Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Samira Abnar

Samira Abnar
Alert button

Diffusion Probabilistic Fields


Mar 01, 2023
Peiye Zhuang, Samira Abnar, Jiatao Gu, Alex Schwing, Joshua M. Susskind, Miguel Ángel Bautista

Add code
Alert button

Figure 1 for Diffusion Probabilistic Fields
Figure 2 for Diffusion Probabilistic Fields
Figure 3 for Diffusion Probabilistic Fields
Figure 4 for Diffusion Probabilistic Fields
* Accepted to ICLR 2023. 20 pages, 17 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

GAUDI: A Neural Architect for Immersive 3D Scene Generation


Jul 27, 2022
Miguel Angel Bautista, Pengsheng Guo, Samira Abnar, Walter Talbott, Alexander Toshev, Zhuoyuan Chen, Laurent Dinh, Shuangfei Zhai, Hanlin Goh, Daniel Ulbricht, Afshin Dehghan, Josh Susskind

Add code
Alert button

Figure 1 for GAUDI: A Neural Architect for Immersive 3D Scene Generation
Figure 2 for GAUDI: A Neural Architect for Immersive 3D Scene Generation
Figure 3 for GAUDI: A Neural Architect for Immersive 3D Scene Generation
Figure 4 for GAUDI: A Neural Architect for Immersive 3D Scene Generation
* Project webpage: https://github.com/apple/ml-gaudi 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?


Jul 21, 2022
Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler

Add code
Alert button

Figure 1 for Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
Figure 2 for Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
Figure 3 for Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
Figure 4 for Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Exploring the Limits of Large Scale Pre-training


Oct 05, 2021
Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi

Add code
Alert button

Figure 1 for Exploring the Limits of Large Scale Pre-training
Figure 2 for Exploring the Limits of Large Scale Pre-training
Figure 3 for Exploring the Limits of Large Scale Pre-training
Figure 4 for Exploring the Limits of Large Scale Pre-training

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers


Sep 22, 2021
Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler

Add code
Alert button

Figure 1 for Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
Figure 2 for Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
Figure 3 for Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
Figure 4 for Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent


Jun 10, 2021
Samira Abnar, Rianne van den Berg, Golnaz Ghiasi, Mostafa Dehghani, Nal Kalchbrenner, Hanie Sedghi

Add code
Alert button

Figure 1 for Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent
Figure 2 for Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent
Figure 3 for Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent
Figure 4 for Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Long Range Arena: A Benchmark for Efficient Transformers


Nov 08, 2020
Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler

Add code
Alert button

Figure 1 for Long Range Arena: A Benchmark for Efficient Transformers
Figure 2 for Long Range Arena: A Benchmark for Efficient Transformers
Figure 3 for Long Range Arena: A Benchmark for Efficient Transformers
Figure 4 for Long Range Arena: A Benchmark for Efficient Transformers

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Transferring Inductive Biases through Knowledge Distillation


Jun 02, 2020
Samira Abnar, Mostafa Dehghani, Willem Zuidema

Add code
Alert button

Figure 1 for Transferring Inductive Biases through Knowledge Distillation
Figure 2 for Transferring Inductive Biases through Knowledge Distillation
Figure 3 for Transferring Inductive Biases through Knowledge Distillation
Figure 4 for Transferring Inductive Biases through Knowledge Distillation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Quantifying Attention Flow in Transformers


May 31, 2020
Samira Abnar, Willem Zuidema

Add code
Alert button

Figure 1 for Quantifying Attention Flow in Transformers
Figure 2 for Quantifying Attention Flow in Transformers
Figure 3 for Quantifying Attention Flow in Transformers
Figure 4 for Quantifying Attention Flow in Transformers

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>