How to Blend Real Footage + AI to Direct a Winter Fox
Oxen
How to Blend Real Footage + AI to Direct a Winter Fox
54:58
100% AI Car Commercial — Behind the Scenes of the Entire Process
Oxen
100% AI Car Commercial — Behind the Scenes of the Entire Process
59:06
How a $1 Qwen3-VL Fine-Tune Beat Gemini 3
Oxen
How a $1 Qwen3-VL Fine-Tune Beat Gemini 3
54:51
Training LTX-2: How to Fine-tune a LoRA for Character Consistency
Oxen
Training LTX-2: How to Fine-tune a LoRA for Character Consistency
57:43
Fine-Tuning Wan 2.1 VACE to Swap Costumes
Oxen
Fine-Tuning Wan 2.1 VACE to Swap Costumes
52:45
Fine-Tuned Qwen-Image-Edit vs Nano-Banana: Generating 1.2 Million Images
Oxen
Fine-Tuned Qwen-Image-Edit vs Nano-Banana: Generating 1.2 Million Images
44:02
Fine-Tuning Qwen-Image-Edit-2509 on Nike Clothing and Poses
Oxen
Fine-Tuning Qwen-Image-Edit-2509 on Nike Clothing and Poses
25:02
Fine-Tuning Qwen-Image-Edit and Using Wan 2.2 to Generate Multiple Actors
Oxen
Fine-Tuning Qwen-Image-Edit and Using Wan 2.2 to Generate Multiple Actors
45:13
Training video generation with Wan 2.2: Conan O’Brien and Will Smith character consistency
Oxen
Training video generation with Wan 2.2: Conan O’Brien and Will Smith character consistency
1:01:12
Did we just fine-tune GPT-OSS 20B to rap like Eminem?
Oxen
Did we just fine-tune GPT-OSS 20B to rap like Eminem?
4:49
Fine-Tuned Qwen-Image-Edit vs Nano-Banana and FLUX.1 Kontext
Oxen
Fine-Tuned Qwen-Image-Edit vs Nano-Banana and FLUX.1 Kontext
49:17
We Fine-Tuned GPT OSS 20B to Rap Like Eminem
Oxen
We Fine-Tuned GPT OSS 20B to Rap Like Eminem
41:11
Fine-Tuning a "Tab Tab" Code Completion Model
Oxen
Fine-Tuning a "Tab Tab" Code Completion Model
45:13
How to Automate Fine Tuning with Oxen AI
Oxen
How to Automate Fine Tuning with Oxen AI
2:28
How to Fine-Tune FLUX-dev and Comparing it to a Fine-Tuned PixArt Model
Oxen
How to Fine-Tune FLUX-dev and Comparing it to a Fine-Tuned PixArt Model
58:42
Fine-tuning a Diffusion Transformer to Generate OpenAI Level Images
Oxen
Fine-tuning a Diffusion Transformer to Generate OpenAI Level Images
53:46
How we Fine-tuned Qwen3.0-6B to Beat GPT-4o on Text2SQL
Oxen
How we Fine-tuned Qwen3.0-6B to Beat GPT-4o on Text2SQL
50:56
How RWKV-7 "Goose" and It's Linear Inference Work with Author Eugene Cheah
Oxen
How RWKV-7 "Goose" and It's Linear Inference Work with Author Eugene Cheah
1:11:17
SLMs - When and When NOT to use them (+ Mistral 3.1 & Gemma-3 Bakeoff)
Oxen
SLMs - When and When NOT to use them (+ Mistral 3.1 & Gemma-3 Bakeoff)
59:32
How Phi-4 Cracked Small Multimodality
Oxen
How Phi-4 Cracked Small Multimodality
35:48
GRPO: How DeepSeek R1's Reinforcement Learning Works
Oxen
GRPO: How DeepSeek R1's Reinforcement Learning Works
35:27
How R1 and GRPO Work (Deep Technical Dive into DeepSeeks Models)
Oxen
How R1 and GRPO Work (Deep Technical Dive into DeepSeeks Models)
44:31
RAGAS: A New Framework for Evaluating RAG
Oxen
RAGAS: A New Framework for Evaluating RAG
43:13
Inside OpenCoder: The Data and Cookbook
Oxen
Inside OpenCoder: The Data and Cookbook
54:45
How Vision LLMs Reasoning: Inside LLaVa CoT
Oxen
How Vision LLMs Reasoning: Inside LLaVa CoT
37:14
Qwen 72B Vision Language Model Running in Oxen.ai
Oxen
Qwen 72B Vision Language Model Running in Oxen.ai
1:00
Model Inference in Oxen.AI
