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.

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

18,366 subscribers

1,915,854 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 (poli)

82,599 views • 1 year ago

We're excited to introduce Arcee.ai's Trinity Large model. An open 400B parameter Mixture of Experts model, delivering frontier-level performance with only 13B active parameters. Trained in collaboration between Arcee, Datology and Prime Intellect.

We're excited to introduce Arcee.ai's Trinity Large model. An open 400B parameter Mixture of Experts model, delivering frontier-level performance with only 13B active parameters. Trained in collaboration between Arcee, Datology and Prime Intellect.

Prime Intellect

178,830 views • 6 months ago

This is GLM 5.2 creating and describing *images* How, since the model is text-only? With Amp's specialized subagents. Multi-modal agentic workflows at the pareto frontier of intelligence, speed, and cost.

This is GLM 5.2 creating and describing images How, since the model is text-only? With Amp's specialized subagents. Multi-modal agentic workflows at the pareto frontier of intelligence, speed, and cost.

Beyang

20,111 views • 1 month ago

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Gradio

29,314 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 @ICML

150,079 views • 1 year ago

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a ___ ___”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a _ _”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Nathan Barry

89,040 views • 9 months ago

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

AK

25,449 views • 2 years ago

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

AK

47,488 views • 2 years ago

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

NVIDIA AI

759,905 views • 1 month ago

How can a visuomotor policy learn from internet videos? We introduce Dreamitate, where a robot uses a fine-tuned video diffusion model to dream the future (top) and imitate the dream to accomplish a task (bottom). website: paper:

How can a visuomotor policy learn from internet videos? We introduce Dreamitate, where a robot uses a fine-tuned video diffusion model to dream the future (top) and imitate the dream to accomplish a task (bottom). website: paper:

Ruoshi Liu

50,797 views • 2 years 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 • 1 year ago

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own synthetic experience.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Norman Di Palo

12,927 views • 2 years ago

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,571 views • 2 years ago

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!

Jessy Lin

107,491 views • 3 years 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

97,560 views • 5 days ago

Brazilian players, we heard you! In addition to the currently list of supported languages, we are excited to let you know that 007 First Light will release with Brazilian Portuguese language text on March 27th, 2026. Pre-order now and get a free Deluxe Edition Upgrade. #007FirstLight #EarnTheNumber #BGS25

Brazilian players, we heard you! In addition to the currently list of supported languages, we are excited to let you know that 007 First Light will release with Brazilian Portuguese language text on March 27th, 2026. Pre-order now and get a free Deluxe Edition Upgrade. #007FirstLight #EarnTheNumber #BGS25

007 First Light

900,836 views • 9 months ago

We are excited to introduce the world's first software-defined aircraft fuselage on our journey to transform aerospace manufacturing. Watch the full video on Youtube:

We are excited to introduce the world's first software-defined aircraft fuselage on our journey to transform aerospace manufacturing. Watch the full video on Youtube:

Saab

90,415 views • 7 months ago

Excited to introduce prompt to ai actors ... the first model to create consistent ai actors: ↳ type a prompt… ↳ create a unique talking actor ↳ edit them with perfect consistency … results are bluffing here's how it works:

Excited to introduce prompt to ai actors ... the first model to create consistent ai actors: ↳ type a prompt… ↳ create a unique talking actor ↳ edit them with perfect consistency … results are bluffing here's how it works:

Romain Torres

179,077 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

299,259 views • 3 years ago