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.

MMaDA-Parallel Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

AK

503,054 subscribers

66,105 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models "Block diffusion sequentially generates blocks of tokens by performing diffusion within each block and conditioning on previous blocks. By combining strength from autoregressive and diffusion models, block diffusion overcomes the limitations of both approaches by supporting variable-length, higher-quality generation and improving inference efficiency with KV caching and parallel sampling."

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models "Block diffusion sequentially generates blocks of tokens by performing diffusion within each block and conditioning on previous blocks. By combining strength from autoregressive and diffusion models, block diffusion overcomes the limitations of both approaches by supporting variable-length, higher-quality generation and improving inference efficiency with KV caching and parallel sampling."

Tanishq Mathew Abraham, Ph.D.

21,813 views • 1 year ago

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.

We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.

Inception

1,910,030 views • 1 year ago

🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the rise for parallel text generation! But unlike autoregressive LMs, they struggle with quality, fixed-length constraints & lack of KV caching. 🚀Introducing Block Diffusion—combining autoregressive and diffusion models for the best of both worlds! 👇1/7

🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the rise for parallel text generation! But unlike autoregressive LMs, they struggle with quality, fixed-length constraints & lack of KV caching. 🚀Introducing Block Diffusion—combining autoregressive and diffusion models for the best of both worlds! 👇1/7

Marianne Arriola

148,063 views • 1 year ago

Major AI breakthrough: Diffusion Large Language Models are here! They're 10x faster and 10x cheaper than traditional LLMs. Here's everything you need to know:

Major AI breakthrough: Diffusion Large Language Models are here! They're 10x faster and 10x cheaper than traditional LLMs. Here's everything you need to know:

Matthew Berman

429,082 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

123,982 views • 1 year ago

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a discrete diffusion objective. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

Mihir Prabhudesai

104,862 views • 1 year ago

Artificial Intelligence (#AI) models that process and interpret visual data are called large vision models. These models, like large language models, are trained on large amounts of data. #midjourney #dalle #stablediffusion (1/8) 🧵 ⤵️

Artificial Intelligence (#AI) models that process and interpret visual data are called large vision models. These models, like large language models, are trained on large amounts of data. #midjourney #dalle #stablediffusion (1/8) 🧵 ⤵️

Nuklai

13,614 views • 2 years ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,017 views • 1 year ago

starting the week with a true groundbreaking work 💥 Large Language Diffusion Models the first billion-parameter scale diffusion model competitive with its pairs (8B model comparable to LLaMA 3 8B) it gets rid of the michael scott syndrome on existing LLMs

starting the week with a true groundbreaking work 💥 Large Language Diffusion Models the first billion-parameter scale diffusion model competitive with its pairs (8B model comparable to LLaMA 3 8B) it gets rid of the michael scott syndrome on existing LLMs

apolinario 🌐

11,833 views • 1 year ago

I think my large language models are malfunctioning

I think my large language models are malfunctioning

Pump.fun

283,106 views • 1 year ago

All the big language models under one roof for the very first time 🤯 Compare the output of OpenAI ChatGPT, Anthropic's Claude and Cohere's language model in a single playground!! Check out this amazing tool to get the best of large language models 👇

All the big language models under one roof for the very first time 🤯 Compare the output of OpenAI ChatGPT, Anthropic's Claude and Cohere's language model in a single playground!! Check out this amazing tool to get the best of large language models 👇

Shubham Saboo

299,254 views • 3 years ago

Google is making progress on their diffusion models... It's now as good as a Gemini 2.0 Flash Lite. The writing is on the wall, a majority of language AI use in the future will be diffusion models.

Google is making progress on their diffusion models... It's now as good as a Gemini 2.0 Flash Lite. The writing is on the wall, a majority of language AI use in the future will be diffusion models.

Carlos E. Perez

193,952 views • 5 months ago

LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

LLaDA (the first Large Language Diffusion Model) is just out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

apolinario 🌐

81,047 views • 1 year ago

GraphRAG-UI GraphRAG-UI is a user-friendly interface for GraphRAG, a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management and interaction method for GraphRAG, supporting the configuration of local large language models like Ollama, making it easier for users to leverage.

