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。

🔥Introducing Rodin Gen-1 with RLHF 🏅the first time to bring #RLHF to #3D Generation, powered by over 100K generations and labels from our in-house artist team.💪🏃💨 (It’s not #Rodin Gen-1.5🤔 Try Rodin Gen-1 with RLHF now at #CG #GenerativeAI

Hyper3D by Deemos

15,259 subscribers

23,874 次观看 • 1 年前 •via X (Twitter)

科学技术 #RLHF #3D #Rodin #CG #GenerativeAI

Anya Rossi• Live Now

Private livecam show

7 条评论

Deemos 的头像

Deemos1 年前

Sorry for the issue on url, try

Wolfy 的头像

Wolfy1 年前

SSL cert expired

Deemos 的头像

Deemos1 年前

Thanks! Will address this soon, try for now

Erik Brossman 的头像

Erik Brossman1 年前

Hands down the best 3d generation tool on the marketplace. So happy with Rodin!

Deeznuttynutz 的头像

Deeznuttynutz1 年前

Can’t wait to try this

AI SHEET POST 的头像

AI SHEET POST1 年前

Would be really useful to have gui friendly featuee that trellis shown in paper by selection of separate segments of subject like hear or weapon or legs cause whole regens are really time consuming

Deemos 的头像

Deemos1 年前

soon

相关视频

🔥Image -> 3D -> 3D Print 🤖Now you can easily obtain your favorite figurine models using #Rodin Gen-1 and 3D printing at any time. #3dprint #GenerativeAI #3D #CG #game

🔥Image -> 3D -> 3D Print 🤖Now you can easily obtain your favorite figurine models using #Rodin Gen-1 and 3D printing at any time. #3dprint #GenerativeAI #3D #CG #game

Hyper3D🔜SIGGRAPH26

24,736 次观看 • 2 年前

🚀 Rodin Gen-1 is now open trials at 🔥Powered by 1.5B #3D Native Large Model, #Rodin creates assets with quad-faces and PBR in 40s. 🔮Rodin is closer than ever to being a production-ready 3D #GenAI tool. We believe it will bridge community to AI era.

🚀 Rodin Gen-1 is now open trials at 🔥Powered by 1.5B #3D Native Large Model, #Rodin creates assets with quad-faces and PBR in 40s. 🔮Rodin is closer than ever to being a production-ready 3D #GenAI tool. We believe it will bridge community to AI era.

Hyper3D by Deemos

206,194 次观看 • 2 年前

Text-to-3D with Blocks📦 Striving towards real-time creation on #Rodin Gen-1 with multiple 3D ControlNets! 🚀 Rodin Gen-1 will be the largest ever 3D large model, and we are planing to open it to public🎉 Stay tuned!

Text-to-3D with Blocks📦 Striving towards real-time creation on #Rodin Gen-1 with multiple 3D ControlNets! 🚀 Rodin Gen-1 will be the largest ever 3D large model, and we are planing to open it to public🎉 Stay tuned!

Hyper3D by Deemos

41,279 次观看 • 2 年前

🤯 Mind-blowing! Just witnessed the magic of #Palworld! 🔥 Check out the incredible Rodin Gen-1 🤖 transforming images into 3D models in just 10 seconds! 🚀 #CG #3D #game #GenerativeAI #GenAI #diffusion

🤯 Mind-blowing! Just witnessed the magic of #Palworld! 🔥 Check out the incredible Rodin Gen-1 🤖 transforming images into 3D models in just 10 seconds! 🚀 #CG #3D #game #GenerativeAI #GenAI #diffusion

Hyper3D by Deemos

114,781 次观看 • 2 年前

Image to 3D, built for detail🤯 Rodin Gen-2.5 helps create high-poly 3D assets with native textures, batch results, and adjustable generation effort. Try it in Hyper3D!

Image to 3D, built for detail🤯 Rodin Gen-2.5 helps create high-poly 3D assets with native textures, batch results, and adjustable generation effort. Try it in Hyper3D!

