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.

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

stash

9,240 subscribers

228,761 Aufrufe • vor 6 Monaten •via X (Twitter)

Nachrichten & Politik Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

16 Kommentare

Profilbild von aksh parekh

aksh parekhvor 6 Monaten

the future of AI is NOT chatbots, but AI creating actions THROUGH ROBOTS! I love your work. this will fuel this revolution!

Profilbild von ⚪️ sierra catalina

⚪️ sierra catalinavor 6 Monaten

woah. lfg.

Profilbild von Kyle Drake

Kyle Drakevor 6 Monaten

Great! Thankyou. Cute tangible interface

Profilbild von aryan mahajan

aryan mahajanvor 6 Monaten

super cool!

Profilbild von DaveTheBasha

DaveTheBashavor 6 Monaten

cool. could you somehow use this on a drone so i could clean gutters? lol

Profilbild von BoldHyun

BoldHyunvor 6 Monaten

SpatialMemory2 builds a multimodal data store in latent space for robot agents. Thousands of hours of video and lidar finally fitting into context. Open source! 🔥 #SpatialMemory2

Profilbild von AnhPhu Nguyen

AnhPhu Nguyenvor 6 Monaten

WOW this literally looks like iron man’s lab

Profilbild von Gil G 🇺🇸

Gil G 🇺🇸vor 6 Monaten

This just like Black Mirror!

Profilbild von Federico Martelli

Federico Martellivor 6 Monaten

persistent spatial memory is the missing layer. context windows were never built for production robots.

Profilbild von Unshackled Pursuit

Unshackled Pursuitvor 6 Monaten

This is nice.

Profilbild von Saïd Aitmbarek

Saïd Aitmbarekvor 6 Monaten

brilliant spatio-temporal angle mate pre-computing embeddings/cosine makes it perfect for multimodal queries. let’s go!

Profilbild von KubaS

KubaSvor 6 Monaten

Amazing - the memory is currently one of the most missing pieces. Especially interesting about storing it in latent space. I must see what the representations look like. Kudos for opensourcing!

Profilbild von hiro

hirovor 6 Monaten

cool

Profilbild von Archana

Archanavor 5 Monaten

that looks so cool

Profilbild von Naiam

Naiamvor 5 Monaten

@humandroidinc

Profilbild von ToniP

ToniPvor 6 Monaten

Curious how SpatialMemory2 handles temporal decay. Robot context shifts a lot: lighting, scene rearrangement, objects moved between sessions. Does the latent store age out stale embeddings, or is it weighted by recency at query time? Asking because we ran into this on textual agent memory. Without some kind of forgetting, the store gets noisy fast.

Ähnliche Videos

Vibecode your robots on Dimensional. Simple demo of our physical agent stack running on the Unitree go2 quadruped. Developers can now program physical space & build dimensional applications via natural language. Fully open source.

Vibecode your robots on Dimensional. Simple demo of our physical agent stack running on the Unitree go2 quadruped. Developers can now program physical space & build dimensional applications via natural language. Fully open source.

stash

32,704 Aufrufe • vor 9 Monaten

Announcing the Dimensional Residency in Shenzhen. Deploy agents into the physical world. Real customers. Real deployments. We provide robots, $10,000 of LLM credits, free housing, office space, and customer intros to jumpstart your robotics company.

Announcing the Dimensional Residency in Shenzhen. Deploy agents into the physical world. Real customers. Real deployments. We provide robots, $10,000 of LLM credits, free housing, office space, and customer intros to jumpstart your robotics company.

stash

32,771 Aufrufe • vor 7 Monaten

Someone just put OpenClaw inside a Unitree G1 humanoid — and it walks. Same agent framework running on your phone. Now integrated with lidar, stereo + RGB cameras, understanding 3D space and temporal context. Works on drones and quadrupeds too. Fully open source. Cool work! Video Source: stash

Someone just put OpenClaw inside a Unitree G1 humanoid — and it walks. Same agent framework running on your phone. Now integrated with lidar, stereo + RGB cameras, understanding 3D space and temporal context. Works on drones and quadrupeds too. Fully open source. Cool work! Video Source: stash

Bo Wang

102,701 Aufrufe • vor 8 Monaten

3rd Place: GrokWorld uses Grok Imagine as a world model to generate synthetic training data for robots — augmenting or replacing months of manual collection in hours. Aptura AI

3rd Place: GrokWorld uses Grok Imagine as a world model to generate synthetic training data for robots — augmenting or replacing months of manual collection in hours. Aptura AI

SpaceX Super Intelligence

847,030 Aufrufe • vor 9 Monaten

[Open Source] Unitree First View Teleoperation for Humanoid Robots In order to advance the convenience of data collection for humanoid robots, we refer to other solutions to do the adaptation development and open source. Github： #Unitree #Humanoid #AGI #AI #EmbodiedIntelligence #Manipulation #Teleoperation #DataCollection

[Open Source] Unitree First View Teleoperation for Humanoid Robots In order to advance the convenience of data collection for humanoid robots, we refer to other solutions to do the adaptation development and open source. Github： #Unitree #Humanoid #AGI #AI #EmbodiedIntelligence #Manipulation #Teleoperation #DataCollection

Unitree

116,897 Aufrufe • vor 2 Jahren

We’re launching Judgment Labs today and announcing $32M in funding. As AI agents take on more of the work that creates economic value, they generate massive amounts of production data: the clearest record of how they behave with users, software, and the real world. Judgment builds infrastructure for improving AI agents from production data.

We’re launching Judgment Labs today and announcing $32M in funding. As AI agents take on more of the work that creates economic value, they generate massive amounts of production data: the clearest record of how they behave with users, software, and the real world. Judgment builds infrastructure for improving AI agents from production data.

