Research Week 1403.pdf
2.4 MB
با سلام. اسلایدهای ارائه هفته پژوهش در مورد مقاله نوریپس پذیرفته شده از RIML خدمت عزیزان تقدیم می‌شود. همینطور در این رشته توییت توضیحاتی در مورد مقاله داده‌ام: https://x.com/MhRohban/status/1867803097596338499
Forwarded from Arash
📣 TA Application Form
🤖 Deep Reinforcement Learning
🧑🏻🏫 Dr. Mohammad Hossein Rohban
⏰ Deadline: December 31th
https://docs.google.com/forms/d/e/1FAIpQLSduvRRAnwi6Ik9huMDFWOvZqAWhr7HHlHjXdZbst55zSv5Hmw/viewform
🤖 Deep Reinforcement Learning
🧑🏻🏫 Dr. Mohammad Hossein Rohban
⏰ Deadline: December 31th
https://docs.google.com/forms/d/e/1FAIpQLSduvRRAnwi6Ik9huMDFWOvZqAWhr7HHlHjXdZbst55zSv5Hmw/viewform
📣 TA Application Form
🤖 Course: System-2 AI
🧑🏻🏫 Instructors: Dr. Rohban, Dr. Soleymani, Mr. Samiei
⏰ Deadline: January 23rd
https://docs.google.com/forms/d/e/1FAIpQLSewqI25q5c3DcsdcCzhCVg42motC2S-bg_xuuPWZ0wA60rYHQ/viewform?usp=dialog
🤖 Course: System-2 AI
🧑🏻🏫 Instructors: Dr. Rohban, Dr. Soleymani, Mr. Samiei
⏰ Deadline: January 23rd
https://docs.google.com/forms/d/e/1FAIpQLSewqI25q5c3DcsdcCzhCVg42motC2S-bg_xuuPWZ0wA60rYHQ/viewform?usp=dialog
💠 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! ✌️
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! ✌️
arXiv.org
Can We Generate Images with CoT? Let's Verify and Reinforce...
Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be...
RIML Lab
💠 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…
جلسه‌ی امروز متاسفانه برگزار نخواهد شد
سایر جلسات از طریق همین کانال اطلاع رسانی خواهد شد
سایر جلسات از طریق همین کانال اطلاع رسانی خواهد شد
💠 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: Wednesday
- 🕒 Time: 2:15 - 3:15 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban
We look forward to your participation! ✌️
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: Wednesday
- 🕒 Time: 2:15 - 3:15 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban
We look forward to your participation! ✌️
arXiv.org
Can We Generate Images with CoT? Let's Verify and Reinforce...
Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be...
Research Position at the Sharif Center for Information Systems and Data Science:
We are seeking several highly skilled students for a project with a deadline for the NeurIPS conference, focusing on predictive maintenance for batteries and bearings.
Candidates should have strong abilities in precise implementation and integrating new ideas into various architectures such as contrastive learning, transformers, PINN(Physics-informed neural networks) and diffusion models to rapidly enhance the research group's capabilities.
The project is under the direct collaboration of Dr. Babak Khalaj, Dr. Siavash Ahmadi, and Dr. Mohammad Hossein Rohban.
To apply and submit your CV, please contact via email: [email protected]
We are seeking several highly skilled students for a project with a deadline for the NeurIPS conference, focusing on predictive maintenance for batteries and bearings.
Candidates should have strong abilities in precise implementation and integrating new ideas into various architectures such as contrastive learning, transformers, PINN(Physics-informed neural networks) and diffusion models to rapidly enhance the research group's capabilities.
The project is under the direct collaboration of Dr. Babak Khalaj, Dr. Siavash Ahmadi, and Dr. Mohammad Hossein Rohban.
To apply and submit your CV, please contact via email: [email protected]
Postdoctoral Research Position Available
The Robust and Interpretable Machine Learning (RIML) Lab at the Computer Engineering Department of Sharif University of Technology is seeking a number of highly motivated and talented postdoctoral researchers to join our team. The successful candidate will work on cutting-edge research involving Large Language Model (LLM) Agents.
