Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory. Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇

Physical Intelligence

44,697 subscribers

449,223 views • 3 months ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Long-term memories don’t always rely on short-term ones. New research uncovers a parallel pathway to memory formation, reshaping how we understand and treat memory impairments.

Long-term memories don’t always rely on short-term ones. New research uncovers a parallel pathway to memory formation, reshaping how we understand and treat memory impairments.

Neuroscience News

42,444 views • 1 year ago

Smol now has short term and long term memory, can build up a conversation with clear progression through topics, and display emotional development. That means we can finally have a conversation about our favorite cars:

Smol now has short term and long term memory, can build up a conversation with clear progression through topics, and display emotional development. That means we can finally have a conversation about our favorite cars:

lord asado 🥩

73,323 views • 1 year ago

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,607 views • 1 year ago

Why having a goldfish memory is key to long-term success...

Why having a goldfish memory is key to long-term success...

Alan Stein, Jr.

53,357 views • 1 year ago

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory

AK

19,923 views • 9 months ago

Exhibit A: short term memory loss.

Exhibit A: short term memory loss.

north star radio ☀️

502,354 views • 1 year ago

1/3 Here's John Sweller talking about how transferring information from working memory to long-term memory transforms us. It's what makes education transformational. Such a fantastic person to have a conversation with. Link to full episode below.

1/3 Here's John Sweller talking about how transferring information from working memory to long-term memory transforms us. It's what makes education transformational. Such a fantastic person to have a conversation with. Link to full episode below.

Anna Stokke

17,076 views • 2 months ago

We've been testing Memory (short-term and long-term) on Perplexity for a while. The results are great, and we are rolling it out widely. You can ask personalized questions, questions about past chats, and use any model or search mode with personal context (both apps and web).

We've been testing Memory (short-term and long-term) on Perplexity for a while. The results are great, and we are rolling it out widely. You can ask personalized questions, questions about past chats, and use any model or search mode with personal context (both apps and web).

Aravind Srinivas

96,450 views • 6 months ago

Remember “Build Back Better” during COVID? The new psyop is: “Short-term pain for the long-term gain.” They must think people have the memory of a goldfish.

Remember “Build Back Better” during COVID? The new psyop is: “Short-term pain for the long-term gain.” They must think people have the memory of a goldfish.

Dr. Simon

43,022 views • 2 months ago

A quick little brain refresh for the guys with short term memory

A quick little brain refresh for the guys with short term memory

jaden

1,113,333 views • 1 year ago

How can #robots remember? 🤖 💭 For robots to understand and respond to questions that require complex multi-step reasoning in scenarios over long periods of time, we built ReMEmbR, a retrieval-augmented memory for embodied robots. 👀 Technical deep dive from #NVIDIAResearch ➡️

How can #robots remember? 🤖 💭 For robots to understand and respond to questions that require complex multi-step reasoning in scenarios over long periods of time, we built ReMEmbR, a retrieval-augmented memory for embodied robots. 👀 Technical deep dive from #NVIDIAResearch ➡️

NVIDIA AI Developer

30,485 views • 1 year ago

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

The Humanoid Hub

17,721 views • 4 months ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

157,523 views • 2 months ago

OpenAI Chief Scientist, Jakub Pachocki: The long-term research goal is to develop an "automated researcher" capable of discovering new scientific ideas "current models can reason for 1-5 hours" The next frontier is long-term planning and memory

OpenAI Chief Scientist, Jakub Pachocki: The long-term research goal is to develop an "automated researcher" capable of discovering new scientific ideas "current models can reason for 1-5 hours" The next frontier is long-term planning and memory

Haider.

157,653 views • 8 months ago

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored

🚨 AI News | TestingCatalog

41,003 views • 3 months ago

We are taking notes on everyone refusing to support women. Oh, and we don't have a short term memory. #HoldTheLine

We are taking notes on everyone refusing to support women. Oh, and we don't have a short term memory. #HoldTheLine

Rep. Nancy Mace

325,919 views • 1 year ago

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

Chen Wang

288,500 views • 3 years ago

"Long Term Memory System" showcase for an android|humanoid robot by Digit Robotics (华夏机器人) Source:

"Long Term Memory System" showcase for an android|humanoid robot by Digit Robotics (华夏机器人) Source:

Vokabre Robotics

12,408 views • 1 month ago

Big Pharma’s worst nightmare: Lion’s Mane. This medicinal mushroom supercharges memory, repairs nerves, and improves long-term memory. Here’s how to take it the right way (and avoid fake, harmful versions): 🧵

Big Pharma’s worst nightmare: Lion’s Mane. This medicinal mushroom supercharges memory, repairs nerves, and improves long-term memory. Here’s how to take it the right way (and avoid fake, harmful versions): 🧵

Healthy Wealthy 24/7

132,733 views • 9 months ago

If you want robots that can just live with you & help 24/7, it needs to build & update its memory on the fly. Current semantic memory representations like VoxelMap from OK-Robot can't change with the world. That's why we built DynaMem: dynamic memory for a changing, open world!

If you want robots that can just live with you & help 24/7, it needs to build & update its memory on the fly. Current semantic memory representations like VoxelMap from OK-Robot can't change with the world. That's why we built DynaMem: dynamic memory for a changing, open world!

Mahi Shafiullah 🏠🤖

29,659 views • 1 year ago