dome | Outlier

It finally happened. We are releasing Stable Cascade (Würstchen v3) together with @StabilityAI ! And guess what? It‘s the best open-source text-to-image model now! You can find the blog post explaining everything here: stability.ai/news/introduci… 🧵 1/5

Introducing, Runway Characters. Real-time intelligent avatars that turn the internet into a conversation. Deployable anywhere via the Runway API, Runway Characters can be customized in any way across every style. All with the ability to embed bespoke knowledge banks, custom voices and instructions. Start integrating Runway Characters directly into your apps, websites, products and services today. Available now at the link below.

Beyond excited to share Uni-1 with the rest of the world!! 😍 This is by FAR the most ambitious, impressive and exciting model we have worked on @LumaLabsAI Multimodal intelligence will shape the future of generative media and I’m thrilled to share our flagship SOTA model 🤩

Really excited to share our newest release on a unified model that does understanding and generation all in one. The team really did a great job here!

@juancopi81 @VoidAsuka @eigenron ☺️

@VoidAsuka @eigenron +1 really like @dome_271

this video might not be a good explanation for beginners. i highly recommend videos by deepia and explainingAI for a deep thorough math-based understanding of diffusion / flow based models. highly underrated channels with exceptional teaching. also, the 3b1b/welch labs video on diffusion is meh. - @Deepia-ls2fo" target="_blank" rel="nofollow noopener">youtube.com/@Deepia-ls2fo - @Explaining-AI" target="_blank" rel="nofollow noopener">youtube.com/@Explaining-AI

Yey!

A good quote that ChatGPT chose for me today: "Creativity is the residue of time wasted." (Einstein) In the upcoming AI era, our worth will come from creativity instead of productivity. We'll have to fight the instincts we cultivated in the past grind era: the 996, the "need to listen to a podcast while cleaning the house to minimize time wasted". We'll have to embrace boredom, lack of structure and loose identities. Such a generational challenge.

Have you ever wondered how the DPO objective is derived and why it looks the way it does? And especially, where do we even start from to derive it? In my latest YouTube video I go into the details of the DPO objective. Let me know what you think! The link is in the next thread ⬇️ Also, are there any suggestions for video topics you have?

Just uploaded a new video on YouTube about Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO). The video shows the full math derivation of the objectives starting with a super intuitive objective! The link is in the thread below ⬇️ The video also shows the derivation of the REINFORCE objective and Importance Sampling and touches upon TRPO and much more! I hope you enjoy the video!

@BLVCKLIGHTai @runwayml Oh cool! I mean any surfboard can be super fun haha

@dome_271 @runwayml Closest to me is Seaside OR. I have to confess tho, these days Im more of a long board type. Haven’t touched a short board in like 15 yrs 😂

After 1.5 years at Luma AI, I have decided to leave and that the AI field is not my thing anymore and that I will pursue a career as a professional surfer. Just kidding, I‘m joining @runwayml

@BLVCKLIGHTai @runwayml Let‘s go, where do you surf at?

@dome_271 @runwayml I would meet you on the shore to catch some waves anytime.

@MysteryGuitarM @runwayml xd haha

@dome_271 @runwayml Not with THAT attitude! 🏄‍♂️

@MysteryGuitarM @runwayml I most certainly could not become a pro surfer

@dome_271 @runwayml You had me for a second!

@AndrewPrifer @runwayml Haha thanks <3

@dome_271 @runwayml Congrats Dome! ❤️ Send me some swag!

@Govindaiii @runwayml make cool video models

@dome_271 @runwayml What will your everyday tasks at runway look like?

Any RLHF experts here? Currently working on a video about PPO / GRPO etc., and I want to introduce importance sampling (see 1st screenshot). Is this a valid step to take, to go from the expected value over trajectories to expected value over actions? And is my explanation for this sound or am I missing something? Because doing so, makes it very straightforward to introduce importance sampling (see 2nd screenshot).

@chirping_ai You mean instead of a long facecam intro?

@dome_271 Please start the visuals from the beginning, it's tough to understand without visuals and since you already have them why not use them from the beginning? Great stuff otherwise!

After a million years I finally uploaded a new video. This time about RoPE! Let me know what you think! youtu.be/V8r__fXx7tU?si…

Lol YouTube suggesting creators new video ideas -> title + thumbnail + description Soon maybe also generate the video for you haha