Загрузка видео...

Не удалось загрузить видео

На главную

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_ai's profile picture

Inception

18,255 subscribers

18,515 просмотров • 6 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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
0:26

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

75,518 просмотров • 10 месяцев назад

Excited to introduce SketchAgent!👩‍🎨 We leverage the prior of pretrained multimodal LLMs for language-driven, sequential sketch generation and human-agent collaborative sketching! ✨ Try our fun interface here:
1:21

Excited to introduce SketchAgent!👩‍🎨 We leverage the prior of pretrained multimodal LLMs for language-driven, sequential sketch generation and human-agent collaborative sketching! ✨ Try our fun interface here:

Yael Vinker

31,956 просмотров • 1 год назад

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.
5:11

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 просмотров • 3 лет назад

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.
3:49

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

21,231 просмотров • 3 месяцев назад

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.
2:00

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

1,046,502 просмотров • 6 месяцев назад

“Next-token prediction” just got a serious rival 🤯 Ant Group just dropped LLaDA 2.1, and it challenges the dominant paradigm of LLMs. Unlike most models that generate one token at a time, LLaDA 2.1 uses diffusion to generate blocks of text in parallel. Why this changes everything: → Global Planning: It effectively sees the "future" while writing the "past" → Parallel Generation: It generates chunks in parallel, not sequentially, being much faster → Massive Efficiency: 16B MoE architecture that only uses ~1.4B active parameters per step. 100% Open Source.
0:23

“Next-token prediction” just got a serious rival 🤯 Ant Group just dropped LLaDA 2.1, and it challenges the dominant paradigm of LLMs. Unlike most models that generate one token at a time, LLaDA 2.1 uses diffusion to generate blocks of text in parallel. Why this changes everything: → Global Planning: It effectively sees the "future" while writing the "past" → Parallel Generation: It generates chunks in parallel, not sequentially, being much faster → Massive Efficiency: 16B MoE architecture that only uses ~1.4B active parameters per step. 100% Open Source.

Alvaro Cintas

31,277 просмотров • 6 месяцев назад

Google just released Muse: a text to image model achieving state of the art performance. It is significantly more efficient than diffusion models. Muse also allows for inpainting, outpainting, and mask-free editing without finetuning or inverting the model.
0:33

Google just released Muse: a text to image model achieving state of the art performance. It is significantly more efficient than diffusion models. Muse also allows for inpainting, outpainting, and mask-free editing without finetuning or inverting the model.

bleedingedge.ai

183,750 просмотров • 3 лет назад

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy, the godfather of AI, dropped a 2 hour course on how he personally uses LLMs daily. • 00:00 - LLMs simplified • 22:49 - which LLM to actually use • 42:00 - one prompt for full research • 1:13:57 - how to code with LLMs • 1:37:04 - NotebookLM podcast generation This course will teach you more about using LLMs than most AI engineers learn in their entire career. Bookmark this & give 2 hours today, no matter what. Then read the article below.
2:11:07

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy, the godfather of AI, dropped a 2 hour course on how he personally uses LLMs daily. • 00:00 - LLMs simplified • 22:49 - which LLM to actually use • 42:00 - one prompt for full research • 1:13:57 - how to code with LLMs • 1:37:04 - NotebookLM podcast generation This course will teach you more about using LLMs than most AI engineers learn in their entire career. Bookmark this & give 2 hours today, no matter what. Then read the article below.

Roan

56,500 просмотров • 1 месяц назад

“IF he does those things, then I reject the notion of a glass ceiling.” -Justin Thind Even some experts that praised the hiring of Pat Fitzgerald called it simply a “high floor, low ceiling” hire for #MichiganState. Here’s how/why it can be more than that:
1:17

“IF he does those things, then I reject the notion of a glass ceiling.” -Justin Thind Even some experts that praised the hiring of Pat Fitzgerald called it simply a “high floor, low ceiling” hire for #MichiganState. Here’s how/why it can be more than that:

Spartan Spotlight

15,008 просмотров • 9 месяцев назад

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM
6:57

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM

Gaurav Sen

27,368 просмотров • 1 год назад

AI is about more than models. Ariana Salvatore, Head of Public Policy Research at Morgan Stanley, explains why control of the AI stack is becoming a strategic priority. Listen to more on Thoughts on the Market.
0:52

AI is about more than models. Ariana Salvatore, Head of Public Policy Research at Morgan Stanley, explains why control of the AI stack is becoming a strategic priority. Listen to more on Thoughts on the Market.

Morgan Stanley

17,299 просмотров • 1 месяц назад

10 million users. 100+ models tested every week. More than 1 trillion tokens processed every day. Henry Wang explains why he thinks the next generation of consumer AI won't be won by the best model, but rather by the teams that can iterate and scale the fastest. Listen now: Henry Wang Josh Liss
0:27

10 million users. 100+ models tested every week. More than 1 trillion tokens processed every day. Henry Wang explains why he thinks the next generation of consumer AI won't be won by the best model, but rather by the teams that can iterate and scale the fastest. Listen now: Henry Wang Josh Liss

Nebius

17,953 просмотров • 2 месяцев назад

As someone who builds with LLMs and diffusion models, this 14-minute heat equation video is the closest thing to a "why noise reversal actually works" explainer I've ever seen released for free. Everyone thinks diffusion is a novel AI concept. It's the heat equation from 1822. The forward process spreads noise like heat, and the reverse process is what your model learns. Bookmark & watch this weekend. Same math, from 19th-century physics to 2025 image generation.
13:12

As someone who builds with LLMs and diffusion models, this 14-minute heat equation video is the closest thing to a "why noise reversal actually works" explainer I've ever seen released for free. Everyone thinks diffusion is a novel AI concept. It's the heat equation from 1822. The forward process spreads noise like heat, and the reverse process is what your model learns. Bookmark & watch this weekend. Same math, from 19th-century physics to 2025 image generation.

fintex

15,604 просмотров • 1 месяц назад

I know why your fave still doesn’t speak up about their mistreatment, because they know their fans would rather suck up to the company than listen to the truth
1:16

I know why your fave still doesn’t speak up about their mistreatment, because they know their fans would rather suck up to the company than listen to the truth

ia

1,191,324 просмотров • 1 год назад

The 🆕 #PowerEdge R260 server took some notes from its prior generation to deliver bigger productivity and better performance. 📈 Learn more about this server in this infographic:
0:22

The 🆕 #PowerEdge R260 server took some notes from its prior generation to deliver bigger productivity and better performance. 📈 Learn more about this server in this infographic:

Dell Technologies

1,375,449 просмотров • 2 лет назад

The ostriches, in this case, are way more than just bird Listen to Katie talk about the potential of derived-antibodies. This is what we're about to lose. 👇
4:17

The ostriches, in this case, are way more than just bird Listen to Katie talk about the potential of derived-antibodies. This is what we're about to lose. 👇

mistersunshinebaby

33,529 просмотров • 11 месяцев назад