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.

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks,... show more

LeRobot

18,487 subscribers

12,495 views • 14 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

LeRobot

22,229 views • 25 days ago

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 views • 1 month ago

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

21,707 views • 28 days ago

Most C Programmers don't have a clue as to how the CPU works. Here is a lecture from my course on the C Language that introduces how to visualise the CPU as a C (or general software) Programmer.... More Details are at: Being able to model the behaviour of CPU provides a solid base to reason about your code. The summary is - - The CPU is a state machine which maintains it's states in registers. - It has busses to memory for requesting data/instruction read/writes. - Interrupts to attend to events. I discuss this and more in my course on the C Language.

Most C Programmers don't have a clue as to how the CPU works. Here is a lecture from my course on the C Language that introduces how to visualise the CPU as a C (or general software) Programmer.... More Details are at: Being able to model the behaviour of CPU provides a solid base to reason about your code. The summary is - - The CPU is a state machine which maintains it's states in registers. - It has busses to memory for requesting data/instruction read/writes. - Interrupts to attend to events. I discuss this and more in my course on the C Language.

Piyush Itankar

28,019 views • 1 year ago

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

213,040 views • 2 days ago

Your robot can now see in depth 👀📏 LeRobot v0.6.0 adds real end-to-end depth support. Plug in an Intel RealSense, set use_depth: true, and depth maps join your RGB observations automatically: captured in millimeters, compressed into compact 12-bit depth video alongside your normal camera streams, and decoded back to physical units at training time. Depth renders live while you record and in the dataset viewer, and it works across SO-100/101, Koch, OpenArm, reBot, Unitree G1 and more. You also get full control over how everything gets encoded, RGB or depth, codec, quality, presets, all of it. More on how it works:

Your robot can now see in depth 👀📏 LeRobot v0.6.0 adds real end-to-end depth support. Plug in an Intel RealSense, set use_depth: true, and depth maps join your RGB observations automatically: captured in millimeters, compressed into compact 12-bit depth video alongside your normal camera streams, and decoded back to physical units at training time. Depth renders live while you record and in the dataset viewer, and it works across SO-100/101, Koch, OpenArm, reBot, Unitree G1 and more. You also get full control over how everything gets encoded, RGB or depth, codec, quality, presets, all of it. More on how it works:

LeRobot

30,424 views • 24 days ago

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

CJ Zafir

39,716 views • 1 month ago

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.

Gipp 🦅

10,776 views • 1 month ago

We asked James Wang why Cerebras can run large models so quickly. His answer: Inference speed is mostly a memory problem. Instead of constantly pulling weights from external memory, Cerebras splits the model across multiple wafers and pipelines the layers together. “Inference is all about memory bandwidth.” “You don’t want to store weights external to the wafer, because the second it’s outside, it becomes much slower.” “We put the weights on the inside.” “The team built a new software stack that basically lets us split the models by layer and store them layer by layer across multiple wafers.” “That allows us to never have to read from external memory, and that’s what makes it so fast.” “For context, Claude is about 100 tokens per second.”

We asked James Wang why Cerebras can run large models so quickly. His answer: Inference speed is mostly a memory problem. Instead of constantly pulling weights from external memory, Cerebras splits the model across multiple wafers and pipelines the layers together. “Inference is all about memory bandwidth.” “You don’t want to store weights external to the wafer, because the second it’s outside, it becomes much slower.” “We put the weights on the inside.” “The team built a new software stack that basically lets us split the models by layer and store them layer by layer across multiple wafers.” “That allows us to never have to read from external memory, and that’s what makes it so fast.” “For context, Claude is about 100 tokens per second.”

MTS

27,935 views • 2 months ago

I find it wild that Physical Intelligence robotics models can work at all given that they only have a 1 second context length. As the robot is moving around a room and cleaning up a table, it only sees the current timestamp of images from the cameras (plus the text description of its task). I asked Sergey Levine was how this model can work at all. If a human had to execute a many minutes long plan in order to accomplish a physical task, but had her memory reset every second, there's no way she could pull it off But somehow just knowing what state the world is literally in this moment is all you need to know to keep a reasonably complication plan going? Sergey's answer calls on Morevac's Paradox, and I thought it was quite interesting. Full episode out tomorrow!

