Multi-student Diffusion Distillation for Better One-step Generators
Paper
•
2410.23274
•
Published
Jonathan Lorraine
lorraine2
AI & ML interests
machine learning, computer vision, generative AI
Recent Activity
authored
a paper
about 1 month ago
Multi-student Diffusion Distillation for Better One-step Generators
posted
an
update
about 1 month ago
🦙New NVIDIA paper: LLaMA-Mesh 🦙
We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.
🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: https://huggingface.co/spaces/Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: https://huggingface.co/Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
reacted
to
their
post
with 👀
about 2 months ago
New NVIDIA paper: ⚡ Multi-student Diffusion Distillation for Better One-step Generators ⚡
Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.
Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/
Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas
Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
Organizations
lorraine2's activity
authored
a
paper
about 1 month ago
posted
an
update
about 1 month ago
Post
2000
🦙New NVIDIA paper: LLaMA-Mesh 🦙
We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.
🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.
🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
reacted to
their
post with 👀
about 2 months ago
Post
1210
New NVIDIA paper: ⚡ Multi-student Diffusion Distillation for Better One-step Generators ⚡
Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.
Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/
Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas
Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.
Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/
Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas
Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
- 1 reply
posted
an
update
about 2 months ago
Post
1210
New NVIDIA paper: ⚡ Multi-student Diffusion Distillation for Better One-step Generators ⚡
Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.
Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/
Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas
Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.
Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/
Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas
Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
-
- 1 reply
reacted to
their
post with 👀
about 2 months ago
Post
294
New NeurIPS paper: “Training Data Attribution via Approximate Unrolling”
Ever wondered how individual data points influence AI decisions? 🤔 We explore how specific training data pieces affect machine learning models' behavior, which can be crucial for making AI systems more transparent, trustworthy, and fair.
Our method, SOURCE, bridges the gap between implicit differentiation and unrolling approaches, combining computational efficiency with flexibility making it suitable for non-converged models and multi-stage training pipelines.
📄 Full paper: https://openreview.net/pdf?id=3NaqGg92KZ
Juhan Bae led along with Wu Lin and Roger Grosse.
Supported by the University of Toronto, Vector Institute, NVIDIA, and Anthropic
Ever wondered how individual data points influence AI decisions? 🤔 We explore how specific training data pieces affect machine learning models' behavior, which can be crucial for making AI systems more transparent, trustworthy, and fair.
Our method, SOURCE, bridges the gap between implicit differentiation and unrolling approaches, combining computational efficiency with flexibility making it suitable for non-converged models and multi-stage training pipelines.
📄 Full paper: https://openreview.net/pdf?id=3NaqGg92KZ
Juhan Bae led along with Wu Lin and Roger Grosse.
Supported by the University of Toronto, Vector Institute, NVIDIA, and Anthropic
posted
an
update
about 2 months ago
Post
294
New NeurIPS paper: “Training Data Attribution via Approximate Unrolling”
Ever wondered how individual data points influence AI decisions? 🤔 We explore how specific training data pieces affect machine learning models' behavior, which can be crucial for making AI systems more transparent, trustworthy, and fair.
Our method, SOURCE, bridges the gap between implicit differentiation and unrolling approaches, combining computational efficiency with flexibility making it suitable for non-converged models and multi-stage training pipelines.
📄 Full paper: https://openreview.net/pdf?id=3NaqGg92KZ
Juhan Bae led along with Wu Lin and Roger Grosse.
Supported by the University of Toronto, Vector Institute, NVIDIA, and Anthropic
Ever wondered how individual data points influence AI decisions? 🤔 We explore how specific training data pieces affect machine learning models' behavior, which can be crucial for making AI systems more transparent, trustworthy, and fair.
Our method, SOURCE, bridges the gap between implicit differentiation and unrolling approaches, combining computational efficiency with flexibility making it suitable for non-converged models and multi-stage training pipelines.
📄 Full paper: https://openreview.net/pdf?id=3NaqGg92KZ
Juhan Bae led along with Wu Lin and Roger Grosse.
Supported by the University of Toronto, Vector Institute, NVIDIA, and Anthropic
liked
a
model
2 months ago
liked
a
Space
2 months ago
upvoted
a
paper
2 months ago
authored
a
paper
2 months ago
posted
an
update
5 months ago
Post
564
🚨 Code now available for "Using Large Language Models for Hyperparameter Optimization" at https://github.com/michaelrzhang/LLM-HyperOpt 🚨
TLDR: You can just ask LLMs which hyperparameters to use, and it works pretty well! You can even directly optimize your model’s code as a hyperparameter with this.
Check out the paper at https://arxiv.org/abs/2312.04528 - with Michael Zhang, Nishkrit Desai, Juhan Bae, and Jimmy Ba
TLDR: You can just ask LLMs which hyperparameters to use, and it works pretty well! You can even directly optimize your model’s code as a hyperparameter with this.
Check out the paper at https://arxiv.org/abs/2312.04528 - with Michael Zhang, Nishkrit Desai, Juhan Bae, and Jimmy Ba
authored
9
papers
5 months ago
Using Large Language Models for Hyperparameter Optimization
Paper
•
2312.04528
•
Published
Graph Metanetworks for Processing Diverse Neural Architectures
Paper
•
2312.04501
•
Published
Scalable Nested Optimization for Deep Learning
Paper
•
2407.01526
•
Published
•
4
Improving Hyperparameter Optimization with Checkpointed Model Weights
Paper
•
2406.18630
•
Published
Training Data Attribution via Approximate Unrolled Differentiation
Paper
•
2405.12186
•
Published
Task Selection for AutoML System Evaluation
Paper
•
2208.12754
•
Published
On Implicit Bias in Overparameterized Bilevel Optimization
Paper
•
2212.14032
•
Published
Lyapunov Exponents for Diversity in Differentiable Games
Paper
•
2112.14570
•
Published
Complex Momentum for Optimization in Games
Paper
•
2102.08431
•
Published