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.

1/ muse spark 1.2 is a very strong multimodal model—it can do visual coding, robotics planning, and audio-visual understanding that all come together through agentic tools.

Alexandr Wang

631,516 subscribers

142,275 views • 1 day ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.

Google AI Developers

62,539 views • 3 months ago

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Matt Deitke

52,769 views • 1 month ago

Meet Muse Spark 1.2 and Muse Code, the agent built to run it against your coding challenges. Now in beta. Together they take a task from idea to production, and deploy teams of agents that plan, write and refine across your repos. Start building now:

Meet Muse Spark 1.2 and Muse Code, the agent built to run it against your coding challenges. Now in beta. Together they take a task from idea to production, and deploy teams of agents that plan, write and refine across your repos. Start building now:

Meta for Developers

55,414 views • 16 days ago

MiniMax-H3 open source: a general-purpose multimodal generative model that unified understanding of multimodalof text, images, video, and audio, and is capable of generating audio and video with native stereo sound, supporting up to 15 seconds at 2K resolution.

MiniMax-H3 open source: a general-purpose multimodal generative model that unified understanding of multimodalof text, images, video, and audio, and is capable of generating audio and video with native stereo sound, supporting up to 15 seconds at 2K resolution.

青龍聖者

58,341 views • 22 days ago

Introducing MiniMax H3, our next-gen open-weight multimodal video model, built for general intelligence beyond single-task generation. H3 understands text, images, video, and audio together, interpreting motion, sound, emotion, and cinematography as one unified creative language, delivering generation with fine-grained precision and cinematic quality. → Native Multimodal Understanding & Generation → Precision Editing & Control → Commercial-Grade Output: film, ads, MVs, UI, game CG → Cinematic Audio-Visual Quality: native stereo audio, up to 2K/24FPS Multi-asset reference for characters, motion, camera movement + voice cloning. Hailuo AI (MiniMax)'s H3 takes ideas from concept to production in one flow. Try it now: #MiniMaxH3

Introducing MiniMax H3, our next-gen open-weight multimodal video model, built for general intelligence beyond single-task generation. H3 understands text, images, video, and audio together, interpreting motion, sound, emotion, and cinematography as one unified creative language, delivering generation with fine-grained precision and cinematic quality. → Native Multimodal Understanding & Generation → Precision Editing & Control → Commercial-Grade Output: film, ads, MVs, UI, game CG → Cinematic Audio-Visual Quality: native stereo audio, up to 2K/24FPS Multi-asset reference for characters, motion, camera movement + voice cloning. Hailuo AI (MiniMax)'s H3 takes ideas from concept to production in one flow. Try it now: #MiniMaxH3

SARAH

97,618 views • 21 days ago

Meet Gemma 3n, a model that runs on as little as 2GB of RAM 🤯 It shares the same architecture as Gemini Nano, and is engineered for incredible performance. We added audio understanding, so now it’s multimodal, fast and lean, and runs on-device (no cloud connection required!)

Meet Gemma 3n, a model that runs on as little as 2GB of RAM 🤯 It shares the same architecture as Gemini Nano, and is engineered for incredible performance. We added audio understanding, so now it’s multimodal, fast and lean, and runs on-device (no cloud connection required!)

Google AI

228,835 views • 1 year ago

Multi-agentic/player pair programming idea sketch in 10 mins — a real-time Tuplesque experience where I can share the screen w/ AIs, directly point it out to code or sketch together on a whiteboard, have an instant groupchat to debug with voice, AI has access to Cursor that could also use its tools to speed up the work. We can all naturally interrupt each other and have fun together. We are all collaborating, shipping features, and leveraging each other’s strengths (eg if Claude is better at frontend it should handle that part of the stack). That’s the pair programming / real agentic coding I’d love to use!

Multi-agentic/player pair programming idea sketch in 10 mins — a real-time Tuplesque experience where I can share the screen w/ AIs, directly point it out to code or sketch together on a whiteboard, have an instant groupchat to debug with voice, AI has access to Cursor that could also use its tools to speed up the work. We can all naturally interrupt each other and have fun together. We are all collaborating, shipping features, and leveraging each other’s strengths (eg if Claude is better at frontend it should handle that part of the stack). That’s the pair programming / real agentic coding I’d love to use!

Karina Nguyen

21,434 views • 1 year ago

Show-o One Single Transformer to Unify Multimodal Understanding and Generation discuss: We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.

Show-o One Single Transformer to Unify Multimodal Understanding and Generation discuss: We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.