• 1-2 years, with the possibility of extension based on performance and funding
• Conduct innovative research on LLM Agents
• Collaborate with a multidisciplinary team of researchers
• Publish high-quality research papers in top-tier conferences and journals
• Mentor graduate and undergraduate students
• Present research findings at international conferences and workshops
Qualifications:
• Ph.D. in Computer Science, Computer Engineering, or a related field earned at most in the last 2 years
• Strong background in natural language processing, machine learning, and artificial intelligence
• Experience with large language models and their applications
• Excellent programming skills (Python, and PyTorch, etc.)
• Strong publication record in relevant areas
• Excellent communication and teamwork skills
Interested candidates should submit the following documents to [email protected] by Feb. 7th:
• A cover letter describing your research interests and career goals
• A detailed CV, including a list of publications
• Contact information for at least two references
For more information about our recent research topics, please check out my google scholar: https://scholar.google.com/citations?hl=en&user=pRyJ6FkAAAAJ&view_op=list_works&sortby=pubdate.
The Robust and Interpretable Machine Learning (RIML) Lab at the Computer Engineering Department of Sharif University of Technology is seeking a number of highly motivated and talented postdoctoral researchers to join our team. The successful candidate will work on cutting-edge research involving Large Language Model (LLM) Agents.
• 1-2 years, with the possibility of extension based on performance and funding
• Conduct innovative research on LLM Agents
• Collaborate with a multidisciplinary team of researchers
• Publish high-quality research papers in top-tier conferences and journals
• Mentor graduate and undergraduate students
• Present research findings at international conferences and workshops
Qualifications:
• Ph.D. in Computer Science, Computer Engineering, or a related field earned at most in the last 2 years
• Strong background in natural language processing, machine learning, and artificial intelligence
• Experience with large language models and their applications
• Excellent programming skills (Python, and PyTorch, etc.)
• Strong publication record in relevant areas
• Excellent communication and teamwork skills
Interested candidates should submit the following documents to [email protected] by Feb. 7th:
• A cover letter describing your research interests and career goals
• A detailed CV, including a list of publications
• Contact information for at least two references
For more information about our recent research topics, please check out my google scholar: https://scholar.google.com/citations?hl=en&user=pRyJ6FkAAAAJ&view_op=list_works&sortby=pubdate.
Google
Mohammad Hossein Rohban
Associate Professor in Computer Engineering, Sharif University of Technology - Cited by 4,439 - Machine Learning - Statistics - Computational Biology
Research Assistant Position Available
The Robust and Interpretable Machine Learning (RIML) Lab at the Computer Engineering Department of Sharif University of Technology is seeking a number of highly motivated and talented research assistants to join our team to work on Large Language Model (LLM) Agents.
Qualifications:
• M.Sc. in Computer Science, Computer Engineering, or a related field earned at most in the last 2 years
• Strong background in natural language processing, machine learning, and artificial intelligence
• Experience with large language models and their applications
• Excellent programming skills (Python, and PyTorch, etc.)
• Excellent communication and teamwork skills
Interested candidates should submit the following documents to [email protected] by Feb. 12th:
• A cover letter describing their research/career goals and why they are interested in this position.
• A detailed CV, including a list of publications
For more information about our recent research topics, please check out my google scholar: https://scholar.google.com/citations?hl=en&user=pRyJ6FkAAAAJ&view_op=list_works&sortby=pubdate.
The Robust and Interpretable Machine Learning (RIML) Lab at the Computer Engineering Department of Sharif University of Technology is seeking a number of highly motivated and talented research assistants to join our team to work on Large Language Model (LLM) Agents.
Qualifications:
• M.Sc. in Computer Science, Computer Engineering, or a related field earned at most in the last 2 years
• Strong background in natural language processing, machine learning, and artificial intelligence
• Experience with large language models and their applications
• Excellent programming skills (Python, and PyTorch, etc.)
• Excellent communication and teamwork skills
Interested candidates should submit the following documents to [email protected] by Feb. 12th:
• A cover letter describing their research/career goals and why they are interested in this position.
• A detailed CV, including a list of publications
For more information about our recent research topics, please check out my google scholar: https://scholar.google.com/citations?hl=en&user=pRyJ6FkAAAAJ&view_op=list_works&sortby=pubdate.