Oxen
Model Inference in Oxen.AI
0:53
Oxen.ai Demo - 11/18/2024
Oxen
Oxen.ai Demo - 11/18/2024
8:56
Upcycling LLMs into MoE with Nvidia Researcher, Ethan He
Oxen
Upcycling LLMs into MoE with Nvidia Researcher, Ethan He
59:28
How Meta's Thinking LLMs Work
Oxen
How Meta's Thinking LLMs Work
47:09
How tree-of-thought, plan-and-solve, and decomposition prompting work with Sander Schulhoff
Oxen
How tree-of-thought, plan-and-solve, and decomposition prompting work with Sander Schulhoff
54:25
Inside The Prompt Report...Part 1
Oxen
Inside The Prompt Report...Part 1
56:42
How To Fine-Tune Llama 3.1 in 11 Minutes
Oxen
How To Fine-Tune Llama 3.1 in 11 Minutes
2:39
Inside the Model that Beat DALL-E and PIXART
Oxen
Inside the Model that Beat DALL-E and PIXART
33:07
How to Use Llama 3.1 to Generate Synthetic Data
Oxen
How to Use Llama 3.1 to Generate Synthetic Data
3:31
How Llama 3.1 Works
Oxen
How Llama 3.1 Works
52:21
How Unlimiformer Works From the Author Herself- Amanda Bertsch
Oxen
How Unlimiformer Works From the Author Herself- Amanda Bertsch
43:52
Fine-Tune Llama 3 8B in Under 14 Minutes!
Oxen
Fine-Tune Llama 3 8B in Under 14 Minutes!
0:40
Will Samba unlock infinite context length?
Oxen
Will Samba unlock infinite context length?
0:41
Will ReFT replace LoRA?
Oxen
Will ReFT replace LoRA?
0:29
Sometimes the idea is right but the dataset isn't
Oxen
Sometimes the idea is right but the dataset isn't
0:59
How ReFT Works w/ Author Zhengxuan Wu
Oxen
How ReFT Works w/ Author Zhengxuan Wu
53:20
Oxen AI's Rust Meetup!
Oxen
Oxen AI's Rust Meetup!
57:42
How Samba Works
Oxen
How Samba Works
21:54
How Interpretable Features in Claude 3 Work
Oxen
How Interpretable Features in Claude 3 Work
38:24
Efficient DiT Fine-Tuning with PixART for Text to Image Generation
Oxen
Efficient DiT Fine-Tuning with PixART for Text to Image Generation
41:38
Comparing HumanEval vs. EvalPlus
Oxen
Comparing HumanEval vs. EvalPlus
45:51
How To Train an LLM With Diffusion From Scratch
Oxen
How To Train an LLM With Diffusion From Scratch
45:05
How Diffusion Works for Text
Oxen
How Diffusion Works for Text
42:24
How 1 Bit LLMs Work
Oxen
How 1 Bit LLMs Work
46:50
Sakana AI's Latest Release: Evolutionary Optimization of Model Merging Recipes
Oxen
Sakana AI's Latest Release: Evolutionary Optimization of Model Merging Recipes
40:22
Fine-Tune Mistral on Your Discord Data
Oxen
Fine-Tune Mistral on Your Discord Data
7:12
How I-JEPA Works
Oxen
How I-JEPA Works
40:20
Fine-Tune An LLM on Your Discord Data (Part 1)
Oxen
Fine-Tune An LLM on Your Discord Data (Part 1)
7:45
How to See Past Versions of Your Data
Oxen
How to See Past Versions of Your Data
0:41
See One Column Changes In Your ML/AI Data #shorts
Oxen
See One Column Changes In Your ML/AI Data #shorts
0:36
Quick and Easy Way to Find Differences in Your Data #shorts
Oxen
Quick and Easy Way to Find Differences in Your Data #shorts
0:49
Fine-Tuning a Self-Rewarding Loop into Mistral 7B
Oxen
Fine-Tuning a Self-Rewarding Loop into Mistral 7B
42:56
How to Use Diff to Specify Keys, Compares, and Added Columns
Oxen
How to Use Diff to Specify Keys, Compares, and Added Columns
12:25
Find Differences in Your Data in Under 5 Minutes
Oxen
Find Differences in Your Data in Under 5 Minutes
5:15
Road to Sora and How Diffusion Transformers Work
