufe • vor 2 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Gerard Pons-Moll

Gerard Pons-Mollvor 2 Tagen

We need *compositionality*

Profilbild von Diakonos

Diakonosvor 2 Tagen

@ptrvilya Any hint on the release date?🥲

Profilbild von Sani Ai Tech

Sani Ai Techvor 1 Tag

@ptrvilya Compositional interaction modeling could unlock much stronger generalization to unseen object combinations

Profilbild von Eplurubusnullus

Eplurubusnullusvor 1 Tag

@ptrvilya This is huge, and exactly what I've been looking for.

Profilbild von ζ Pedram ζ

ζ Pedram ζvor 2 Tagen

@ptrvilya Need more then that but this is a good start Morphological intelligence is foundational to Kung Fu and Cybernetics imho.. The next level is something I study, how to keep the coffee in your mug.. while being pushed around.

Profilbild von Diakonos

Diakonosvor 2 Tagen

@ptrvilya God sent lolll 🔥🔥🔥great work can wait to use it

Profilbild von Jo

Jovor 1 Tag

@ptrvilya Perhaps we should borrow a concept from video compression: model only the interactions that change, while preserving and reusing everything that remains unchanged. I hear you, it’s like, why reconstruct the entire scene when only a small part of it is interacting?

Profilbild von Vantix AI Agency

Vantix AI Agencyvor 1 Tag

@ptrvilya 222k sequences and up to 5 objects composed so elegantly building on local interactions to scale compositionally is such a smart breakthrough

Ähnliche Videos

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 Aufrufe • vor 3 Jahren

A few weeks ago, we shared our progress on articulated objects and long-horizon tasks. Here are two representative examples: - We've been steadily expanding our asset library to cover more articulated objects. Articulated objects have always been a challenging asset class to handle in simulation. Interacting with them requires robots to master atomic skills such as pushing, pulling, opening, and closing, and to understand part structure, interaction constraints, and how the object moves. - Long-horizon tasks can now be generated at scale. Long-horizon tasks are the other hard category: they require chaining multiple sub-goals in sequence. A failure early in the task can cascade and make the rest unrecoverable. Axis is scaling along three dimensions at once: data volume, data quality, and task difficulty.

A few weeks ago, we shared our progress on articulated objects and long-horizon tasks. Here are two representative examples: - We've been steadily expanding our asset library to cover more articulated objects. Articulated objects have always been a challenging asset class to handle in simulation. Interacting with them requires robots to master atomic skills such as pushing, pulling, opening, and closing, and to understand part structure, interaction constraints, and how the object moves. - Long-horizon tasks can now be generated at scale. Long-horizon tasks are the other hard category: they require chaining multiple sub-goals in sequence. A failure early in the task can cascade and make the rest unrecoverable. Axis is scaling along three dimensions at once: data volume, data quality, and task difficulty.

Axis Robotics

14,217 Aufrufe • vor 3 Monaten

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

36,059 Aufrufe • vor 1 Jahr

Creator of C#, Anders Hejlsberg(Anders Hejlsberg), on the design goals that shaped the language and why standardisation was a goal from the beginning: “The overarching thing was this power and productivity of C++ with the ease of use of Visual Basic. We knew we wanted to build an object oriented language. We wanted managed code or byte code so we could target different runtime environments. We wanted garbage collection and exception handling, but also things like a unified object system where, and that's true in C#, anything can be assigned to an object. If it's a value type, we box it. And it's a self-describing object. So, reflection: you can ask an object, ‘what are you’? And you can get all of the facts about it at runtime, and you can dynamically manipulate it in ways that just don't exist in a lot of other environments. We wanted a language that made this new model of properties, methods and events first class because that was how components were built as opposed to just sort of functions and procedures and even objects. And we wanted to create a language that was standardised. We wanted to give this language to a standardisation committee and try to level the playing field there. And all of those things were sort of like what was rolled up in C#”

Creator of C#, Anders Hejlsberg(Anders Hejlsberg), on the design goals that shaped the language and why standardisation was a goal from the beginning: “The overarching thing was this power and productivity of C++ with the ease of use of Visual Basic. We knew we wanted to build an object oriented language. We wanted managed code or byte code so we could target different runtime environments. We wanted garbage collection and exception handling, but also things like a unified object system where, and that's true in C#, anything can be assigned to an object. If it's a value type, we box it. And it's a self-describing object. So, reflection: you can ask an object, ‘what are you’? And you can get all of the facts about it at runtime, and you can dynamically manipulate it in ways that just don't exist in a lot of other environments. We wanted a language that made this new model of properties, methods and events first class because that was how components were built as opposed to just sort of functions and procedures and even objects. And we wanted to create a language that was standardised. We wanted to give this language to a standardisation committee and try to level the playing field there. And all of those things were sort of like what was rolled up in C#”