GraphRAG-UI GraphRAG-UI is a user-friendly interface for GraphRAG, a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management and interaction method for GraphRAG, supporting the configuration of local large language models like Ollama, making it easier for users to leverage.

AK

27,249 views • 1 year ago

AutoAdapt automates the design and tuning of domain adaptation workflows for large language models. It improves performance without requiring additional compute, making deployment more accessible:

AutoAdapt automates the design and tuning of domain adaptation workflows for large language models. It improves performance without requiring additional compute, making deployment more accessible:

Microsoft Research

10,753 views • 1 month ago

3.5 Soon: Up to 8+ Layers, 16 LLMs in Parallel🪄 A fully parallel, multi-layered system with 8+ orchestration layers handling everything from prompt parsing and tool execution to code generation and live editing—all powered by 16+ LLMs running in sync for real-time, adaptive creation. ➡️v1: Single agent, single output ↕️v2: Multiple agents, single output 🔃v3: Single agent, multiple outputs 🔀v3.5: Multiple agents, multiple outputs — scalable, context-aware, and built for real-time builds🔨

3.5 Soon: Up to 8+ Layers, 16 LLMs in Parallel🪄 A fully parallel, multi-layered system with 8+ orchestration layers handling everything from prompt parsing and tool execution to code generation and live editing—all powered by 16+ LLMs running in sync for real-time, adaptive creation. ➡️v1: Single agent, single output ↕️v2: Multiple agents, single output 🔃v3: Single agent, multiple outputs 🔀v3.5: Multiple agents, multiple outputs — scalable, context-aware, and built for real-time builds🔨

ALCHEMIST AI 🔮

13,423 views • 1 year ago

Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿

Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿

Cohere Labs

206,467 views • 1 year ago

🤔 How to fine-tune an Imitation Learning policy (e.g., Diffusion Policy, ACT) with RL? As an RL practitioner, I’ve been struggling with this problem for a while. Here’s why it’s tough: 1️⃣ Special designs (usually for multimodal action distributions) in modern IL models make them non-trivial to fine-tune by RL. 2️⃣ Large policy models + RL's poor sample efficiency = a nightmare But finally, we figured out a simple solution that works for any model architecture! 🌟 Check out our #ICLR2025 paper: “Policy Decorator: Model-Agnostic Online Refinement for Large Policy Models”, led by my amazing mentee Xiu Yuan. 🔗 🧵 Read more below!

🤔 How to fine-tune an Imitation Learning policy (e.g., Diffusion Policy, ACT) with RL? As an RL practitioner, I’ve been struggling with this problem for a while. Here’s why it’s tough: 1️⃣ Special designs (usually for multimodal action distributions) in modern IL models make them non-trivial to fine-tune by RL. 2️⃣ Large policy models + RL's poor sample efficiency = a nightmare But finally, we figured out a simple solution that works for any model architecture! 🌟 Check out our #ICLR2025 paper: “Policy Decorator: Model-Agnostic Online Refinement for Large Policy Models”, led by my amazing mentee Xiu Yuan. 🔗 🧵 Read more below!

Tongzhou Mu 🤖🦾🦿

16,923 views • 1 year ago

FramePainter Endowing Interactive Image Editing with Video Diffusion Priors

FramePainter Endowing Interactive Image Editing with Video Diffusion Priors

AK

32,181 views • 1 year ago

Each booth at Apsara 2025 is buzzing with the latest AI innovations! From the next-generation large language models of the Qwen3 family and the Wan 2.5 models to the new agent development framework feature in Model Studio, the updates are rolling in! Stay tuned as we zoom into the booths and bring the breakthroughs to you!🔥

Each booth at Apsara 2025 is buzzing with the latest AI innovations! From the next-generation large language models of the Qwen3 family and the Wan 2.5 models to the new agent development framework feature in Model Studio, the updates are rolling in! Stay tuned as we zoom into the booths and bring the breakthroughs to you!🔥

Alibaba Group

161,575 views • 8 months ago