Hyper3D by Deemos

5,781,061 次观看 • 1 个月前

Yes‼️Introducing one of the new features of #Rodin Gen-2: Generate into Parts🔥 🤯For the first time, 3D GenAI truly understands the underlying structure of objects. Coming June 2025🚀 Demo made with Hugging Face Gradio #3D #MCP #b3d #Game #UE #Unity #GenerativeAI

Yes‼️Introducing one of the new features of #Rodin Gen-2: Generate into Parts🔥 🤯For the first time, 3D GenAI truly understands the underlying structure of objects. Coming June 2025🚀 Demo made with Hugging Face Gradio #3D #MCP #b3d #Game #UE #Unity #GenerativeAI

Hyper3D by Deemos

111,978 次观看 • 1 年前

🤯 Gemini 3.1 Pro Google DeepMind generates parametric 3D models straight from images! 🚀Paired with Rodin Gen-2 Edit's Refine, #Gemini effortlessly delivers million-face detailed #3D models. 🔥3D Generation workflows are evolving! See it in action 👇 #CG #Hyper3D

🤯 Gemini 3.1 Pro Google DeepMind generates parametric 3D models straight from images! 🚀Paired with Rodin Gen-2 Edit's Refine, #Gemini effortlessly delivers million-face detailed #3D models. 🔥3D Generation workflows are evolving! See it in action 👇 #CG #Hyper3D

Hyper3D🔜SIGGRAPH26

77,998 次观看 • 6 个月前

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!

ComfyUI

19,076 次观看 • 10 个月前

#SIGGRAPH2024 🚀So glad to announce that the foundation model behind #3D GenAI #Rodin Gen-1, CLAY has been officially accepted by ACM SIGGRAPH Technical Paper Journal Track. 🔥The final paper is still being prepared, but here's a sneak peek of its Technical Video❤️

#SIGGRAPH2024 🚀So glad to announce that the foundation model behind #3D GenAI #Rodin Gen-1, CLAY has been officially accepted by ACM SIGGRAPH Technical Paper Journal Track. 🔥The final paper is still being prepared, but here's a sneak peek of its Technical Video❤️

Hyper3D by Deemos

22,187 次观看 • 2 年前

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.

Muratcan Koylan

27,168 次观看 • 2 年前

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

AI at Meta

408,893 次观看 • 2 年前

New short course on Reinforcement Learning from Human Feedback! RLHF is one of the key techniques that led to the rise of modern LLMs. It is used to align LLMs with human preferences, to make them more honest, helpful and harmless, by (i) learning a reward function that mimics human preferences, as expressed in human-provided labels, then, (ii) tuning an LLM to generate outputs that receive a high reward. In this course, taught by Nikita Namjoshi, Developer Advocate for GenAI at Google Cloud, you'll learn the details of how RLHF works, including how to apply it to tune an LLM for your own applications. You'll also use an open source library to tune a base LLM to align with human preferences expressed in a training set, and evaluate the tuned model by comparing its responses before and after RLHF-tuning. Please sign up here!

New short course on Reinforcement Learning from Human Feedback! RLHF is one of the key techniques that led to the rise of modern LLMs. It is used to align LLMs with human preferences, to make them more honest, helpful and harmless, by (i) learning a reward function that mimics human preferences, as expressed in human-provided labels, then, (ii) tuning an LLM to generate outputs that receive a high reward. In this course, taught by Nikita Namjoshi, Developer Advocate for GenAI at Google Cloud, you'll learn the details of how RLHF works, including how to apply it to tune an LLM for your own applications. You'll also use an open source library to tune a base LLM to align with human preferences expressed in a training set, and evaluate the tuned model by comparing its responses before and after RLHF-tuning. Please sign up here!

Andrew Ng

205,562 次观看 • 2 年前

🚀 Introducing Meshy-4 — The next-gen 3D model generator is now available to everyone at ✨ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. ❤️ Watch the video and discover Meshy’s full potential with us!

🚀 Introducing Meshy-4 — The next-gen 3D model generator is now available to everyone at ✨ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. ❤️ Watch the video and discover Meshy’s full potential with us!