The Pragmatic Engineer

18,332 Aufrufe • vor 4 Monaten

MaterialFusion Enhancing Inverse Rendering with Material Diffusion Priors discuss: Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail to render accurately under new lighting conditions due to the intrinsic challenge of disentangling albedo and material properties from input images. To address this challenge, we introduce MaterialFusion, an enhanced conventional 3D inverse rendering pipeline that incorporates a 2D prior on texture and material properties. We present StableMaterial, a 2D diffusion model prior that refines multi-lit data to estimate the most likely albedo and material from given input appearances. This model is trained on albedo, material, and relit image data derived from a curated dataset of approximately ~12K artist-designed synthetic Blender objects called BlenderVault. we incorporate this diffusion prior with an inverse rendering framework where we use score distillation sampling (SDS) to guide the optimization of the albedo and materials, improving relighting performance in comparison with previous work. We validate MaterialFusion's relighting performance on 4 datasets of synthetic and real objects under diverse illumination conditions, showing our diffusion-aided approach significantly improves the appearance of reconstructed objects under novel lighting conditions. We intend to publicly release our BlenderVault dataset to support further research in this field.

MaterialFusion Enhancing Inverse Rendering with Material Diffusion Priors discuss: Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail to render accurately under new lighting conditions due to the intrinsic challenge of disentangling albedo and material properties from input images. To address this challenge, we introduce MaterialFusion, an enhanced conventional 3D inverse rendering pipeline that incorporates a 2D prior on texture and material properties. We present StableMaterial, a 2D diffusion model prior that refines multi-lit data to estimate the most likely albedo and material from given input appearances. This model is trained on albedo, material, and relit image data derived from a curated dataset of approximately ~12K artist-designed synthetic Blender objects called BlenderVault. we incorporate this diffusion prior with an inverse rendering framework where we use score distillation sampling (SDS) to guide the optimization of the albedo and materials, improving relighting performance in comparison with previous work. We validate MaterialFusion's relighting performance on 4 datasets of synthetic and real objects under diverse illumination conditions, showing our diffusion-aided approach significantly improves the appearance of reconstructed objects under novel lighting conditions. We intend to publicly release our BlenderVault dataset to support further research in this field.

AK

22,959 Aufrufe • vor 2 Jahren

🔥Ukrainian Defense Forces continue to mirror-strike commercial objects that Russian occupiers have seized along with Ukrainian cities. Today, another commercial center, "Galaktika" in Donetsk, with an area of 22,760 m², was hit. After a UAV strike on the territory of the object, a large-scale fire broke out. During the occupation, the Ukrainian "Epitsentr" operated here. That is, this Russian object is Ukrainian property that the invaders simply appropriated after capturing the city and renamed it to "Galaktika". Similar large commercial objects are regularly used by occupation formations for their own purposes, including for storing property and ensuring the logistical needs of occupation structures.

🔥Ukrainian Defense Forces continue to mirror-strike commercial objects that Russian occupiers have seized along with Ukrainian cities. Today, another commercial center, "Galaktika" in Donetsk, with an area of 22,760 m², was hit. After a UAV strike on the territory of the object, a large-scale fire broke out. During the occupation, the Ukrainian "Epitsentr" operated here. That is, this Russian object is Ukrainian property that the invaders simply appropriated after capturing the city and renamed it to "Galaktika". Similar large commercial objects are regularly used by occupation formations for their own purposes, including for storing property and ensuring the logistical needs of occupation structures.

Cloooud |🇺🇦

17,840 Aufrufe • vor 1 Monat

🚀 Struggling with the lack of high-quality data for AI-driven human-object interaction research? We've got you covered! Introducing HUMOTO, a groundbreaking 4D dataset for human-object interaction, developed with a combination of wearable motion capture, SOTA 6D pose estimation vision models, LLM, and the professional refining works of multiple animation studios. HUMOTO features: ✅ Over 700 diverse daily activities ✅ Interactions with 60+ objects, 70+ articulated parts. ✅ Fine-grained text annotations ✅ Detailed hand and finger movements We hope HUMOTO will fuel your Humanoid AI research and drive new advancements! For research or commercial license inquiries, please contact yizho@adobe.com. Explore the dataset: 👉 HUMOTO Dataset Website Learn more: 👉 HUMOTO Project Page Jiaxin Lu Qixing Huang #AI #HumanObjectInteraction #HumanoidAI #MotionCapture #HUMOTO #AdobeResearch

