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.

Diffusion language models are SO FAST!! A new startup, Inception Labs, has released Mercury Coder, "the first commercial-scale diffusion large language model" It's 5-10x faster than current gen LLMs, providing high-quality responses at low costs. And you can try it now!

Tanishq Mathew Abraham, Ph.D.

87,605 subscribers

354,178 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

11 Comments

Tanishq Mathew Abraham, Ph.D.1 year ago

The performance is similar to small frontier models while achieving a throughput of ~1000 tokens/sec... on H100s! Reaching this level of throughput for autoregressive LLMs typically requires specialized chips.

Tanishq Mathew Abraham, Ph.D.1 year ago

It's currently tied for second place on Copilot Arena!

Tanishq Mathew Abraham, Ph.D.1 year ago

.@InceptionAILabs is a new company that is founded by some of the leading researchers in diffusion language models (@StefanoErmon, @adityagrover_, @volokuleshov)

Tanishq Mathew Abraham, Ph.D.1 year ago

You can try out Mercury Coder right now, over here:

Lucid Scientific, Inc.1 year ago

Expand the possibilities of your metabolic research. Resipher tracks real-time cellular oxygen consumption in standard 96-well plates, delivering continuous real-time data directly from your incubator. Request a free virtual demo or quote today >>

Jonathan Whitaker1 year ago

Speed is cool! It did the '// This part is left as an exercise for the reader' thing on my first test though hahaha

bubble boi in NY🗽1 year ago

Reporting as spam

Tanishq Mathew Abraham, Ph.D.1 year ago

🤣🤣🤣

Joshua Popelka1 year ago

Has it helped with any of the limitations of current autoregressive models? Like hallucinations; would be super exciting then.

Tianyu Hua1 year ago

open source?

Midas 霊 👑 (kween/acc)1 year ago

@EastlondonDev i think you're right 3 months

Related Videos

Try the first diffusion language model on the playground. Inception Labs' Mercury Coder generates over 1000 tokens/sec.

Try the first diffusion language model on the playground. Inception Labs' Mercury Coder generates over 1000 tokens/sec.

AI SDK

17,964 views • 1 year ago

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:

David Ondrej

45,692 views • 3 months ago

We’re excited to launch Mercury, the first commercial-scale diffusion LLM tailored for chat applications! Ultra-fast and efficient, Mercury brings real-time responsiveness to conversations, just like Mercury Coder did for code.

We’re excited to launch Mercury, the first commercial-scale diffusion LLM tailored for chat applications! Ultra-fast and efficient, Mercury brings real-time responsiveness to conversations, just like Mercury Coder did for code.

Inception

90,673 views • 11 months ago

Just found the dLLM library to create Diffusion Language Models It's still early but it's insanely fun to experiment with diffusion (training, inference, eval) dLLM has the potential of becoming the main library for diffusion LLMs

Just found the dLLM library to create Diffusion Language Models It's still early but it's insanely fun to experiment with diffusion (training, inference, eval) dLLM has the potential of becoming the main library for diffusion LLMs

Maxime Labonne

75,421 views • 7 months ago

China's Qafind Labs just launched the first Diffusion Language Model (DLM). 🔥 ChatDLM, described as the first Diffusion Language Model (DLM), will be open-sourced soon. - Inference Speed: 2,800 tokens/sec (on A100), which is insanely fast. - Context Window: 131,072 tokens. More details 👇

China's Qafind Labs just launched the first Diffusion Language Model (DLM). 🔥 ChatDLM, described as the first Diffusion Language Model (DLM), will be open-sourced soon. - Inference Speed: 2,800 tokens/sec (on A100), which is insanely fast. - Context Window: 131,072 tokens. More details 👇

AshutoshShrivastava

73,296 views • 1 year ago

Block Diffusion Interpolating Between Autoregressive and Diffusion Language Models

Block Diffusion Interpolating Between Autoregressive and Diffusion Language Models

AK

160,553 views • 1 year ago

Mercury 2 is live 🚀🚀 The world’s first reasoning diffusion LLM, delivering 5x faster performance than leading speed-optimized LLMs. Watching the team turn years of research into a real product never gets old, and I’m incredibly proud of what we’ve built. We’re just getting started on what diffusion can do for language.

Mercury 2 is live 🚀🚀 The world’s first reasoning diffusion LLM, delivering 5x faster performance than leading speed-optimized LLMs. Watching the team turn years of research into a real product never gets old, and I’m incredibly proud of what we’ve built. We’re just getting started on what diffusion can do for language.

