正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

✨✨ Announcing Open Source Dataset from excavators in real construction sites retrofitted by Flywheel (YC S25)! ✨✨ This 100hrs of observation+action data enables training autonomy models for excavators. We were able to train a small task model from 6 hours of dataset on a Kubota U17 on Y Combinator... show more

Jash Mota

1,167 subscribers

36,631 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 条评论

Jash Mota 的头像

Jash Mota1 年前

Dataset link:

Vai Viswanathan 的头像

Vai Viswanathan1 年前

@flywheel_inc Yo! Major shoutout for open sourcing the data

Jash Mota 的头像

Jash Mota1 年前

@flywheel_inc Thanks man!

Pranav Ashok 的头像

Pranav Ashok1 年前

@flywheel_inc Amazing, congrats!

Mohamed Anis 的头像

Mohamed Anis1 年前

@flywheel_inc The leap from simulated to real world autonomy hinges on datasets like this where edge case density is orders of magnitude higher

nicov 的头像

nicov1 年前

@flywheel_inc banger 🔥🔥🔥

Ivan @ FF Classroom 的头像

Ivan @ FF Classroom1 年前

@flywheel_inc This looks amazing!

Neil Nie 的头像

Neil Nie1 年前

@flywheel_inc This is awesome! Congrats guys!

Jash Mota 的头像

Jash Mota1 年前

@flywheel_inc Thanks Neil!

Trevor Healy 的头像

Trevor Healy1 年前

@flywheel_inc Sweet!

ζ Pedram ζ 的头像

ζ Pedram ζ1 年前

@flywheel_inc Oh yea

₭URO𓃵 的头像

₭URO𓃵1 年前

@flywheel_inc Hey man, nice work, dm me plz

相关视频

Flywheel AI (Flywheel (YC S25)) lets construction crews operate excavators remotely, improving safety and productivity. They're already deployed on various sites and collect operation data to automate excavation workflows. Congrats on the launch, Jash Mota & Mahimana!

Flywheel AI (Flywheel (YC S25)) lets construction crews operate excavators remotely, improving safety and productivity. They're already deployed on various sites and collect operation data to automate excavation workflows. Congrats on the launch, Jash Mota & Mahimana!

Y Combinator

61,576 次观看 • 1 年前

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

✨ Introducing 𝐎𝐩𝐞𝐧𝐕𝐋𝐀 — an open-source vision-language-action model for robotics! 👐 - SOTA generalist policy - 7B params - outperforms Octo, RT-2-X on zero-shot evals 🦾 - trained on 970k episodes from OpenX dataset 🤖 - fully open: model/code/data all online 🤗 🧵👇

Moo Jin Kim

227,218 次观看 • 2 年前

Inside Jash Mota's robot startup that lets people run excavators (construction equipment) remotely. Advanced teleoperation has its place and it's here. Flywheel (YC S25) lets humans control equipment in a much nicer way than having to get out in the hot sun on a vibrating, loud, smelly tractor and Jash shows me around the humble beginnings of his company that just went through Y Combinator.

Inside Jash Mota's robot startup that lets people run excavators (construction equipment) remotely. Advanced teleoperation has its place and it's here. Flywheel (YC S25) lets humans control equipment in a much nicer way than having to get out in the hot sun on a vibrating, loud, smelly tractor and Jash shows me around the humble beginnings of his company that just went through Y Combinator.

Robert Scoble

11,891 次观看 • 1 年前

Demo Day for Y Combinator F25 is Wednesday! ✨ Reply "F25" for a link to a spreadsheet with the companies, their revenue, customers, and founder backgrounds. Made in minutes with Riveter (YC F24).

Demo Day for Y Combinator F25 is Wednesday! ✨ Reply "F25" for a link to a spreadsheet with the companies, their revenue, customers, and founder backgrounds. Made in minutes with Riveter (YC F24).

Abby Grills

23,786 次观看 • 11 个月前

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable"✨ We train a 350M-param generative world model on a large dataset w/ 210 tasks and show that we can predict *when* hallucination happens and use that to fix it! 🧵1/n

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable"✨ We train a 350M-param generative world model on a large dataset w/ 210 tasks and show that we can predict when hallucination happens and use that to fix it! 🧵1/n

Nicklas Hansen

59,934 次观看 • 4 个月前

This is the best way to understand how ML models actually work! Use Drawdata to draw a 2D dataset in Jupyter. Use it to actively pick data from the widget and update the model as the data is being drawn! Fully interactive, real-time, and open-source!

This is the best way to understand how ML models actually work! Use Drawdata to draw a 2D dataset in Jupyter. Use it to actively pick data from the widget and update the model as the data is being drawn! Fully interactive, real-time, and open-source!

Daily Dose of Data Science

52,132 次观看 • 1 年前

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Matt Shumer

383,384 次观看 • 2 年前

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,464 次观看 • 3 年前

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵

David Duvenaud

1,468,950 次观看 • 6 个月前

say hi to kled v3, the data collection layer for agi. any dataset a lab can describe, collected from the real world by 500,000 people in under 72 hours.

say hi to kled v3, the data collection layer for agi. any dataset a lab can describe, collected from the real world by 500,000 people in under 72 hours.

Avi Patel

1,271,200 次观看 • 1 个月前

Also fine-tuned NVIDIA Gr00T N1.5 on TWIST2 dataset Due to lack of realistic sim, we stick with replaying an observation and inferring action chunks realtime on a H100 Model fits well!

Also fine-tuned NVIDIA Gr00T N1.5 on TWIST2 dataset Due to lack of realistic sim, we stick with replaying an observation and inferring action chunks realtime on a H100 Model fits well!

Arnie Ramesh

18,122 次观看 • 11 个月前

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

Vaibhav (VB) Srivastav

156,386 次观看 • 2 年前

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

Unitree

5,633,606 次观看 • 7 个月前

It's time for Y Combinator W25 Demo Day already! 💬✨Reply with "W25" and I'll DM you the spreadsheet with details on all companies in the batch, made with Riveter (YC F24). Making this list took minutes in Riveter.

It's time for Y Combinator W25 Demo Day already! 💬✨Reply with "W25" and I'll DM you the spreadsheet with details on all companies in the batch, made with Riveter (YC F24). Making this list took minutes in Riveter.

Abby Grills

31,366 次观看 • 1 年前

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 次观看 • 8 个月前

☀️Soaking up the last bits of summer🌊 ✨YCH model Comms OPEN in VGEN for $80✨ 🔗Link in the comments #Live2D #Vtuber

☀️Soaking up the last bits of summer🌊 ✨YCH model Comms OPEN in VGEN for $80✨ 🔗Link in the comments #Live2D #Vtuber

DG_studio@Art&Live2D(commision open)

14,030 次观看 • 1 年前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 2 年前

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Over the Reality 🌐

34,785 次观看 • 2 个月前

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

252,658 次观看 • 2 个月前