🚀 Struggling with the lack of high-quality data for AI-driven human-object interaction research? We've got you covered! Introducing HUMOTO, a groundbreaking 4D dataset for human-object interaction, developed with a combination of wearable motion capture, SOTA 6D pose estimation vision models, LLM, and the professional refining works of multiple animation studios. HUMOTO features: ✅ Over 700 diverse daily activities ✅ Interactions with 60+ objects, 70+ articulated parts. ✅ Fine-grained text annotations ✅ Detailed hand and finger movements We hope HUMOTO will fuel your Humanoid AI research and drive new advancements! For research or commercial license inquiries, please contact [email protected]. Explore the dataset: 👉 HUMOTO Dataset Website Learn more: 👉 HUMOTO Project Page Jiaxin Lu Qixing Huang #AI #HumanObjectInteraction #HumanoidAI #MotionCapture #HUMOTO #AdobeResearch

Yi Zhou

71,609 Aufrufe • vor 1 Jahr

HOLY SHIT! Sparc 3D is INSANE! All they need to do now is enable PBR texture support, object separation and decimation and this in my opinion completely replaces photogrammetry. The quality of the reconstruction of these 3D objects from a single image is mind blowing to me. Yes, the model is insanely dense to allow all of this detail but the fact that AI can generate with this level of fidelity is CRAZY!!! You can try it for free on Huggingface

HOLY SHIT! Sparc 3D is INSANE! All they need to do now is enable PBR texture support, object separation and decimation and this in my opinion completely replaces photogrammetry. The quality of the reconstruction of these 3D objects from a single image is mind blowing to me. Yes, the model is insanely dense to allow all of this detail but the fact that AI can generate with this level of fidelity is CRAZY!!! You can try it for free on Huggingface

Travis Davids

18,230 Aufrufe • vor 1 Jahr

This is the latest Google research on XR Interaction: World Mouse. Instead of using hand rays or gestures to point at things in the physical space, you move a cursor with a mouse and the system figures out where that cursor should sit in the 3D world. It works in two main ways: - On an object, the cursor follows the surface, so you can move precisely across walls, screens, furniture, or virtual objects. - Between objects, the system creates a smooth bridge through space, so the cursor can travel from one surface to another. That means you can go from a 2D panel to a 3D object, place content on a real wall, manipulate virtual objects, or interact with physical devices through digital proxies. This is the type of news, tools and product updates I share weekly in my newsletter. If you are into 3D XR and AI make sure to check it out (link on top of my profile). Based on “World Mouse: Exploring Interactions with a Cross-Reality Cursor” by Esen K. Tütüncü, Mar Gonzalez-Franco, Khushman Patel, and Eric J. Gonzalez

Gabriele Romagnoli

29,043 Aufrufe • vor 6 Monaten

🚨FROM METAPOD TO A SPIKY GLOBE At the start of this footage, the object appears to be in the form of a Metapod. It stays that way for several seconds before the camera pulls back and loses the detail. When the object comes back into view it appears wider. By the end it looks circular, with short spikes around its edge. It could be just one single object rotating through different angles, the video never really gives us a clear view of the actual change itself. We begin with a Metapod and finish with what looks like a spiky ball. #ufotwitter #uapX #UFO #UAP #Metapod #UFOSighting

🚨FROM METAPOD TO A SPIKY GLOBE At the start of this footage, the object appears to be in the form of a Metapod. It stays that way for several seconds before the camera pulls back and loses the detail. When the object comes back into view it appears wider. By the end it looks circular, with short spikes around its edge. It could be just one single object rotating through different angles, the video never really gives us a clear view of the actual change itself. We begin with a Metapod and finish with what looks like a spiky ball. #ufotwitter #uapX #UFO #UAP #Metapod #UFOSighting

Skywatch Signal

13,186 Aufrufe • vor 29 Tagen

A drone just mapped an entire cemetery and found 9,940 individual grave headstones on its own in 21 minutes A 335 megapixel scan gets fused with 134 million lidar points, building a full 3D model of the terrain down to 5cm resolution An AI model called SAM3 scans the imagery and outlines every single headstone automatically, no human tracing anything by hand The system converts every detected object straight into CAD vectors, ready to export as a working drawing Surveyors used to spend weeks manually outlining thousands of objects on a map like this one This pipeline exported a finished CAD file in 21 minutes