Stefano Ermon

1,026,162 views • 3 months ago

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin

机器之心 JIQIZHIXIN

18,126 views • 7 months ago

🚨In our NeurIPS paper, we bring encoder-decoders back.. for diffusion language models! ⚡️Encoder-decoders make diffusion sampling fast: a small (fast) decoder denoises tokens progressively and a large (slower) encoder represents clean context.

🚨In our NeurIPS paper, we bring encoder-decoders back.. for diffusion language models! ⚡️Encoder-decoders make diffusion sampling fast: a small (fast) decoder denoises tokens progressively and a large (slower) encoder represents clean context.

Marianne Arriola

31,659 views • 7 months ago

We're moving beyond autoregressive LLMs! Autoregressive LLMs generate text word-by-word, which can be slow and affect quality, while diffusion models refine noise step-by-step, allowing for faster iterations and error correction. Here's Gemini Diffusion running at 857 tokens/s:

We're moving beyond autoregressive LLMs! Autoregressive LLMs generate text word-by-word, which can be slow and affect quality, while diffusion models refine noise step-by-step, allowing for faster iterations and error correction. Here's Gemini Diffusion running at 857 tokens/s:

Akshay 🚀

34,524 views • 1 year ago

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Vaibhav (VB) Srivastav

21,394 views • 1 year ago

Video diffusion models generate high-quality videos but are too slow for interactive applications. We MIT CSAIL Adobe Research introduce CausVid, a fast autoregressive video diffusion model that starts playing the moment you hit "Generate"! A thread 🧵

Video diffusion models generate high-quality videos but are too slow for interactive applications. We MIT CSAIL Adobe Research introduce CausVid, a fast autoregressive video diffusion model that starts playing the moment you hit "Generate"! A thread 🧵

Tianwei Yin

83,714 views • 1 year ago

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 views • 2 years ago

Diffusion clicked for me when I read about score-based models, a line of work pioneered by Stefano Ermon (et al.) at Stanford. So it was a full-circle moment to collab with him and Inception on a video about training & sampling techniques for making diffusion LLMs faster.

Diffusion clicked for me when I read about score-based models, a line of work pioneered by Stefano Ermon (et al.) at Stanford. So it was a full-circle moment to collab with him and Inception on a video about training & sampling techniques for making diffusion LLMs faster.

Julia Turc

26,941 views • 4 months ago

Listen to Samar Khanna explain why parallel generation, rather than sequential, raises the performance ceiling for language models. Learn more about diffusion LLMs. → We're hiring:

Listen to Samar Khanna explain why parallel generation, rather than sequential, raises the performance ceiling for language models. Learn more about diffusion LLMs. → We're hiring:

Inception

18,407 views • 3 months ago

This video explains how diffusion models are overtaking Large Language Models for generation tasks like: 1. Code Generation 2. Image Generation 3. Video Generation 00:00 Agenda 00:20 How are they different from LLMs? 05:09 Internal Mechanism 10:09 How are vectors generated? 12:08 Conclusion 13:02 Opinion Piece AI Engineering Course: #Diffusion #AI #LLMs

This video explains how diffusion models are overtaking Large Language Models for generation tasks like: 1. Code Generation 2. Image Generation 3. Video Generation 00:00 Agenda 00:20 How are they different from LLMs? 05:09 Internal Mechanism 10:09 How are vectors generated? 12:08 Conclusion 13:02 Opinion Piece AI Engineering Course: #Diffusion #AI #LLMs

Gaurav Sen

27,910 views • 7 months ago

"An hour of planning can save you 10 hours of doing." ✨📝 Planned Diffusion 📝 ✨ makes a plan before parallel dLLM generation. Planned Diffusion runs 1.2-1.8× faster than autoregressive and an order of magnitude faster than diffusion, while staying within 0.9–5% AR quality.

"An hour of planning can save you 10 hours of doing." ✨📝 Planned Diffusion 📝 ✨ makes a plan before parallel dLLM generation. Planned Diffusion runs 1.2-1.8× faster than autoregressive and an order of magnitude faster than diffusion, while staying within 0.9–5% AR quality.

Daniel Israel

38,699 views • 7 months ago

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:

BURKOV

58,434 views • 1 year ago

Introducing Parallax, the first fully distributed inference and serving engine for large language models. Try it now: 🧵

Introducing Parallax, the first fully distributed inference and serving engine for large language models. Try it now: 🧵

Gradient

160,966 views • 11 months ago

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.

Inception

21,021 views • 25 days ago