正在加载视频...

视频加载失败

返回首页

Coarse2Real (C2R) transfers simple 3D renderings into realistic style video. Check our paper and project page to learn how to hedge small amount of synthetic paired data with real non-pair data for training the C2R model. We will release the model soon!

Papagina_Yi's profile picture

Yi Zhou

1,383 subscribers

12,406 次观看 • 4 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Announcing our commercial partnership with Booster Robotics Booster builds humanoid robot hardware, OS, and developer tools to make humanoid robots more affordable, reliable, and practical. The partnership centers on using simulation to multiply the value of real-robot data—expanding teleoperation demonstrations into scalable training data across diverse tasks and scenes. This joint effort powers sim-real co-training and foundation-model development, accelerating progress from hardware iteration to deployable robot policies. Together, we're building simulation‑powered data infrastructure for Physical AI — making scalable training data accessible to model developers and the broader robotics ecosystem.
0:12

Announcing our commercial partnership with Booster Robotics Booster builds humanoid robot hardware, OS, and developer tools to make humanoid robots more affordable, reliable, and practical. The partnership centers on using simulation to multiply the value of real-robot data—expanding teleoperation demonstrations into scalable training data across diverse tasks and scenes. This joint effort powers sim-real co-training and foundation-model development, accelerating progress from hardware iteration to deployable robot policies. Together, we're building simulation‑powered data infrastructure for Physical AI — making scalable training data accessible to model developers and the broader robotics ecosystem.

Axis Robotics

67,421 次观看 • 22 天前

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
0:13

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 次观看 • 1 年前

My sister and I are putting great care into the physics of our 3D customizable vtuber avatar! -^u^- We wanna make the tails as flowy as possible! 🐾 Here is the link to our model's preview page! A guide on how to use the model will be uploaded soon 🩷
0:13

My sister and I are putting great care into the physics of our 3D customizable vtuber avatar! -^u^- We wanna make the tails as flowy as possible! 🐾 Here is the link to our model's preview page! A guide on how to use the model will be uploaded soon 🩷

Pastell & Palette🤍 3D Customizable Model!

14,921 次观看 • 10 个月前

Thanks for the tweet. We improve 3D Gaussain splatting for dash cam videos that contain serious reflections and obstructions. With Dash cam videos, it's possible to leverage massive driving data. Visit our page at Codes will be soon.
0:11

Thanks for the tweet. We improve 3D Gaussain splatting for dash cam videos that contain serious reflections and obstructions. With Dash cam videos, it's possible to leverage massive driving data. Visit our page at Codes will be soon.

Xiao-Xiao Long

44,444 次观看 • 2 年前

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.
0:18

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.

Alec Helbling

65,484 次观看 • 3 个月前

Today, we will build a ✈️ Flight Price comparison app in 📱React Native, similar to Skyscanner, Google Flights, and Kayak The challenging part is getting real data about flight prices. We will learn how to Scrape the WEB and unlock any data 👀 See you soon 👋
0:16

Today, we will build a ✈️ Flight Price comparison app in 📱React Native, similar to Skyscanner, Google Flights, and Kayak The challenging part is getting real data about flight prices. We will learn how to Scrape the WEB and unlock any data 👀 See you soon 👋

Vadim Savin @notJust.dev

176,942 次观看 • 2 年前

A Letter to Our Community: The Road Ahead for Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷
0:13

A Letter to Our Community: The Road Ahead for Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷

Axis Robotics

27,858 次观看 • 7 个月前

It's almost out! In just 3 hours, our 3D vtuber customizable model will release! 🩷-^u^- Stay tuned for full showcase! For those new to 3D or Warudo, a guide on how to use the model will be included <3
0:16

It's almost out! In just 3 hours, our 3D vtuber customizable model will release! 🩷-^u^- Stay tuned for full showcase! For those new to 3D or Warudo, a guide on how to use the model will be included <3

Pastell & Palette🤍 3D Customizable Model!

21,293 次观看 • 9 个月前

The Blender Grease Pencil is great for 2D animation, storyboarding, 3D sketching, illustrating, and allows devs to draw directly into the 3D viewport. Check out SIMON BLAKENEY's tutorial on how to bring Grease Pencil data over to the Epic Ecosystem of tools and start creating non-photorealistic styles!:
0:19

The Blender Grease Pencil is great for 2D animation, storyboarding, 3D sketching, illustrating, and allows devs to draw directly into the 3D viewport. Check out SIMON BLAKENEY's tutorial on how to bring Grease Pencil data over to the Epic Ecosystem of tools and start creating non-photorealistic styles!:

Unreal Engine

15,464 次观看 • 11 个月前

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.
0:12

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.

AI at Meta

195,607 次观看 • 1 年前

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.
0:13

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.