A drone just mapped an entire cemetery and found 9,940 individual grave headstones on its own in 21 minutes A 335 megapixel scan gets fused with 134 million lidar points, building a full 3D model of the terrain down to 5cm resolution An AI model called SAM3 scans the imagery and outlines every single headstone automatically, no human tracing anything by hand The system converts every detected object straight into CAD vectors, ready to export as a working drawing Surveyors used to spend weeks manually outlining thousands of objects on a map like this one This pipeline exported a finished CAD file in 21 minutes

pulmencr

39,083 Aufrufe • vor 2 Monaten

What is going on with UFO cloaking capabilities? "I looked up and I couldn't see the craft. You actually cannot see the craft. The light bends around it." "We have these tools that tell us where to look. All our sensors are pumped into our visor. It shows us the object in a box right on our visor." "We have every expectation of having a successful merge and seeing this object. And then it wasn't there." "We still see it on the flare. We still see the energy emitting from that area, but nothing visually." "They are describing phenomena, objects that appear very often out of nowhere and disappear on the spot."

What is going on with UFO cloaking capabilities? "I looked up and I couldn't see the craft. You actually cannot see the craft. The light bends around it." "We have these tools that tell us where to look. All our sensors are pumped into our visor. It shows us the object in a box right on our visor." "We have every expectation of having a successful merge and seeing this object. And then it wasn't there." "We still see it on the flare. We still see the energy emitting from that area, but nothing visually." "They are describing phenomena, objects that appear very often out of nowhere and disappear on the spot."

American Alchemy

20,354 Aufrufe • vor 5 Monaten

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down: 1. We use Apple Vision Pro (yes!!) to give the human operator first person control of the humanoid. Vision Pro parses human hand pose and retargets the motion to the robot hand, all in real time. From the human’s point of view, they are immersed in another body like the Avatar. Teleoperation is slow and time-consuming, but we can afford to collect a small amount of data. 2. We use RoboCasa, a generative simulation framework, to multiply the demonstration data by varying the visual appearance and layout of the environment. In Jensen’s keynote video below, the humanoid is now placing the cup in hundreds of kitchens with a huge diversity of textures, furniture, and object placement. We only have 1 physical kitchen at the GEAR Lab in NVIDIA HQ, but we can conjure up infinite ones in simulation. 3. Finally, we apply MimicGen, a technique to multiply the above data even more by varying the motion of the robot. MimicGen generates vast number of new action trajectories based on the original human data, and filters out failed ones (e.g. those that drop the cup) to form a much larger dataset. To sum up, given 1 human trajectory with Vision Pro -> RoboCasa produces N (varying visuals) -> MimicGen further augments to NxM (varying motions). This is the way to trade compute for expensive human data by GPU-accelerated simulation. A while ago, I mentioned that teleoperation is fundamentally not scalable, because we are always limited by 24 hrs/robot/day in the world of atoms. Our new GR00T synthetic data pipeline breaks this barrier in the world of bits. Scaling has been so much fun for LLMs, and it's finally our turn to have fun in robotics! We are building tools to enable everyone in the ecosystem to scale up with us. Links in thread:

Jim Fan

364,721 Aufrufe • vor 2 Jahren

The Koala gripper is a co-designed system that pairs a handheld data collection device and a robotic gripper, allowing a single operator to easily record task demonstrations. Engineered with three controllable degrees of freedom and force-optimized triggers, the device enables complex, human-like object interactions. Training on a dataset of several hundred demonstrations has yielded successful policies, while unlocking capabilities outside the realm of parallel jaw grippers. By facilitating the transfer of intuitive human techniques to robotic platforms, the Koala gripper bridges the gap between human actions and autonomous dexterous manipulation. Learn more:

The Koala gripper is a co-designed system that pairs a handheld data collection device and a robotic gripper, allowing a single operator to easily record task demonstrations. Engineered with three controllable degrees of freedom and force-optimized triggers, the device enables complex, human-like object interactions. Training on a dataset of several hundred demonstrations has yielded successful policies, while unlocking capabilities outside the realm of parallel jaw grippers. By facilitating the transfer of intuitive human techniques to robotic platforms, the Koala gripper bridges the gap between human actions and autonomous dexterous manipulation. Learn more:

RAI Institute

18,978 Aufrufe • vor 1 Monat

Tony Blair and Oracle co-founder Larry Ellison plan to use digital ID to "unify" all data on each country's citizens "so it can be consumed and used by" their AI models. "We have to take all of this data... and move it into a single... unified data platform." "When we want to ask a question, we've provided that AI model with all the data they need to understand our country." "We need to unify all of the national data, put it into a database where it's easily consumable by the AI model, and then ask whatever question you like."

Tony Blair and Oracle co-founder Larry Ellison plan to use digital ID to "unify" all data on each country's citizens "so it can be consumed and used by" their AI models. "We have to take all of this data... and move it into a single... unified data platform." "When we want to ask a question, we've provided that AI model with all the data they need to understand our country." "We need to unify all of the national data, put it into a database where it's easily consumable by the AI model, and then ask whatever question you like."

