🚀 Open Research Position: Hallucination Detection & Mitigation in Vision-Language Models (VLMs)

We are looking for motivated students to join our research on hallucination detection and mitigation in Visual Question Answering (VQA) models at RIML Lab.

🔍 Project Description
Visual Question Answering (VQA) models generate text-based answers by analyzing an input image and a query. Despite their success, they still suffer from hallucination issues, where responses are incorrect, misleading, or not grounded in the image content.
This research focuses on detecting and mitigating these hallucinations to enhance the reliability and accuracy of VQA models.

📄 Relevant Papers
"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding"
"CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models"
"Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization"

🔹 Must-Have Requirements
- Strong Python programming skills
- Knowledge of deep learning (especially VLMs)
- Hands-on experience with PyTorch
- Ready to start immediately

⏳ Workload
Commitment: At least 20 hours per week


📌 Note: Filling out this form does not guarantee acceptance. Only shortlisted candidates will receive an email notification.

📅 Application Deadline: March 28, 2025
🔗 Apply here: Google Form

🛑 This position is now closed. Shortlisted candidates have been notified by March 30, 2025. Thank you to everyone who applied! Stay tuned for future opportunities.

📧 For inquiries: [email protected]
💬 Telegram: @amirezzati

@RIMLLab
#research_position #ML_research #DeepLearning #VQA

گروه Geometric Deep Learning به مباحث مرتبط با اشیاء هندسی می‌پردازد. پیش‌بینی رفتار پروتئین‌ها یا مولکول‌های شیمیایی که ساختار هندسی‌شون در اینکه چطوری در عمل رفتار می‌کنن مؤثره. مباحث تئوری مرتبط باهاش یه چیزی میان گراف و جبر و دیپ لرنینگ هست.
تحت نظر آقای سید محمد حسینی، دانشجوی دکترای مشترک دکتر جعفری و دکتر رهبان

https://docs.google.com/forms/d/e/1FAIpQLSd8FEHOmscpFo6R2SEA5LbFQ8fyM518yXIe07G29XYLk6Rgzg/viewform

پست لینکدین دکتر رهبان

نوروز باستانی و سال جدید با آغاز بهار شروع شد. در سال گذشته موقعیت‌های بسیاری را با دانشجویانم و اعضای آزمایشگاه RIML دور یکدیگر جمع گشتیم و جشن گرفتیم. من معتقدم که دانشجویان مهم‌ترین سرمایه‌های این کشور هستند و ما باید قدر ایشان را بیشتر بدانیم.
در سال گذشته ما در آزمایشگاه سعی داشتیم تا در جهت حل مشکلات کشور و علم قدم برداریم و در جهت بهتر کردن زندگی انسان‌ها تلاش کنیم. همچنین ۱۰ مقاله در کنفرانس‌ها و ژورنال‌های برتر CVPR, ICLR, ICML, NeurIPS, TMLR, ECCV با موضوع اعتمادپذیری در یادگیری ماشین منتشر کردیم.
همچنین در برگزاری ورکشاپ Spurious Correlation and Shortcut Learning در کنفرانس ICLR2025 که برای اولین بار توسط یک تیم از ایران در یکی از کنفرانس‌های برتر هوش مصنوعی اتفاق می‌افتد، تلاش کردیم.
همچنین اعضای آزمایشگاه نقش مهم و پررنگی در برگزاری مسابقه بین‌المللی هوش مصنوعی RAYAN داشتند.
ممنون از تیم فوق‌العاده، همکاران و حمایت‌کنندگان که این سال را الهام‌بخش و فوق‌العاده کردند.

#open_position -> closed

We are seeking 2–3 interns/collaborators:
- 2 positions focused primarily on technical aspects 
- 1 position with a 50/50 focus on theoretical and applied Machine Learning 

If you are interested in research on Histopathology Whole Slide Images (WSIs), VLMs, vLLMs, Self-Supervised Learning (SSL), and/or Theoretical Machine Learning—with the goal of submitting papers to conferences such as NeurIPS, ICLR, CVPR, ICASSP, WACV, or journals like IEEE Transactions on Medical Imaging, TMLR, and JMLR—please send your CV to [email protected]

For more context, you can review these relevant papers:
1. https://arxiv.org/abs/2408.08258
2. https://arxiv.org/abs/2306.11207
3. https://ieeexplore.ieee.org/document/10643565