CYANPUPPETS

36,997 次观看 • 5 个月前

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗
0:15

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗

NVIDIA AI

40,359 次观看 • 11 个月前

Our 1st Acquisition We've made a significant leap forward by officially acquiring Nidum, a decentralized AI computing platform poised to redefine blockchain intelligence and AI decentralization. With Nidums decentralized computing power, AI model training and global resource pool, we are now positioned at the forefront of blockchain driven AI innovation. What does that mean for our ecosystem? ✅ Scalable AI solutions powered by blockchain ✅ Decentralized AI model training & data privacy ✅ Expanded $BCUT utility in the AI economy Explore the dedicated website page to learn why this acquisition is a game changer for the our ecosystem and AI decentralization.
0:17

Our 1st Acquisition We've made a significant leap forward by officially acquiring Nidum, a decentralized AI computing platform poised to redefine blockchain intelligence and AI decentralization. With Nidums decentralized computing power, AI model training and global resource pool, we are now positioned at the forefront of blockchain driven AI innovation. What does that mean for our ecosystem? ✅ Scalable AI solutions powered by blockchain ✅ Decentralized AI model training & data privacy ✅ Expanded $BCUT utility in the AI economy Explore the dedicated website page to learn why this acquisition is a game changer for the our ecosystem and AI decentralization.

bitsCrunch

90,665 次观看 • 1 年前

Data Streaming 🤝 Data Intelligence Confluent and Databricks are teaming up to empower organizations with AI-ready, real-time data. Our seamless integrations between Tableflow, Delta Tables, and Unity Catalog will connect operational and analytical systems, to power AI-driven applications. Learn how we’re bridging the data divide in Jay Kreps and Ali Ghodsi’s blog ➡️
0:10

Data Streaming 🤝 Data Intelligence Confluent and Databricks are teaming up to empower organizations with AI-ready, real-time data. Our seamless integrations between Tableflow, Delta Tables, and Unity Catalog will connect operational and analytical systems, to power AI-driven applications. Learn how we’re bridging the data divide in Jay Kreps and Ali Ghodsi’s blog ➡️

Confluent

10,266 次观看 • 1 年前

System identification (sysid) is the process of finding the physical parameters that make a simulation match reality. If you're training an RL locomotion policy in simulation, the accuracy of your motor model directly affects how well the policy transfers to the real robot. A recent git commit by Kevin Zakka added a sysid toolbox to MuJoCo which automates this process: you provide recorded motor data and a MuJoCo model, and it optimizes the model parameters to minimize the difference between simulated and real trajectories. For my RobStride Dynamics RS02 QDD motors (17 Nm peak, 7.75:1 gear), I built a Rust tool that sends multi-sine torque excitation at 1 kHz and records position/velocity feedback. I then feed this data into MuJoCo's sysid optimizer.
0:11

System identification (sysid) is the process of finding the physical parameters that make a simulation match reality. If you're training an RL locomotion policy in simulation, the accuracy of your motor model directly affects how well the policy transfers to the real robot. A recent git commit by Kevin Zakka added a sysid toolbox to MuJoCo which automates this process: you provide recorded motor data and a MuJoCo model, and it optimizes the model parameters to minimize the difference between simulated and real trajectories. For my RobStride Dynamics RS02 QDD motors (17 Nm peak, 7.75:1 gear), I built a Rust tool that sends multi-sine torque excitation at 1 kHz and records position/velocity feedback. I then feed this data into MuJoCo's sysid optimizer.

David Bar

48,347 次观看 • 4 个月前

We are releasing the fastest TTS model as open source! One of the biggest problems we encountered while optimizing TTS models is optimization itself. Since it is LLM-based, even optimizing with VLLM and SgLang libraries is not enough. Additionally, I made the outputs much better with special optimizations for training. The voices you are listening to are results obtained from only 20% of the model training. We trained these outputs on 8xB200 in 24 hours. Even though the dataset includes some low-quality data, the model's output is much better. We will release the code as open source tomorrow. Data: Emilia-3m Model: EchoDit (custom) Codec: DacVae Opt: Flash-attn + CacheDit
0:12

We are releasing the fastest TTS model as open source! One of the biggest problems we encountered while optimizing TTS models is optimization itself. Since it is LLM-based, even optimizing with VLLM and SgLang libraries is not enough. Additionally, I made the outputs much better with special optimizations for training. The voices you are listening to are results obtained from only 20% of the model training. We trained these outputs on 8xB200 in 24 hours. Even though the dataset includes some low-quality data, the model's output is much better. We will release the code as open source tomorrow. Data: Emilia-3m Model: EchoDit (custom) Codec: DacVae Opt: Flash-attn + CacheDit

Kadir Nar

32,232 次观看 • 29 天前

which tutorial (+code) should I release next? > Left: 3D graph data viz > Right: Severance game projects are built with Three.js and mediapipe AI vision learn how to build real-time hand tracking apps for 3D design, games, etc.
0:12

which tutorial (+code) should I release next? > Left: 3D graph data viz > Right: Severance game projects are built with Three.js and mediapipe AI vision learn how to build real-time hand tracking apps for 3D design, games, etc.

AA

19,435 次观看 • 1 年前