I find it wild that Physical Intelligence robotics models can work at all given that they only have a 1 second context length. As the robot is moving around a room and cleaning up a table, it only sees the current timestamp of images from the cameras (plus the text description of its task). I asked Sergey Levine was how this model can work at all. If a human had to execute a many minutes long plan in order to accomplish a physical task, but had her memory reset every second, there's no way she could pull it off But somehow just knowing what state the world is literally in this moment is all you need to know to keep a reasonably complication plan going? Sergey's answer calls on Morevac's Paradox, and I thought it was quite interesting. Full episode out tomorrow!

Dwarkesh Patel

125,151 views • 10 months ago

$QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.$

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 views • 3 months ago

The 1000th episode of the No Laying Up podcast is available now in your feeds and we take a look back at the winding road we took to get here. Favorite episodes, hardest you’ve laughed, most stressful moments and more - this one is a fun trip down memory lane and a great reminder of how NLU has grown and changed over the years. No Laying Up Episode 1000 is available now wherever you get your podcasts, we hope you enjoy it.

The 1000th episode of the No Laying Up podcast is available now in your feeds and we take a look back at the winding road we took to get here. Favorite episodes, hardest you’ve laughed, most stressful moments and more - this one is a fun trip down memory lane and a great reminder of how NLU has grown and changed over the years. No Laying Up Episode 1000 is available now wherever you get your podcasts, we hope you enjoy it.

No Laying Up

101,041 views • 1 year ago

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

466,333 views • 1 year ago

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.

Alex Veremeyenko

16,147 views • 14 days ago

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 views • 1 year ago

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

Taranjeet

471,972 views • 1 year ago

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

81,361 views • 2 months ago

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

Chris Paxton

20,486 views • 1 year ago

In my past research experience, finding or developing an appropriate simulation environment, dataset, and benchmark has always been a challenge. Missing features, limited support, or unexpected bugs often occupied my days and nights. Moreover, current simulation platforms are relatively fragmented—making it challenging to replicate the success of the RT-X dataset in unifying community efforts. Introducing RoboVerse, we provide a unified platform, dataset, and benchmark for scalable and generalizable robot learning. We hope to build a shared foundation to combine the community efforts. RoboVerse includes: MetaSim: We carefully designed a configuration system and a universal interface to align current robotic simulators. With MetaSim, you can use any simulator with the same code—bringing together the community’s diverse efforts under one framework! RoboVerse Dataset and Benchmark: We unify popular simulation environments and benchmarks into a single cohesive system and introduce the RoboVerse dataset—a large-scale, high-quality synthetic dataset. Additionally, we propose a standardized benchmark across both imitation learning and reinforcement learning. A cool feature enabled by our unified framework: Hybrid Simulation! You can now integrate physics engines and renderers from different simulators—e.g., using MuJoCo precise physics with Isaac photorealistic rendering. This not only elevates simulation fidelity but also significantly enhances real-world transfer performance across complex robotic applications. Hopefully, our team’s efforts could serve the robotic community to thrive vibrantly in the years to come. RoboVerse is open-sourced🥳!!! Project Page: Documentation: Github Repo: Paper:

In my past research experience, finding or developing an appropriate simulation environment, dataset, and benchmark has always been a challenge. Missing features, limited support, or unexpected bugs often occupied my days and nights. Moreover, current simulation platforms are relatively fragmented—making it challenging to replicate the success of the RT-X dataset in unifying community efforts. Introducing RoboVerse, we provide a unified platform, dataset, and benchmark for scalable and generalizable robot learning. We hope to build a shared foundation to combine the community efforts. RoboVerse includes: MetaSim: We carefully designed a configuration system and a universal interface to align current robotic simulators. With MetaSim, you can use any simulator with the same code—bringing together the community’s diverse efforts under one framework! RoboVerse Dataset and Benchmark: We unify popular simulation environments and benchmarks into a single cohesive system and introduce the RoboVerse dataset—a large-scale, high-quality synthetic dataset. Additionally, we propose a standardized benchmark across both imitation learning and reinforcement learning. A cool feature enabled by our unified framework: Hybrid Simulation! You can now integrate physics engines and renderers from different simulators—e.g., using MuJoCo precise physics with Isaac photorealistic rendering. This not only elevates simulation fidelity but also significantly enhances real-world transfer performance across complex robotic applications. Hopefully, our team’s efforts could serve the robotic community to thrive vibrantly in the years to come. RoboVerse is open-sourced🥳!!! Project Page: Documentation: Github Repo: Paper:

Haoran Geng

84,249 views • 1 year ago

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,078 views • 15 days ago