Technical Requirements
- English proficiency at least B2 (preferred) or B1 
- Familiarity with Machine Learning and PyTorch 
- Experience with Git
- Ability to run and interpret academic GitHub repositories 
- Clean coding practices
- Solid understanding of Mathematics; preferably very strong in Probability and Statistics, Stochastic Processes, Information Theory, Machine Learning Theory, and High-Dimensional Statistics [for the theory-focused candidate]

Non-Technical Requirements
- Persistent and “try-hard” attitude 
- Available on-call 
- Enthusiastic about learning new platforms 
- Willing to dedicate significant time 
- Extremely resilient, comfortable with frequent schedule changes, and unafraid of polite rejections [for the theory-focused candidate]

Benefits
- Supportive RIML environment 
- Opportunity to work closely with Dr. Rohban (mainly for the theory-focused position) 
- Possibility of a research-related recommendation letter from Dr. Rohban

Final Thing
Guys, I really mean everything stated above for the Non-Technical Requirements, if you don’t meet them, please do’t email.

Research Position at the Center for Information Systems and Data Science, Sharif University in Collaboration with a Top-Three Global Institution or medical university school in  Bioinformatics.

Projects Descriptions:

1. Utilizing Large Language Models and Retrieval-Augmented Generation (RAG): Applying  knowledge graph  in medicine, inspired by Stanford University's work.

2. Predicting Profiles for Protein Sequences Using Natural Language Processing: Leveraging the performance of transformers in natural languages by treating protein sequences as a language, similar to Microsoft's research.

3. Applying Manifold Learning and Riemannian Geometry in Protein Dynamics Analysis: Designing and predicting the effects of protein dynamics using approaches akin to those from Cambridge University.

✅Requirements:
A bachelor's and master's student with strong implementation skills and clean coding in artificial intelligence, capable of reading and analyzing new Bioinformatics papers, ideating and extensively testing with well-known deep and reinforcement learning architectures, and possessing intermediate Bioinformatics or biology knowledge.

💥This project will be conducted in collaboration with three professors from Sharif University's Computer and Electrical Engineering faculties and supervised by a senior scientist from one of the top three universities in the United States.

🆔To apply and submit your CV, please contact via email with the subject line "Research Position in Bioinformatics":
[email protected]

فیلم جلسه ۴ الی ۷ درس System 2 در آپارات و یوتیوب آزمایشگاه آپلود شد.

یوتیوب
آپارات

تا جلسه ۱۲ آپلود شد.

🚀 Join Nan Jiang’s Talk at Sharif University of Technology

🎙 Title: Rethinking the Theoretical Foundation of Reinforcement Learning

👨‍🏫 Speaker: Nan Jiang (Associate Professor, University of Illinois Urbana-Champaign)
📅 Date: Thursday (Apr 24, 2025)
🕗 Time: 7:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/KMjp2cGrnWCqSJAh7

@DeepRLCourse

دوستان عزیزی که درخواست دادین متاسفانه تعداد زیادی از ایمیل‌هاتون اسپم شده بود و یک‌مقدار فرایند بررسی طولانی‌تر میشه. ایشالا تا چند روز آینده به همه پاسخ نهایی اعلام میشه.

🚀 Join this insightful Discussion at Sharif University of Technology

🎙 Subject: Exploration in Reinforcement Learning

👨‍🏫 Guest: Ian Osband (Researcher in Artificial Intelligence, formerly at DeepMind and OpenAI)
📅 Date: Thursday (May 1, 2025)
🕗 Time: 3:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/TWqkmomDAKDdioxu5

@DeepRLCourse

🚀 Join Benjamin Eysenbach’s Talk at Sharif University of Technology

🎙 Title: Self-Supervised Agents: Exploring and Learning with Minimal Feedback

👨‍🏫 Speaker: Benjamin Eysenbach (Assistant Professor, Princeton University)
📅 Date: Thursday (May 1, 2025)
🕗 Time: 4:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/j4pUEa89N8kzCRpb9

@DeepRLCourse

🚀 Join Jeff Clune’s Talk at Sharif University of Technology

🎙 Title: Open-Ended and AI-Generating Algorithms in the Era of Foundation Models

👨‍🏫 Speaker: Jeff Clune (University of British Columbia, Vector Institute, DeepMind)
📅 Date: Friday (May 2, 2025)
🕗 Time: 8:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/57sRPPLWMd9dcF8F9

@DeepRLCourse

🚀 Research Internship Opportunities
We are seeking highly motivated interns or collaborators for upcoming research projects in the areas of Low-Level Hardware Design and Multi-Agent Large Language Models (LLMs). The goal is to produce high-quality research with potential for submission to top-tier conferences or journals.