Google
Mohammad Hossein Rohban
Associate Professor in Computer Engineering, Sharif University of Technology - Cited by 4,439 - Machine Learning - Statistics - Computational Biology
💠 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: Correcting Diffusion Generation through Resampling
🔸 Presenter: Ali Aghayari
🌀 Abstract:
This paper addresses distributional discrepancies in diffusion models, which cause missing objects in text-to-image generation and reduced image quality. Existing methods overlook this root issue, leading to suboptimal results. The authors propose a particle filtering framework that uses real images and a pre-trained object detector to measure and correct these discrepancies through resampling. Their approach improves object occurrence by 5% and FID by 1.0 on MS-COCO, outperforming previous methods in generating more accurate and higher-quality images.
📄 Papers: Correcting Diffusion Generation through Resampling
Session Details:
- 📅 Date: Tuesday
- 🕒 Time: 5:30 - 6:30 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban
We look forward to your participation! ✌️
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: Correcting Diffusion Generation through Resampling
🔸 Presenter: Ali Aghayari
🌀 Abstract:
This paper addresses distributional discrepancies in diffusion models, which cause missing objects in text-to-image generation and reduced image quality. Existing methods overlook this root issue, leading to suboptimal results. The authors propose a particle filtering framework that uses real images and a pre-trained object detector to measure and correct these discrepancies through resampling. Their approach improves object occurrence by 5% and FID by 1.0 on MS-COCO, outperforming previous methods in generating more accurate and higher-quality images.
📄 Papers: Correcting Diffusion Generation through Resampling
Session Details:
- 📅 Date: Tuesday
- 🕒 Time: 5:30 - 6:30 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban
We look forward to your participation! ✌️
arXiv.org
Correcting Diffusion Generation through Resampling
Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has...
🚀 Join Richard Sutton’s Talk at Sharif University of Technology
🎙 Title: The Increasing Role of Sensorimotor Experience in Artificial Intelligence
👨🏫 Speaker: Rich Sutton (Keen Technologies, University of Alberta, OpenMind Research Institute)
📅 Date: Wednesday
🕗 Time: 8 PM Iran Time
💡 Sign Up Here: https://forms.gle/q1M7qErWvydFxR9m6
🎙 Title: The Increasing Role of Sensorimotor Experience in Artificial Intelligence
👨🏫 Speaker: Rich Sutton (Keen Technologies, University of Alberta, OpenMind Research Institute)
📅 Date: Wednesday
🕗 Time: 8 PM Iran Time
💡 Sign Up Here: https://forms.gle/q1M7qErWvydFxR9m6
Forwarded from System 2 - Spring 2025
🎥 فیلم جلسه اول درس System 2
🔸 موضوع: Introduction & Motivation
🔸 مدرسین: دکتر رهبان و آقای سمیعی
🔸 تاریخ: ۲۱ بهمن ۱۴۰۳
🔸لینک یوتیوب
🔸 لینک آپارات
🔸 موضوع: Introduction & Motivation
🔸 مدرسین: دکتر رهبان و آقای سمیعی
🔸 تاریخ: ۲۱ بهمن ۱۴۰۳
🔸لینک یوتیوب
🔸 لینک آپارات
🚀 We will be live from 19:45. Join us here:
https://www.youtube.com/watch?v=Y4UZNc4eh4U
🎙 Title: The Increasing Role of Sensorimotor Experience in Artificial Intelligence
👨🏫 Speaker: Rich Sutton (Keen Technologies, University of Alberta, OpenMind Research Institute)
https://www.youtube.com/watch?v=Y4UZNc4eh4U
🎙 Title: The Increasing Role of Sensorimotor Experience in Artificial Intelligence
👨🏫 Speaker: Rich Sutton (Keen Technologies, University of Alberta, OpenMind Research Institute)
🚀 Join Michael Littman’s Talk at Sharif University of Technology
🎙 Title: Assessing the Robustness of Deep RL Algorithms
👨🏫 Speaker: Michael Littman (Brown University, Humanity-Centered Robotics Initiative)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 5:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/amgtsGrDVn4mdRai9
🎙 Title: Assessing the Robustness of Deep RL Algorithms
👨🏫 Speaker: Michael Littman (Brown University, Humanity-Centered Robotics Initiative)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 5:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/amgtsGrDVn4mdRai9
🚀 Join Chris Watkins’s Talk at Sharif University of Technology
🎙 Title: From Shortest Paths to Value Iteration to Q-Learning
👨🏫 Speaker: Chris Watkins (Professor of Computer Science, Royal Holloway)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 3:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/ET3Y5jB6Jt9vkQ2x9
@DeepRLCourse
🎙 Title: From Shortest Paths to Value Iteration to Q-Learning
👨🏫 Speaker: Chris Watkins (Professor of Computer Science, Royal Holloway)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 3:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/ET3Y5jB6Jt9vkQ2x9
@DeepRLCourse
🚀 Join Peter Stone’s Talk at Sharif University of Technology
🎙 Title: Multiagent RL: Cooperation and Competition
👨🏫 Speaker: Peter Stone (Professor of Computer Science, University of Texas at Austin)
📅 Date: Thursday (Feb 27, 2025)
🕗 Time: 3:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/M4QxTUWimGyvUmPv7
@DeepRLCourse
🎙 Title: Multiagent RL: Cooperation and Competition
👨🏫 Speaker: Peter Stone (Professor of Computer Science, University of Texas at Austin)
📅 Date: Thursday (Feb 27, 2025)
🕗 Time: 3:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/M4QxTUWimGyvUmPv7
@DeepRLCourse
🔥 Open Position: Research Intern/Collaborator – Virtual Staining of Histopathology Images
🔸 Join our CVPR conference paper project on Virtual Staining!
