-
21:07
This question inspired LoRA fine-tuning
Канал: Julia Turc
Дата: 25.10.2026
13:22
70 years of rebranding intelligence
Канал: Julia Turc
Дата: 07.10.2026
25:38
What makes a voice expressive?
Канал: Julia Turc
Дата: 02.09.2026
33:30
Why can't ChatGPT Voice set a timer? | Voice AI expert explains
Канал: Julia Turc
Дата: 07.08.2026
21:30
How far are we from "Her"?
Канал: Julia Turc
Дата: 24.07.2026
26:37
What it takes to build *realtime* voice models | Voxtral
Канал: Julia Turc
Дата: 22.06.2026
30:39
"An endless demand for compute" | Jonathan Ross, founder of Groq
Канал: Julia Turc
Дата: 11.06.2026
28:50
But what exactly are world models?
Канал: Julia Turc
Дата: 23.05.2026
24:02
The physics behind Flow Matching models
Канал: Julia Turc
Дата: 12.04.2026
22:46
How is hardware reshaping LLM design?
Канал: Julia Turc
Дата: 03.03.2026
22:15
Why are diffusion LLMs so fast?
Канал: Julia Turc
Дата: 09.02.2026
18:14
An image is NxN words | Transformers in vision: ViT, DiT, MMDiT
Канал: Julia Turc
Дата: 03.02.2026
16:57
Why are Transformers replacing CNNs?
Канал: Julia Turc
Дата: 01.12.2025
17:54
I asked them to show me their RAG pipeline...
Канал: Julia Turc
Дата: 17.11.2025
24:55
Transformers & Diffusion LLMs: What's the connection?
Канал: Julia Turc
Дата: 06.11.2025
24:17
Text diffusion: A new paradigm for LLMs
Канал: Julia Turc
Дата: 06.10.2025
27:50
Hierarchical Reasoning Model: Substance or Hype?
Канал: Julia Turc
Дата: 08.09.2025
20:28
The physics behind diffusion models
Канал: Julia Turc
Дата: 18.08.2025
25:07
Reverse-engineering GGUF | Post-Training Quantization
Канал: Julia Turc
Дата: 14.07.2025
24:08
Training models with only 4 bits | Fully-Quantized Training
Канал: Julia Turc
Дата: 19.06.2025
24:37
The myth of 1-bit LLMs | Quantization-Aware Training
Канал: Julia Turc
Дата: 28.05.2025
20:34
How LLMs survive in low precision | Quantization Fundamentals
Канал: Julia Turc
Дата: 17.05.2025
16:04
Knowledge Distillation: How LLMs train each other
Канал: Julia Turc
Дата: 30.04.2025
26:42
Mixture of Experts: How LLMs get bigger without getting slower
Канал: Julia Turc
Дата: 23.04.2025
24:02
Llama 4 Explained: Architecture, Long Context, and Native Multimodality
Канал: Julia Turc
Дата: 09.04.2025
23:16
DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs
Канал: Julia Turc
Дата: 19.03.2025
22:03
Proximal Policy Optimization (PPO) for LLMs Explained Intuitively
Канал: Julia Turc
Дата: 07.03.2025
13:49
Tülu 3 from AI2: Full open-source fine-tuning recipe for LLMs
Канал: Julia Turc
Дата: 23.02.2025
15:53
8 Timeless tips for training LLMs | Become a better ML engineer
Канал: Julia Turc
Дата: 17.02.2025
15:29
How does DeepSeek actually work? | Full technical review
Канал: Julia Turc
Дата: 30.01.2025
09:53
Discover How LLMs Work by Dissecting Llama
Канал: Julia Turc
Дата: 28.01.2025