Alex Shan

3,590,177 Aufrufe • vor 5 Monaten

My team is hiring in multimodal representation learning. We are working on tactile representations to equip robots with a physical understanding of the world. Bored of scraping disembodied internet data and looking for a new challenge? Apply here:

My team is hiring in multimodal representation learning. We are working on tactile representations to equip robots with a physical understanding of the world. Bored of scraping disembodied internet data and looking for a new challenge? Apply here:

Mustafa Mukadam

56,704 Aufrufe • vor 2 Jahren

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Databricks

47,044 Aufrufe • vor 1 Jahr

Your Openclaw / Agent can now control multiple robots in realtime. We’ve abstracted and standardized all hardware and control interfaces so your agent can run our spatial tool calls on ANY robot. Fleet command of humanoid, quadruped, xARM, and Piper arm in unison. Fully open source.

Your Openclaw / Agent can now control multiple robots in realtime. We’ve abstracted and standardized all hardware and control interfaces so your agent can run our spatial tool calls on ANY robot. Fleet command of humanoid, quadruped, xARM, and Piper arm in unison. Fully open source.

stash

17,225 Aufrufe • vor 8 Monaten

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Yuke Zhu

141,540 Aufrufe • vor 2 Jahren

🤖 China has launched a factory where robots build robots UBTECH Robotics has opened a “smart” factory in Liuzhou for the mass production of humanoid robots. Robots are already being used on the production line to help assemble other robots. The facility is designed to produce more than 10,000 humanoids a year, with a target rate of roughly one finished robot every 10 minutes. For now, it all looks like industrial automation. Skynet, please take a number and wait your turn.

🤖 China has launched a factory where robots build robots UBTECH Robotics has opened a “smart” factory in Liuzhou for the mass production of humanoid robots. Robots are already being used on the production line to help assemble other robots. The facility is designed to produce more than 10,000 humanoids a year, with a target rate of roughly one finished robot every 10 minutes. For now, it all looks like industrial automation. Skynet, please take a number and wait your turn.

NEXTA

45,655 Aufrufe • vor 1 Monat

Today, we are open-sourcing the Innate OS, the intuitive agentic OS for general-purpose robots 🎮 Try it today in our simulator and make the smartest robot ⬇️ Here is a demo with two robots collaborating We are entering the physical agents era, but building for mobile robots is still reserved for PhDs. We designed the Innate OS for intuitiveness, so that everyone can start automating their lives. Innate OS runs on our <$1k open-source robot or on your computer. It takes just a minute to build your first agent in our simulator.

Today, we are open-sourcing the Innate OS, the intuitive agentic OS for general-purpose robots 🎮 Try it today in our simulator and make the smartest robot ⬇️ Here is a demo with two robots collaborating We are entering the physical agents era, but building for mobile robots is still reserved for PhDs. We designed the Innate OS for intuitiveness, so that everyone can start automating their lives. Innate OS runs on our <$1k open-source robot or on your computer. It takes just a minute to build your first agent in our simulator.

Innate

63,340 Aufrufe • vor 1 Monat

Introducing DAPI by Diffusion Studio: a video editing CLI built for your coding agents. Generate motion graphics. Edit hours of footage. All by talking to Claude. This entire video? Prompted. 100%. Open source. Cross-platform.

Introducing DAPI by Diffusion Studio: a video editing CLI built for your coding agents. Generate motion graphics. Edit hours of footage. All by talking to Claude. This entire video? Prompted. 100%. Open source. Cross-platform.

konstantinpaulus

91,718 Aufrufe • vor 2 Monaten

Announcing Dimensional: the open-source OS for physical space. Command any robot in natural language. Program atoms, not bits.

Announcing Dimensional: the open-source OS for physical space. Command any robot in natural language. Program atoms, not bits.

stash

193,536 Aufrufe • vor 1 Jahr

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,967 Aufrufe • vor 2 Jahren

Robots should take your order, not your data Last week at KBW, peaq × World brought proof of human to robots in Seoul 🇰🇷

Robots should take your order, not your data Last week at KBW, peaq × World brought proof of human to robots in Seoul 🇰🇷

peaq

20,445 Aufrufe • vor 1 Monat

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 Aufrufe • vor 2 Jahren

Agents can now understand physical space and temporality on Dimensional. Input: “Find the model airplane” With SpatioTemporal RAG, our agent has an emergent understanding of objects, stairwells, and obstacles in latent space.

Agents can now understand physical space and temporality on Dimensional. Input: “Find the model airplane” With SpatioTemporal RAG, our agent has an emergent understanding of objects, stairwells, and obstacles in latent space.

stash

10,569 Aufrufe • vor 9 Monaten

1/ We’ve built Cosift, an open source collaborative index for agents. Whenever an agent requires a piece of data from the web, it can also index it in Cosift for easier later retrieval. Agents require the same data repeatedly, and do the costly and time consuming work every time. Cosift gives agents a collaborative space where they can index this data for easy retrieval. It’s open source and free, and its development is based on the 400B exchanges that were made so far on Pilot Protocol.

1/ We’ve built Cosift, an open source collaborative index for agents. Whenever an agent requires a piece of data from the web, it can also index it in Cosift for easier later retrieval. Agents require the same data repeatedly, and do the costly and time consuming work every time. Cosift gives agents a collaborative space where they can index this data for easy retrieval. It’s open source and free, and its development is based on the 400B exchanges that were made so far on Pilot Protocol.

Razvan Roman

75,924 Aufrufe • vor 1 Monat