DEV Community

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

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Jev After Eight Days of Independent Tests: Level With Mid-Price LLMs, Behind the Frontier

Jev After Eight Days of Independent Tests: Level With Mid-Price LLMs, Behind the Frontier

4
Comments 2
17 min read
Robot Training Data Is Messier Than You Think: Auditing 4,959 Episodes with an Open-Source Tool

Robot Training Data Is Messier Than You Think: Auditing 4,959 Episodes with an Open-Source Tool

Comments 1
9 min read
AI Can Remember Everything. That's Exactly the Problem.

AI Can Remember Everything. That's Exactly the Problem.

2
Comments 2
3 min read
LTX-2.5: How a Diffusion-Based Video Decoder Changes the Open-Weights Video Generation Stack

LTX-2.5: How a Diffusion-Based Video Decoder Changes the Open-Weights Video Generation Stack

Comments
5 min read
Pythonaibrain-NLP 0.2.0 Is Now on PyPI — A Structured NLU/NLG Architecture for Python

Pythonaibrain-NLP 0.2.0 Is Now on PyPI — A Structured NLU/NLG Architecture for Python

Comments
4 min read
My Understanding of Machine Learning and Its Real-World Applications

My Understanding of Machine Learning and Its Real-World Applications

Comments
4 min read
AI Model Evaluation: Best Practices for Testing and Validation

AI Model Evaluation: Best Practices for Testing and Validation

1
Comments
2 min read
World‑to‑Wrist: Task‑Conditioned Wrist Modeling for Fine‑Grained Robot Manipulation

World‑to‑Wrist: Task‑Conditioned Wrist Modeling for Fine‑Grained Robot Manipulation

Comments
2 min read
Distilled Chain‑of‑Thought Can Be Gaming Exploited

Distilled Chain‑of‑Thought Can Be Gaming Exploited

Comments
2 min read
SkewAdam cuts training memory over 60%

SkewAdam cuts training memory over 60%

Comments
2 min read
Segment‑level consolidation reduces construction tokens by up to ~86% with modest throughput gains

Segment‑level consolidation reduces construction tokens by up to ~86% with modest throughput gains

Comments
2 min read
Vision‑language models cap at sixty percent accuracy

Vision‑language models cap at sixty percent accuracy

Comments
2 min read
Proactive memory stops long‑horizon drift

Proactive memory stops long‑horizon drift

Comments
2 min read
Self-supervised skill rubrics cut LLM agent failures

Self-supervised skill rubrics cut LLM agent failures

Comments
2 min read
Training your own LLM usually means building a specialist

Training your own LLM usually means building a specialist

Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.