Telegram Group & Telegram Channel
💠 Compositional Learning Journal Club

Join us this week for an in-depth discussion on Compositional Learning in the context of cutting-edge text-to-image generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle compositional tasks and where improvements can be made.

This Week's Presentation:

🔹 Title: Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step


🔸 Presenter: Amir Kasaei

🌀 Abstract:
This paper explores the use of Chain-of-Thought (CoT) reasoning to improve autoregressive image generation, an area not widely studied. The authors propose three techniques: scaling computation for verification, aligning preferences with Direct Preference Optimization (DPO), and integrating these methods for enhanced performance. They introduce two new reward models, PARM and PARM++, which adaptively assess and correct image generations. Their approach improves the Show-o model, achieving a +24% gain on the GenEval benchmark and surpassing Stable Diffusion 3 by +15%.


📄 Papers: Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step


Session Details:
- 📅 Date: Sunday
- 🕒 Time: 5:30 - 6:30 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban

We look forward to your participation! ✌️



tg-me.com/RIMLLab/151
Create:
Last Update:

💠 Compositional Learning Journal Club

Join us this week for an in-depth discussion on Compositional Learning in the context of cutting-edge text-to-image generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle compositional tasks and where improvements can be made.

This Week's Presentation:

🔹 Title: Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step


🔸 Presenter: Amir Kasaei

🌀 Abstract:
This paper explores the use of Chain-of-Thought (CoT) reasoning to improve autoregressive image generation, an area not widely studied. The authors propose three techniques: scaling computation for verification, aligning preferences with Direct Preference Optimization (DPO), and integrating these methods for enhanced performance. They introduce two new reward models, PARM and PARM++, which adaptively assess and correct image generations. Their approach improves the Show-o model, achieving a +24% gain on the GenEval benchmark and surpassing Stable Diffusion 3 by +15%.


📄 Papers: Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step


Session Details:
- 📅 Date: Sunday
- 🕒 Time: 5:30 - 6:30 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban

We look forward to your participation! ✌️

BY RIML Lab




Share with your friend now:
tg-me.com/RIMLLab/151

View MORE
Open in Telegram


RIML Lab Telegram | DID YOU KNOW?

Date: |

NEWS: Telegram supports Facetime video calls NOW!

Secure video calling is in high demand. As an alternative to Zoom, many people are using end-to-end encrypted apps such as WhatsApp, FaceTime or Signal to speak to friends and family face-to-face since coronavirus lockdowns started to take place across the world. There’s another option—secure communications app Telegram just added video calling to its feature set, available on both iOS and Android. The new feature is also super secure—like Signal and WhatsApp and unlike Zoom (yet), video calls will be end-to-end encrypted.

How to Use Bitcoin?

n the U.S. people generally use Bitcoin as an alternative investment, helping diversify a portfolio apart from stocks and bonds. You can also use Bitcoin to make purchases, but the number of vendors that accept the cryptocurrency is still limited. Big companies that accept Bitcoin include Overstock, AT&T and Twitch. You may also find that some small local retailers or certain websites take Bitcoin, but you’ll have to do some digging. That said, PayPal has announced that it will enable cryptocurrency as a funding source for purchases this year, financing purchases by automatically converting crypto holdings to fiat currency for users. “They have 346 million users and they’re connected to 26 million merchants,” says Spencer Montgomery, founder of Uinta Crypto Consulting. “It’s huge.”

RIML Lab from tw


Telegram RIML Lab
FROM USA