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.

decision models, now open and multimodal!

Viviana Márquez

1,470 subscribers

34,027 views • 4 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

3 Comments

Atif Saleem3 days ago

I really think that @liquidai is an underrated AI lab that will have its day when local AI becomes a norm in daily life for normal people and their things.

AGTP4 days ago

We actually went deeper on how these models act as a fast and cheap alternative for AI judgment here:

Memo Ai agent3 days ago

What’s the hf space name

Related Videos

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

SGLang

251,685 views • 12 days ago

We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation. It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & Thinking Machines' Inkling. Code: ramp-public/portallib Models: Hugging Face /RampPublic

We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation. It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & Thinking Machines' Inkling. Code: ramp-public/portallib Models: Hugging Face /RampPublic

Ramp Labs

171,845 views • 2 months ago

The Gemma family continues to grow today! 🩺 Announcing new models for MedGemma, our collection of multimodal open models specifically designed for health AI development that can run on a single GPU. 1️⃣ MedGemma 27B Multimodal 2️⃣ MedSigLIP (Read the thread to learn more)

The Gemma family continues to grow today! 🩺 Announcing new models for MedGemma, our collection of multimodal open models specifically designed for health AI development that can run on a single GPU. 1️⃣ MedGemma 27B Multimodal 2️⃣ MedSigLIP (Read the thread to learn more)

Google AI Developers

61,037 views • 1 year ago

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Avi Chawla

557,650 views • 1 year ago

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟

Akshay 🚀

60,627 views • 1 year ago

Meet Molmo: a family of open, state-of-the-art multimodal AI models. Our best model outperforms proprietary systems, using 1000x less data. Molmo doesn't just understand multimodal data—it acts on it, enabling rich interactions in both the physical and virtual worlds. Try it for yourself:

Meet Molmo: a family of open, state-of-the-art multimodal AI models. Our best model outperforms proprietary systems, using 1000x less data. Molmo doesn't just understand multimodal data—it acts on it, enabling rich interactions in both the physical and virtual worlds. Try it for yourself:

Ai2

515,797 views • 2 years ago

You saw our AstroCLIP, and have heard of MultiModal Universe! Now, come build and scale Foundation models for Astrophysics with us at PolymathicAI! Check this out: Deadline: Feb 14, 2025!

You saw our AstroCLIP, and have heard of MultiModal Universe! Now, come build and scale Foundation models for Astrophysics with us at PolymathicAI! Check this out: Deadline: Feb 14, 2025!

Shirley Ho

11,481 views • 1 year ago

👀 Seeing is just the beginning. With Qwen-MM-Plugins, turn your favorite agent harness multimodal-native — read images, videos & documents, edit videos, work with 3D/CAD, and more. From multimodal models → multimodal agents. 🚀 Watch it in action:

👀 Seeing is just the beginning. With Qwen-MM-Plugins, turn your favorite agent harness multimodal-native — read images, videos & documents, edit videos, work with 3D/CAD, and more. From multimodal models → multimodal agents. 🚀 Watch it in action:

Qwen

797,477 views • 2 months ago

🧑‍🍳 Experiment with a multimodal LLM in WebAR. The AI identifies ingredients, sets up bounding boxes, and prepares them for AR. I'm also using open-source models to generate recipes and corresponding images. #threejs #8thwall #generativeai

🧑‍🍳 Experiment with a multimodal LLM in WebAR. The AI identifies ingredients, sets up bounding boxes, and prepares them for AR. I'm also using open-source models to generate recipes and corresponding images. #threejs #8thwall #generativeai

Stijn Spanhove

61,019 views • 2 years ago

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Siddharth Sharma

193,085 views • 2 years ago

open d1 decision models are here! • small enough to run them on my macbook • multimodal for fun things like video input here i'm using d1-3B to rate how cute my outfit is. don't follow me for more fashion advice 💜 see more fun demos on our hugging face space:

open d1 decision models are here! • small enough to run them on my macbook • multimodal for fun things like video input here i'm using d1-3B to rate how cute my outfit is. don't follow me for more fashion advice 💜 see more fun demos on our hugging face space:

leonie

11,098 views • 4 days ago

1/ Today we're introducing Cua-S1-4B-0.2, the first multimodal decision model trained with RLOO on live computer-use tasks, using task-completion rewards. Text and multimodal adapters are available under Apache-2.0:

1/ Today we're introducing Cua-S1-4B-0.2, the first multimodal decision model trained with RLOO on live computer-use tasks, using task-completion rewards. Text and multimodal adapters are available under Apache-2.0:

Cua

161,531 views • 18 days ago

Alibaba just open-sourced Qwen 3.6-35B A3B 35B MoE model (only ~3B active), multimodal, agentic coding, Apache 2.0. This isn’t just efficient—it’s built for real workflows. Open models are catching up fast.

Alibaba just open-sourced Qwen 3.6-35B A3B 35B MoE model (only ~3B active), multimodal, agentic coding, Apache 2.0. This isn’t just efficient—it’s built for real workflows. Open models are catching up fast.

Mervin Praison

13,063 views • 5 months ago

a tiny AI 0.5B just turned a normal phone video into a fully labeled 3D room run phone. SpatialLM that understands walls, doors, furniture, and everything layout. it trained as a standard multimodal LLM. Most vision models see pixels, SpatialLM sees space. Open models :

a tiny AI 0.5B just turned a normal phone video into a fully labeled 3D room run phone. SpatialLM that understands walls, doors, furniture, and everything layout. it trained as a standard multimodal LLM. Most vision models see pixels, SpatialLM sees space. Open models :

Md Ismail Šojal 🕷️

64,716 views • 2 days ago

EVE is now live on Wally, RunAnywhere's Jev-class decision models. Powered by Perplexity's open pplx-decider-v1-27b. Same capability, same cost, 4x faster. $5 free on signup.

EVE is now live on Wally, RunAnywhere's Jev-class decision models. Powered by Perplexity's open pplx-decider-v1-27b. Same capability, same cost, 4x faster. $5 free on signup.

RunAnywhere

12,805 views • 8 days ago

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

AI at Meta

121,573 views • 2 years ago

Meta presents TUNA Taming Unified Visual Representations for Native Unified Multimodal Models

Meta presents TUNA Taming Unified Visual Representations for Native Unified Multimodal Models

AK

32,796 views • 10 months ago

MiniMax H3 from is now available on Venice. Open-weight multimodal video model with native stereo audio on every generation. Available anonymously.

MiniMax H3 from is now available on Venice. Open-weight multimodal video model with native stereo audio on every generation. Available anonymously.

Venice

18,047 views • 2 months ago

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Yin Cui

34,990 views • 1 year ago