In-Depth: 3 - Detailed Analysis

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Prabhakar Chaudhary

Oct 30

NyoomFloat12: How a 12-Bit Fixed-Length Format Doubles LLM Inference Throughput Without Losing a Single Bit

#ai #machinelearning #deeplearning #python

5 min read

Tonera

Oct 30

Qwen-Image-2.1 vs Flux3-klein: E-commerce Image Editing

#deeplearning #opensource #ai #machinelearning

3 min read

Umesh Tharuka Malaviarachchi

Oct 30

Low-Rank Adaptation: Why Freezing Most Weights Still Fine-Tunes a Large Model

#machinelearning #datascience #ai #deeplearning

8 min read

Omar Essam El Sherbiny

Oct 30

Teaching a CNN to read hieroglyphs: 96.9% on 59 signs, and why my first model failed

#machinelearning #deeplearning #python #computervision

4 min read

Umesh Tharuka Malaviarachchi

Oct 30

State Space Models: Why Linear Recurrences Rival Attention for Long Sequences

#machinelearning #datascience #ai #deeplearning

7 min read

Siddhi

Oct 30

Exploring Accelerated ML: Training a Neural Network and Understanding TPUs

#tensorflow #deeplearning #machinelearning #beginners

4 min read

Gendora

Oct 30

What AI Gender Swap Filters Reveal About the Challenges of Identity-Preserving Image Editing

#ai #deeplearning #machinelearning

5 min read

Umesh Tharuka Malaviarachchi

Oct 30

Evaluating Retrieval-Augmented Generation: Why End-to-End Accuracy Hides the Real Failures

#machinelearning #datascience #ai #deeplearning

9 min read

Umesh Tharuka Malaviarachchi

Oct 29

Neural Collapse: Why the Last Layer Converges to a Simple Geometric Structure

#machinelearning #datascience #ai #deeplearning

8 min read

Umesh Tharuka Malaviarachchi

Oct 29

Rotary Position Embeddings: How Rotating Queries and Keys Encodes Relative Position

#machinelearning #datascience #ai #deeplearning

7 min read

Umesh Tharuka Malaviarachchi

Oct 29

In-Context Learning: How a Forward Pass Learns Without Updating a Single Weight

#machinelearning #datascience #ai #deeplearning

10 min read

Prabhakar Chaudhary

Oct 29

MuonGS: Squeezing 15% More Speed Out of LLM Pretraining via Relaxed Weight-Norm Control

#ai #machinelearning #deeplearning #research

4 min read

Soham Sharma

Oct 28

PyTorch Custom Dataset and DataLoader: getitem, len, collate_fn, and num_workers

#pytorch #python #deeplearning #datascience

9 min read

Ivan Zdravkov

Oct 28

LoRA on a 16 GB card: what fits and what does not

#ai #pytorch #deeplearning #opensource

5 min read

Umesh Tharuka Malaviarachchi

Oct 28

Direct Preference Optimization: Why You Can Align a Model Without a Reward Model

#machinelearning #datascience #ai #deeplearning

8 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

Deep Learning

NyoomFloat12: How a 12-Bit Fixed-Length Format Doubles LLM Inference Throughput Without Losing a Single Bit

Qwen-Image-2.1 vs Flux3-klein: E-commerce Image Editing

Low-Rank Adaptation: Why Freezing Most Weights Still Fine-Tunes a Large Model

Teaching a CNN to read hieroglyphs: 96.9% on 59 signs, and why my first model failed

State Space Models: Why Linear Recurrences Rival Attention for Long Sequences

Exploring Accelerated ML: Training a Neural Network and Understanding TPUs

What AI Gender Swap Filters Reveal About the Challenges of Identity-Preserving Image Editing

Evaluating Retrieval-Augmented Generation: Why End-to-End Accuracy Hides the Real Failures

Neural Collapse: Why the Last Layer Converges to a Simple Geometric Structure

Rotary Position Embeddings: How Rotating Queries and Keys Encodes Relative Position

In-Context Learning: How a Forward Pass Learns Without Updating a Single Weight

MuonGS: Squeezing 15% More Speed Out of LLM Pretraining via Relaxed Weight-Norm Control

PyTorch Custom Dataset and DataLoader: getitem, len, collate_fn, and num_workers

LoRA on a 16 GB card: what fits and what does not

Direct Preference Optimization: Why You Can Align a Model Without a Reward Model