MeshyAI 🔜 gamescom

52,515 次观看 • 2 年前

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.

Generalist

84,081 次观看 • 16 天前

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

Travis Davids

61,232 次观看 • 1 年前

Welcome to the next Gen #WEB3 Wallet, powered by BREG your personal A.I. Assistant, created with ❤️ by #iLuminaryAI 🙌🏼 Join our waitlist now for a unique opportunity to try our app for free and become eligible for our upcoming token airdrop. Don't miss out, limited spots available!

Welcome to the next Gen #WEB3 Wallet, powered by BREG your personal A.I. Assistant, created with ❤️ by #iLuminaryAI 🙌🏼 Join our waitlist now for a unique opportunity to try our app for free and become eligible for our upcoming token airdrop. Don't miss out, limited spots available!

Iluminary

98,045 次观看 • 2 年前

At CES 2026, the NEURA Robotics team debuted the next-gen 4NE-1 and its new smaller sibling. Preorders for the 4NE-1 v3.5 are live now. Price: €98,000 (Drops to €60,000 for 20+ units) Check out our quick conversation with CEO David Reger at the booth.

At CES 2026, the NEURA Robotics team debuted the next-gen 4NE-1 and its new smaller sibling. Preorders for the 4NE-1 v3.5 are live now. Price: €98,000 (Drops to €60,000 for 20+ units) Check out our quick conversation with CEO David Reger at the booth.

The Humanoid Hub

42,553 次观看 • 7 个月前

Privacy-first research is the core of everything we do at Project Aria. 🛡️✨ We’re thrilled to release EgoBlur Gen 2—our next-gen open-source solution for preserving privacy in egocentric video. Key Features: ✅ Optimized for Gen 2! Tuned for high-res data & next-gen hardware ⚡️ ✅ Native for VRS, MP4, JPEG, and PNG EgoBlur Gen 2 helps you automatically detect and obscure faces and license plates on egocentric cameras from Aria Gen 2 with ease. 🔍 Dive into the models: 👉

Privacy-first research is the core of everything we do at Project Aria. 🛡️✨ We’re thrilled to release EgoBlur Gen 2—our next-gen open-source solution for preserving privacy in egocentric video. Key Features: ✅ Optimized for Gen 2! Tuned for high-res data & next-gen hardware ⚡️ ✅ Native for VRS, MP4, JPEG, and PNG EgoBlur Gen 2 helps you automatically detect and obscure faces and license plates on egocentric cameras from Aria Gen 2 with ease. 🔍 Dive into the models: 👉

Project Aria @Meta

20,069 次观看 • 3 个月前

#WATCH | Ranchi, Jharkhand | President of the All India Students Association, Neha Bora says, "We call them Gen Z because the young mass of this country will be eligible to vote in some time or became eligible to vote in the last few years. Several of the students who are Gen Z, are sitting at Jaipal Singh Munda Stadium right now. So, BJP-RSS can try all they like, PM can make videos after videos and their MPs can act strangely in the Parliament to make themselves relatable to Gen Z, Mohan Bhagwat can interact with the Gen Z. But the deceit they did with the Gen Z, Millenials and every generation of this country resides in our memory. So, hijacking student movement is not something possible for them. Honestly, they do not know how to participate in students' movement. If they knew, they would not have turned violent in today's march which was for the students."

#WATCH | Ranchi, Jharkhand | President of the All India Students Association, Neha Bora says, "We call them Gen Z because the young mass of this country will be eligible to vote in some time or became eligible to vote in the last few years. Several of the students who are Gen Z, are sitting at Jaipal Singh Munda Stadium right now. So, BJP-RSS can try all they like, PM can make videos after videos and their MPs can act strangely in the Parliament to make themselves relatable to Gen Z, Mohan Bhagwat can interact with the Gen Z. But the deceit they did with the Gen Z, Millenials and every generation of this country resides in our memory. So, hijacking student movement is not something possible for them. Honestly, they do not know how to participate in students' movement. If they knew, they would not have turned violent in today's march which was for the students."

ANI

41,815 次观看 • 14 天前