正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🚨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

1,181 subscribers

31,659 次观看 • 7 个月前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

AI at Meta

74,531 次观看 • 1 年前

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

AK

165,158 次观看 • 3 年前

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)

Xuanchi Ren

668,540 次观看 • 23 天前

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Afiz ⚡️

249,552 次观看 • 2 年前

Our Latent Encoder-Decoder code base is fully open sourced, you can train and visualize the latent space: Code⚙️: ArXiv 📚: #CVPR2026

Our Latent Encoder-Decoder code base is fully open sourced, you can train and visualize the latent space: Code⚙️: ArXiv 📚: #CVPR2026

Xueyan Zou

19,139 次观看 • 3 个月前

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 次观看 • 7 个月前

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 次观看 • 1 年前

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!

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.

354,178 次观看 • 1 年前

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 次观看 • 2 年前

👀Humans compare images by looking back and forth. Many open-weight VLMs encode each image independently, and defer comparison to the LM. We introduce SVE: Stateful Visual Encoders for Vision-Language Models, where the visual encoder itself becomes change-aware. 🌐Project: 📰Paper: 💻Code: 1/n

👀Humans compare images by looking back and forth. Many open-weight VLMs encode each image independently, and defer comparison to the LM. We introduce SVE: Stateful Visual Encoders for Vision-Language Models, where the visual encoder itself becomes change-aware. 🌐Project: 📰Paper: 💻Code: 1/n

Zirui "Colin" Wang

51,020 次观看 • 15 天前

Block Diffusion Interpolating Between Autoregressive and Diffusion Language Models

Block Diffusion Interpolating Between Autoregressive and Diffusion Language Models

AK

160,553 次观看 • 1 年前

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Slater Stich

28,721 次观看 • 1 年前

Omni-Attribute Open-vocabulary Attribute Encoder for Visual Concept Personalization

Omni-Attribute Open-vocabulary Attribute Encoder for Visual Concept Personalization

AK

13,988 次观看 • 6 个月前

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Ivana Balazevic

43,469 次观看 • 1 年前

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,404 次观看 • 2 个月前

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

AK

32,888 次观看 • 2 年前

I caught up with Amanda Bertsch at #NeurIPS2023, who was presenting Unlimiformer, a retrieval-augmentation method for encoder-decoder models allowing unlimited length inputs. Paper: Unlimiformer: Long-Range Transformers with Unlimited Length Input Work with Uri Alon Graham Neubig, and Matt Gormley More #NeurIPS2023 coverage to come (Follow Cohere to not miss any of it).

I caught up with Amanda Bertsch at #NeurIPS2023, who was presenting Unlimiformer, a retrieval-augmentation method for encoder-decoder models allowing unlimited length inputs. Paper: Unlimiformer: Long-Range Transformers with Unlimited Length Input Work with Uri Alon Graham Neubig, and Matt Gormley More #NeurIPS2023 coverage to come (Follow Cohere to not miss any of it).

Jay Alammar

25,862 次观看 • 2 年前

Apple FastVLM-7B Efficient Vision Encoding for Vision Language Models larger variants using Qwen2-7B LLM outperform recent works like Cambrian-1-8B while using a single image encoder with a 7.9x faster TTFT vibe coding a video captioning app with it in anycoder

Apple FastVLM-7B Efficient Vision Encoding for Vision Language Models larger variants using Qwen2-7B LLM outperform recent works like Cambrian-1-8B while using a single image encoder with a 7.9x faster TTFT vibe coding a video captioning app with it in anycoder

AK

60,588 次观看 • 9 个月前

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 次观看 • 1 年前

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

MIT CSAIL

34,347 次观看 • 2 年前