🤖 Position — LLM & Multi-Agent Research Intern
Focus: Multi-Agent Systems, Large Language Models, and LLM Orchestration
Technical Requirements:
• Proficiency in Python and PyTorch
• Familiarity with transformers, LangChain, vLLMs, or agent frameworks
• Experience with Git and working with academic codebases
• Basic understanding of Machine Learning

🔧 Position — Low-Level Hardware Intern
Focus: Verilog / SystemVerilog, FPGA-based Systems, and Hardware Acceleration
Technical Requirements:
• Strong knowledge of digital logic design
• Hands-on experience with Verilog or SystemVerilog
• Familiarity with FPGA toolchains (e.g., Vivado, ModelSim)
• Comfortable reading and adapting low-level academic GitHub repositories
• Clean and modular hardware coding practices

📌 General Requirements (All Positions)
• English proficiency
• Independent, resilient, and willing to commit serious time
• Able to work in a fast-paced, research-oriented environment
• Passionate about learning new tools and solving challenging problems
• On-call availability and a strong sense of accountability

📨 To Apply:
Please fill out this form completely and upload your CV.

📅 Application Deadline: May 15, 2025

📚 For relevant background reading, please see:
1. https://arxiv.org/abs/2412.07822
2. https://arxiv.org/abs/2503.16528

🚀 Join Peter Dayan’s Talk at Sharif University of Technology

🎙 Title: Mind Games: Explorations in Cognitive Hierarchies (Abstract)

👨‍🏫 Speaker: Peter Dayan (Max Planck Institute for Biological Cybernetics)
📅 Date: Friday (May 16, 2025)
🕗 Time: 1:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/UTqGf7GAYzvon1xE6

@DeepRLCourse

🚀 Join Benjamin Van Roy’s Talk at Sharif University of Technology

🎙 Title: Exploration in Reinforcement Learning

👨‍🏫 Speaker: Benjamin Van Roy (Stanford University and Google DeepMind)
📅 Date: Friday (May 16, 2025)
🕗 Time: 7:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/RMDzNCBFKdzsRDzR8

@DeepRLCourse

🚀 Join Ida Momennejad’s Talk at Sharif University of Technology

🎙 Title: Memory, Planning, and Reasoning in Brains & AI

👨‍🏫 Speaker: Ida Momennejad (Microsoft Research NYC)
📅 Date: Friday (May 16, 2025)
🕗 Time: 4:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/qi5WA7FSWyoLyEsA7

@DeepRLCourse

🚀 Join Abhishek Gupta’s Talk at Sharif University of Technology

🎙 Title: World Models Beyond Autoregressive Next State Prediction (Abstract)

👨‍🏫 Speaker: Abhishek Gupta (University of Washington)
📅 Date: Friday (May 16, 2025)
🕗 Time: 6:00 PM Iran Time
💡 Sign Up Here: https://forms.gle/6mig87mbUwfgtRtv5

@DeepRLCourse

🚀 Join Wolfram Schultz’s Talk at Sharif University of Technology

🎙 Title: Neuronal Reward Mechanisms underlying Reinforcement Learning

👨‍🏫 Speaker: Wolfram Schultz (University of Cambridge)
📅 Date: Thursday (May 22, 2025)
🕗 Time: 4:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/PgdKCFMq5j73XzHE7

@DeepRLCourse

🚀 Research Opportunity – LLM Reasoning Project

⛔️ Position Closed

We are looking for a motivated student to join a 50/50 Research & Development project focused on reasoning in Large Language Models (LLMs).

🔍 Requirements:
1. Solid understanding of Deep Learning
2. Experience working with LLMs
3. Proficiency in PyTorch
4. Familiarity with Prompt Engineering
5. Ability to write clean, maintainable code

💡 Soft Skills:
1. Curiosity about LLMs and research
2. Strong teamwork and communication skills
3. Ability to commit at least 20 hours per week

📚 Some related resources to explore:
1. CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning
2. Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
3. https://www.solvingforpattern.org/2013/04/10/creativity-through-abductive-reasoning/

⛔️ Position Closed

This project is jointly supervised by Dr. Rahban and Dr. Jafari.