Forem

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Simple Next-Token Predictors are Powerful Universal Learners, Challenging Complexity Assumptions of Large Language Models

Simple Next-Token Predictors are Powerful Universal Learners, Challenging Complexity Assumptions of Large Language Models

Comments
4 min read
Drag Your Way to Photorealistic Image Manipulation: Interactive Point-based GAN Control

Drag Your Way to Photorealistic Image Manipulation: Interactive Point-based GAN Control

Comments
5 min read
Open-Source AI Tools: Opportunities and Challenges in Model Replication and Certification
Cover image for Open-Source AI Tools: Opportunities and Challenges in Model Replication and Certification

Open-Source AI Tools: Opportunities and Challenges in Model Replication and Certification

Comments
4 min read
Unlocking AI's Compositional Generalization: Skills-in-Context Boosts Language Model Performance

Unlocking AI's Compositional Generalization: Skills-in-Context Boosts Language Model Performance

Comments
5 min read
Model Openness Framework: Enhancing Transparency and Reproducibility in Generative AI

Model Openness Framework: Enhancing Transparency and Reproducibility in Generative AI

Comments
5 min read
xLSTM-UNet: Advanced AI Model Outperforms ViM-UNet in Medical Image Segmentation
Cover image for xLSTM-UNet: Advanced AI Model Outperforms ViM-UNet in Medical Image Segmentation

xLSTM-UNet: Advanced AI Model Outperforms ViM-UNet in Medical Image Segmentation

Comments
4 min read
Context Augmented Retrieval: Boosting LLM Performance with Efficient Information Retrieval
Cover image for Context Augmented Retrieval: Boosting LLM Performance with Efficient Information Retrieval

Context Augmented Retrieval: Boosting LLM Performance with Efficient Information Retrieval

Comments
1 min read
Use Guardrails for safeguarding generative AI applications built using custom or third-party models

Use Guardrails for safeguarding generative AI applications built using custom or third-party models

6
Comments
8 min read
Segment CT Scans with NVIDIA's VISTA-3D Model 00:45

Segment CT Scans with NVIDIA's VISTA-3D Model

Comments 3
1 min read
Exploring Text Preprocessing Techniques in Natural Language Processing
Cover image for Exploring Text Preprocessing Techniques in Natural Language Processing

Exploring Text Preprocessing Techniques in Natural Language Processing

6
Comments
2 min read
Reducing the Filtering Effect in Public School Admissions: A Bias-aware Analysis for Targeted Interventions

Reducing the Filtering Effect in Public School Admissions: A Bias-aware Analysis for Targeted Interventions

Comments 1
4 min read
Mathematics for Machine Learning - Day 10

Mathematics for Machine Learning - Day 10

5
Comments
6 min read
Is GPT-4 conscious?

Is GPT-4 conscious?

1
Comments 1
4 min read
Vision language models are blind
Cover image for Vision language models are blind

Vision language models are blind

6
Comments 1
4 min read
The 1 Principle to Build Regular Equivariant CNNs

The 1 Principle to Build Regular Equivariant CNNs

1
Comments
6 min read
Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency
Cover image for Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency

Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency

Comments
4 min read
Accuracy is Not All You Need
Cover image for Accuracy is Not All You Need

Accuracy is Not All You Need

Comments
4 min read
On scalable oversight with weak LLMs judging strong LLMs
Cover image for On scalable oversight with weak LLMs judging strong LLMs

On scalable oversight with weak LLMs judging strong LLMs

1
Comments
3 min read
Backpropagation through space, time, and the brain

Backpropagation through space, time, and the brain

Comments
3 min read
Qwen2 Technical Report
Cover image for Qwen2 Technical Report

Qwen2 Technical Report

1
Comments
4 min read
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Comments
4 min read
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash

Comments
4 min read
Parametric Matrix Models
Cover image for Parametric Matrix Models

Parametric Matrix Models

Comments
4 min read
xLSTMTime : Long-term Time Series Forecasting With xLSTM

xLSTMTime : Long-term Time Series Forecasting With xLSTM

2
Comments
4 min read
AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models
Cover image for AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models

AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models

Comments
3 min read
loading...