Wide Awake Media

54,156 Aufrufe • vor 11 Monaten

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

Roblox

288,814 Aufrufe • vor 8 Monaten

We've released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference. This work is led by PhD students Ava Pun, Kangle Deng, Ruixuan Liu, and in collaboration with CMU faculty Changliu Liu and Deva Ramanan. LegoGPT is a small first step towards the ultimate goal of generative manufacturing of physical objects. Our implementation is limited to 20x20x20 dimensions, 21 object categories, and simple brick types, but we are working on scaling it up! Code: Website: Demo:

We've released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference. This work is led by PhD students Ava Pun, Kangle Deng, Ruixuan Liu, and in collaboration with CMU faculty Changliu Liu and Deva Ramanan. LegoGPT is a small first step towards the ultimate goal of generative manufacturing of physical objects. Our implementation is limited to 20x20x20 dimensions, 21 object categories, and simple brick types, but we are working on scaling it up! Code: Website: Demo:

Jun-Yan Zhu

38,913 Aufrufe • vor 1 Jahr

Larry Ellison—owner of Oracle, CBS, and now TikTok—tells Tony Blair about his plan to use digital ID to "unify" all data on each country's citizens "so it can be consumed and used by" his AI models. "We have to take all of this data... and move it into a single, if you will, unified data platform." "When we want to ask a question, we've provided that AI model with all the data they need to understand our country." "We need to unify all of the national data, put it into a database where it's easily consumable by the AI model, and then ask whatever question you like."

Larry Ellison—owner of Oracle, CBS, and now TikTok—tells Tony Blair about his plan to use digital ID to "unify" all data on each country's citizens "so it can be consumed and used by" his AI models. "We have to take all of this data... and move it into a single, if you will, unified data platform." "When we want to ask a question, we've provided that AI model with all the data they need to understand our country." "We need to unify all of the national data, put it into a database where it's easily consumable by the AI model, and then ask whatever question you like."

Wide Awake Media

144,707 Aufrufe • vor 8 Monaten

[] = edited info for privacy "I am a [Major US Carrier] A320/321 Captain, the following sighting occurred during one of my flights recently. Since I have shared my story, several other [Major US Carrier] pilots have reached out to me and shared their similar experiences, including sharing their video recordings of these objects from the Flight Levels. All seen at the base of the big dipper. [Last week of July], 2023, I departed Santo Domingo DR at 2305 destined for New York JFK. My route of flight was L453 in NY Oceanic airspace, non radar hundreds of miles offshore. At approximately 1 hour into the flight as we were approaching the southern boundary of the NY oceanic airspace, and at 32,000 feet, I called out a visual on traffic that was excessively bright and looked like about 80 miles range... and then disappeared visually. I never saw the traffic on TCAS. Then a few minutes later I saw two objects round in shape, one lighted and one not flying in a formation just above the horizon, at a range I guessed of 120-200 NM. The object/s would illuminate to be as bright as a star for several seconds, then go dark for a few minutes, only to illuminate again. The brightness would vary from bright to very bright to dark. The color of the lighted object was white light. There was a second object you can clearly see in the photos that would follow the illuminated object, but it would not illuminate itself. Except for the 3:10-3:30 second point of my video I think you can see the second object illuminate. This went on for the remaining 2-2.5 hours of my flight to NY on L453 in Oceanic airspace. After reviewing the photos, I think the objects might have been a bit further away, but distance is very difficult to gauge at night. I have the brand new Samsung S23 phone which has the best camera on the market for a cell phone and I started recording this object in video. I have a great 7 min video of it appearing and disappearing while I was talking to other airliners on 123.45 vhf about it. You can hear that conversation in the video! Another airliner approximately 400 NM ahead of us at 36,000 feet stated they saw the same thing. I also took about 30 photos of these objects in "night mode" on the phone and they came out really good... in one of them you can actually see the lighted object and the unlit object very clearly as round metallic objects. All of the photos were taken with some sort of long exposure setting to be able to get as much light as possible to the sensor... You will be able to see in the long exposure photos the stars are pins of light but the UFO's are streaks of light because they are moving! It is actually amazing! All of this happened over about a 2.5 hour flight and continued for the entirety of our flight. The light seemed to be on or just above the horizon until we got closer to our destination of NY. Just prior to beginning our descent the objects appeared much higher in the sky 80-90 degrees above the horizon and much further away, actually out of the atmosphere."

Ryan Graves

694,787 Aufrufe • vor 3 Jahren