23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
🔹 Title: Explain Before You Answer: A Survey on Compositional Visual Reasoning
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17298
• PDF: https://arxiv.org/pdf/2508.17298
• Project Page: https://github.com/pokerme7777/Compositional-Visual-Reasoning-Survey
• Github: https://github.com/pokerme7777/Compositional-Visual-Reasoning-Survey
@Machine_learn
"GPT-5 moves from human-comparable to above human-expert performance"
GPT-5 outperforms licensed human experts by 25-30% and achieves SOTA results on the US medical licensing exam and the MedQA benchmark.
I sound like a broken record, but AI models are better than most doctors.
📚 Paper
@Machine_learn
با عرض سلام ما برای یکی از مقالاتمون در حوزه ی پزشکی نیاز به نفر ۴ ام داریم با قبولی شرایط پرداخت میتونیم اضافه کنیم.
@Raminmousa
📃 Energy-Based Transformers are Scalable Learners and Thinkers
Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. In this paper, we ask the question "Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning?" Interestingly, we find the answer is yes, by learning to explicitly verify the compatibility between inputs and candidate-predictions, and then re-framing prediction problems as optimization with respect to this verifier. Specifically, we train Energy-Based Transformers (EBTs) -- a new class of Energy-Based Models (EBMs) -- to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy minimization until convergence. Across both discrete (text) and continuous (visual) modalities, we find EBTs scale faster than the dominant Transformer++ approach during training, achieving an up to 35% higher scaling rate with respect to data, batch size, parameters, FLOPs, and depth. During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks, and EBTs outperform Diffusion Transformers on image denoising while using fewer forward passes.
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
📚 Read
@Machine_learn
با عرض سلام ما برای یکی از مقالاتمون در حوزه ی پزشکی نیاز به نفر ۴ ام داریم با قبولی شرایط پرداخت میتونیم اضافه کنیم.
@Raminmousa
Crystal Generation with Space Group Informed Transformer
🖥 Github: https://github.com/deepmodeling/crystalformer
📕 Paper: https://arxiv.org/abs/2504.02367v1
🔗 Dataset: https://paperswithcode.com/dataset/alex-20
@Machine_learn
با عرض سلام این مورد باقی مونده و این هفته سابمیت مقاله می باشد.
@Raminmousa
با عرض سلام ما برای یکی از مقالاتمون در حوزه ی پزشکی نیاز به نفر ۴ ام داریم با قبولی شرایط پرداخت میتونیم اضافه کنیم.
@Raminmousa
Awesome Claude Code 🤝 Awesome Claude Code Agents
📌 Github
@Machine_learn
با عرض سلام اين مقاله اين هفته سابميت ميشه و فقط يك نفر كم داريم....!
@Raminmousa
🔹 Title: Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
• PDF: https://arxiv.org/pdf/2507.23698
• Github: https://github.com/CraftJarvis/ROCKET-3
@Machine_learn
GPT-5 prompting guide
📚 Read
@Machine_learn
📄 Generative Artificial Intelligence in Healthcare: Applications, Implementation Challenges, and Future Directions
📎 Study the paper
@Machine_learn
Title: Personalized Safety Alignment for Text-to-Image Diffusion Models
Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01151
• PDF: https://arxiv.org/pdf/2508.01151
• Github: https://m-e-agi-lab.github.io/PSAlign/
@Machine_learn
📃 A Comprehensive and Systematic Review for Deep Learning-Based De Novo Peptide Sequencing
📎 Study the paper
@Machine_learn
Scientific Visualization: Python + Matplotlib
📚 Book
@Machine_learn
"Transcendence" is when an LLM, trained on diverse data from many experts, can exceed the ability of the individuals in its training data.
This paper demonstrates three types: when AI picks the right expert skill to use, when AI has less bias than experts & when it generalizes.
📚 Read
@Machine_learn
Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against LLMs
📚 Paper
@Machine_learn
🔹 Title: Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
🔹 Publication Date: Published on Aug 25
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18032
• PDF: https://arxiv.org/pdf/2508.18032
@Machine_learn
🔹 Title: Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2507.23698
• PDF: https://arxiv.org/pdf/2507.23698
• Github: https://github.com/CraftJarvis/ROCKET-3
@Machine_learn
The Data Engineering Handbook
📚 Github
@Machine_learn
📑 Machine learning-based drug-drug interaction prediction: a critical review of models, limitations, and data challenges
📎 Study the paper
@Machine_learn
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
📚Read
@Machine_learn
Foundations of
Large Language Models
@Machine_learn
Introduction to Python for
Econometrics, Statistics and Data Analysis
📚 Github
@Machine_learn
با عرض سلام ما برای یکی از مقالاتمون در حوزه ی پزشکی نیاز به نفر ۴ ام داریم با قبولی شرایط پرداخت میتونیم اضافه کنیم.
@Raminmousa
We offer you daily Udemy courses for free and without any fees.
/channel/DataScienceC
Breaking the Sorting Barrier for Directed Single-Source Shortest Paths
📚 link
@Machine_learn
CoAct-1: Computer-using Agents with Coding as Actions
📚 Read
@Machine_learn