julia-turc
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
How is hardware reshaping LLM design?
|
|
1 | 0 | 3 March 2026 |
|
Why are diffusion LLMs so fast?
|
|
1 | 2 | 9 February 2026 |
|
An image is NxN words | Transformers in vision: ViT, DiT, MMDiT
|
|
1 | 0 | 3 February 2026 |
|
The relationship between convolution & self-attention
|
|
1 | 1 | 14 January 2026 |
|
Why are Transformers replacing CNNs?
|
|
1 | 5 | 1 December 2025 |
|
Inside a Real RAG Pipeline (Continua AI Case Study)
|
|
1 | 17 | 17 November 2025 |
|
David Petrou: Building social AI after 17 years at Google
|
|
0 | 1 | 8 November 2025 |
|
Transformers & Diffusion LLMs: What's the connection?
|
|
1 | 9 | 6 November 2025 |
|
Text diffusion: A new paradigm for LLMs
|
|
1 | 11 | 6 October 2025 |
|
Hierarchical Reasoning Model: Substance or Hype?
|
|
1 | 13 | 8 September 2025 |
|
The physics behind diffusion models
|
|
1 | 6 | 18 August 2025 |
|
Reverse-engineering GGUF | Post-Training Quantization
|
|
1 | 4 | 18 July 2025 |
|
Training models with only 4 bits | Fully-Quantized Training
|
|
1 | 8 | 19 June 2025 |
|
How LLMs survive in low precision | Quantization Fundamentals
|
|
1 | 3 | 19 May 2025 |