BML Publication
BML reviews and publishes top articles and posts from ML researchers, engineers and practitioners
![Imagine yourself: Tuning-Free Personalized Image Generation](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Fmeta-ai-imagine-yourself.png&w=1200&q=75)
Imagine yourself: Tuning-Free Personalized Image Generation
Diffusion models have demonstrated remarkable efficacy across various image-to-image tasks. In this research, we introduce Imagine yourself, a state-of-the-art model designed for personalized image generation.
Read more →![LLMs develop their own understanding of reality as their language abilities improve](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2FMIT-EmRep.png&w=1200&q=75)
LLMs develop their own understanding of reality as their language abilities improve
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.
Read more →![CoT Prompting: Not the AI reasoning breakthrough we thought?](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2FYoutube_Thumbnails.avif&w=1200&q=75)
CoT Prompting: Not the AI reasoning breakthrough we thought?
Most people assume Chain-of-Thought (CoT) prompting is a way to make large language models reason better. But new research suggests its benefits might be more limited than we thought. By the end of this research breakdown, you'll understand why CoT might not be the game-changer we all hoped for – and how you can adjust your AI strategies accordingly.
Read more →![Extrinsic Hallucinations in LLMs](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Ffactuality-prompt-eval.png&w=1200&q=75)
Extrinsic Hallucinations in LLMs
Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term, hallucination has been somewhat generalized to cases when the model makes mistakes. Here, I would like to narrow down the problem of hallucination to cases where the model output is fabricated and not grounded by either the provided context or world knowledge.
Read more →![Can Generative AI Lead to AI Collapse?](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2F1_FmBXc5Vk4TUSThtFxovGMQ.jpg&w=1200&q=75)
Can Generative AI Lead to AI Collapse?
AI eating its own tail: the risk of model collapse in generative systems.
Read more →![Tips for Effectively Training Your Machine Learning Models](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Fcyberpunk_machine_learning_model_machines.png&w=1200&q=75)
Tips for Effectively Training Your Machine Learning Models
In machine learning projects, achieving optimal model performance requires paying attention to various steps in the training process. But before focusing on the technical aspects of model training, it is important to define the problem, understand the context, and analyze the dataset in detail. Once you have a solid grasp of the problem and data, you can proceed to implement strategies that’ll help you build robust and efficient models. Here, we outline five actionable tips that are essential for training machine learning models.
Read more →![Building a Machine Learning Platform [Definitive Guide]](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2FDiagram-experiment-tracker.webp&w=1200&q=75)
Building a Machine Learning Platform [Definitive Guide]
Moving across the typical machine learning lifecycle can be a nightmare. From gathering and processing data to building models through experiments, deploying the best ones, and managing them at scale for continuous value in...
Read more →![5 Effective Ways to Handle Imbalanced Data in Machine Learning](/_next/image?url=%2Fstatic%2Fimages%2Fnews%2Fbalance_scales_weighing_data_one_side_heavier.png&w=1200&q=75)
5 Effective Ways to Handle Imbalanced Data in Machine Learning
Here’s a something that new machine learning practitioners figure out almost immediately: not all datasets are created equal. It may now seem obvious to you, but had you considered this before undertaking machine learning projects on a real world dataset? As an example of a single class vastly outnumbering the rest, take for instance […]
Read more →![Tips for Effectively Training Your Machine Learning Models](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Fmlm-header-bala-feature-engg-tips.png&w=1200&q=75)
Tips for Effectively Training Your Machine Learning Models
Feature engineering is an important step in the machine learning pipeline. It is the process of transforming data in its native format into meaningful features to help the machine learning model learn better from the data.If done right, feature engineering can significantly enhance the performance of machine learning algorithms. Beyond the basics of understanding your data and preprocessing, effective feature engineering involves creating interaction terms, generating indicator variables, and binning features into buckets. These techniques help extract relevant information from the data and help build robust machine learning solutions. In this guide, we’ll explore these feature engineering techniques by spinning up a sample housing dataset.
Read more →