We are looking for dedicated researchers, with a preference for local candidates, as this role requires 20 hrs/week of in-person collaboration.
🔸 Technical Requirements:
💠 Strong English reading & writing skills for technical documentation.
💠 Hands-on experience with:
🌀 PyTorch & deep learning fundamentals
🌀 Running & troubleshooting GitHub repositories
🌀 Exposure to generative models (GANs, diffusion models) is a plus!
🌀 Ability to write clean, organized Python code
🔸 Non-Technical Requirements:
💠 Commitment to 20 hrs/week in-person work at our lab
💠 Persistence in solving technical challenges (e.g., debugging model training)
💠 Strong teamwork & communication skills
💠 Curiosity about medical imaging & generative AI
🔸 Why Join?
💠 Mentorship from Dr. Rohban & the RIML Lab team
💠 Hands-on experience with generative models (GANs/Diffusion) for medical imaging
💠 Work with collaborative coding (GitHub) & Linux-based workflows
💠 Opportunity for CVPR-tier co-authorship & strong recommendation letters
📩 How to Apply
The deadline for submission has already passed
🔸 Join our CVPR conference paper project on Virtual Staining!
We are looking for dedicated researchers, with a preference for local candidates, as this role requires 20 hrs/week of in-person collaboration.
🔸 Technical Requirements:
💠 Strong English reading & writing skills for technical documentation.
💠 Hands-on experience with:
🌀 PyTorch & deep learning fundamentals
🌀 Running & troubleshooting GitHub repositories
🌀 Exposure to generative models (GANs, diffusion models) is a plus!
🌀 Ability to write clean, organized Python code
🔸 Non-Technical Requirements:
💠 Commitment to 20 hrs/week in-person work at our lab
💠 Persistence in solving technical challenges (e.g., debugging model training)
💠 Strong teamwork & communication skills
💠 Curiosity about medical imaging & generative AI
🔸 Why Join?
💠 Mentorship from Dr. Rohban & the RIML Lab team
💠 Hands-on experience with generative models (GANs/Diffusion) for medical imaging
💠 Work with collaborative coding (GitHub) & Linux-based workflows
💠 Opportunity for CVPR-tier co-authorship & strong recommendation letters
📩 How to Apply
The deadline for submission has already passed
Forwarded from Deep RL (Sp25)
🚀 Join Jakob Foerster’s Talk at Sharif University of Technology
🎙 Title: Reinforcement Learning at the Hyperscale!
👨🏫 Speaker: Jakob Foerster (Associate Professor, University of Oxford)
📅 Date: Friday (Mar 7, 2025)
🕗 Time: 1:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/HYDizuvMkxVGA5hu7
@DeepRLCourse
🎙 Title: Reinforcement Learning at the Hyperscale!
👨🏫 Speaker: Jakob Foerster (Associate Professor, University of Oxford)
📅 Date: Friday (Mar 7, 2025)
🕗 Time: 1:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/HYDizuvMkxVGA5hu7
@DeepRLCourse
Forwarded from 10th WSS ☃️
Please open Telegram to view this post
VIEW IN TELEGRAM
RIML Lab
کد تخفیف ۵۰ درصدی مخصوص اعضای کانال:
RIMLLab