AK

124,048 views • 2 years ago

I’ve been eyeing this robotics platform by Vicarius Surgical for a long time and I am vi-curious to see what it can do. I like that the engineers/designers solved the surgical robotics problem in a different way. I wonder how strong it is and does it scale

I’ve been eyeing this robotics platform by Vicarius Surgical for a long time and I am vi-curious to see what it can do. I like that the engineers/designers solved the surgical robotics problem in a different way. I wonder how strong it is and does it scale

Jonathan DeLong, MD

112,338 views • 3 years ago

An 100% open-source rival to n8n just launched. Sim is a drag-and-drop platform for building agentic workflows that runs entirely on your local machine. → Visual, Figma-like canvas interface → Works with any local LLM via Ollama → Native MCP support to connect 100+ tools

An 100% open-source rival to n8n just launched. Sim is a drag-and-drop platform for building agentic workflows that runs entirely on your local machine. → Visual, Figma-like canvas interface → Works with any local LLM via Ollama → Native MCP support to connect 100+ tools

Oliver Prompts

77,286 views • 7 months ago

Space for all 🏳️‍🌈 As part of our #PrideMonth celebration, we unveiled the Pride flag on Lab, a visual reminder that inclusivity is one of NASA JPL's core values and that by fostering a diverse and equitable work environment, we can Dare Mighty Things Together.

Space for all 🏳️‍🌈 As part of our #PrideMonth celebration, we unveiled the Pride flag on Lab, a visual reminder that inclusivity is one of NASA JPL's core values and that by fostering a diverse and equitable work environment, we can Dare Mighty Things Together.

Life at NASA's Jet Propulsion Laboratory

265,277 views • 3 years ago

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Darshal Jaitwar

141,038 views • 7 months ago

MCP-apps support is coming soon to Visual Studio Code Really excited about this - IDE as agentic SDLC C&C center - devs can stay focused even more inside their work and bring pieces of it to their IDE like JIRA/linear tickets and other tools right in the IDE Tnx Connor Peet

MCP-apps support is coming soon to Visual Studio Code Really excited about this - IDE as agentic SDLC C&C center - devs can stay focused even more inside their work and bring pieces of it to their IDE like JIRA/linear tickets and other tools right in the IDE Tnx Connor Peet

Oren Melamed

13,366 views • 7 months ago

An AI model from China just crossed a cinematic threshold. Seedance 2.0 is here. It delivers state-of-the-art motion, prompt adherence, and visual fidelity. 10 wild examples 👇 1/10

An AI model from China just crossed a cinematic threshold. Seedance 2.0 is here. It delivers state-of-the-art motion, prompt adherence, and visual fidelity. 10 wild examples 👇 1/10

ZARA

37,969 views • 6 months ago

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.

Pietro Schirano

11,427 views • 8 months ago

Most AI video tools can create a striking moment. The harder part is keeping the whole scene consistent. Dreamina Seedance 2.5 is coming soon to the Dreamina platform, bringing several features designed for creators: - Up to 50 multimodal references Use images, videos, audio, and visual references to guide the generation. - Up to 30-second continuous videos Build longer story beats without cutting everything into tiny clips. - White-model and green-screen control Guide movement, composition, and visual performance with greater precision. - Multilingual creation Create content for audiences across different markets. - Precise local editing Adjust selected parts of a video while keeping the rest intact. AI storytelling is about to become more flexible—and much easier to shape. 👉 #dreamina #dreaminapartner #seedance #dreaminaseedance25

Most AI video tools can create a striking moment. The harder part is keeping the whole scene consistent. Dreamina Seedance 2.5 is coming soon to the Dreamina platform, bringing several features designed for creators: - Up to 50 multimodal references Use images, videos, audio, and visual references to guide the generation. - Up to 30-second continuous videos Build longer story beats without cutting everything into tiny clips. - White-model and green-screen control Guide movement, composition, and visual performance with greater precision. - Multilingual creation Create content for audiences across different markets. - Precise local editing Adjust selected parts of a video while keeping the rest intact. AI storytelling is about to become more flexible—and much easier to shape. 👉 #dreamina #dreaminapartner #seedance #dreaminaseedance25

Parul Gautam

38,399 views • 24 days ago

Meta just launched its 1st image model after Mark Zuckerberg’s AI shake-up. Muse Image is Meta Superintelligence Labs' first image generator after Muse Spark. They said the model will power new editing features in Meta’s Instagram photo app and be added to its marketer tools for creating platform ads. Meta had relied on Midjourney and Black Forest Labs for generation inside Meta AI. Muse Image brings that layer in-house, so Meta controls quality, cost, and product timing. Consumers get free access through Meta AI, WhatsApp chats, and Instagram Stories. Power users need Meta One or another monthly plan when free limits run out. Users can start from prompts, add photos, annotate edits, or sketch changes directly. Meta says it can erase photobombers, create QR codes, and keep visual text readable. Advertisers get variants through Advantage+ creative, with edits, style swaps, and brand-matched versions. Meta says internal tests trail GPT Image 2 but beat Nano Banana 2 on editing. This is another move in Meta's effort in trying to convert AI infrastructure spending into revenue beyond social ads.

Rohan Paul

20,377 views • 1 month ago