Oxen
Road to Sora and How Diffusion Transformers Work
39:19
How to Fine-Tune an LLM on Text2SQL Data
Oxen
How to Fine-Tune an LLM on Text2SQL Data
9:28
How Medusa Works
Oxen
How Medusa Works
52:16
How Lumiere Works
Oxen
How Lumiere Works
43:23
Depth Anything - Generating Depth Maps from a Single Image with Neural Networks
Oxen
Depth Anything - Generating Depth Maps from a Single Image with Neural Networks
36:07
Deep Dive Into The Toolformer
Oxen
Deep Dive Into The Toolformer
37:31
How To Create A New Repo From Your Terminal w/ Oxen.ai
Oxen
How To Create A New Repo From Your Terminal w/ Oxen.ai
6:08
Deep Dive Into How Self Rewarding Language Models Work
Oxen
Deep Dive Into How Self Rewarding Language Models Work
40:02
How DPO Works and Why It's Better Than RLHF
Oxen
How DPO Works and Why It's Better Than RLHF
45:21
Efficient Streaming Language Models with Attention Sinks - Arxiv Dives with Oxen.ai
Oxen
Efficient Streaming Language Models with Attention Sinks - Arxiv Dives with Oxen.ai
56:07
Deep dive into Mixture of Experts (MOE) with the Mixtral 8x7B paper
Oxen
Deep dive into Mixture of Experts (MOE) with the Mixtral 8x7B paper
28:59
Practical ML - Benchmarking RAG with variety of LLMs over 100k+ documents
Oxen
Practical ML - Benchmarking RAG with variety of LLMs over 100k+ documents
53:00
How LLaVA works 🌋 A Multimodal Open Source LLM for image recognition and chat.
Oxen
How LLaVA works 🌋 A Multimodal Open Source LLM for image recognition and chat.
46:15
Practical ML - Document Retrieval for RAG with Chroma, General Text Embeddings, and Oxen.ai
Oxen
Practical ML - Document Retrieval for RAG with Chroma, General Text Embeddings, and Oxen.ai
43:47
How Mistral 7B works - Arxiv Dives with Oxen.ai
Oxen
How Mistral 7B works - Arxiv Dives with Oxen.ai
34:23
How to Fine-Tune Mamba on Your Data
Oxen
How to Fine-Tune Mamba on Your Data
50:02
Deep dive into how Mamba works - Linear-Time Sequence Modeling with SSMs - Arxiv Dives
Oxen
Deep dive into how Mamba works - Linear-Time Sequence Modeling with SSMs - Arxiv Dives
44:23
How to train a Vision Transformer (ViT) for real time image classification - Practical ML Dives
Oxen
How to train a Vision Transformer (ViT) for real time image classification - Practical ML Dives
52:17
How CLIP enables Zero-shot image classification - Arxiv Dives with Oxen.ai
Oxen
How CLIP enables Zero-shot image classification - Arxiv Dives with Oxen.ai
37:24
Intro to Vision Transformers (ViT) - Arxiv Dives
Oxen
Intro to Vision Transformers (ViT) - Arxiv Dives
35:57
Mechanistic Interpretability of LLMs Part 2 - Arxiv Dives with Oxen.ai
Oxen
Mechanistic Interpretability of LLMs Part 2 - Arxiv Dives with Oxen.ai
45:16
Mechanistic Interpretability of LLMs Part 1 - Arxiv Dives with Oxen.ai
Oxen
Mechanistic Interpretability of LLMs Part 1 - Arxiv Dives with Oxen.ai
40:50
How to use the Oxen.ai command line tool for data version control
Oxen
How to use the Oxen.ai command line tool for data version control
11:15
Data Version Control 101 with Oxen
Oxen
Data Version Control 101 with Oxen
17:32
Attention Is All You Need - How Transformers Work - Arxiv Dives w/ Oxen.ai
Oxen
Attention Is All You Need - How Transformers Work - Arxiv Dives w/ Oxen.ai
48:05
Write an Encoder-Decoder Transformer Model in less than 5 minutes with GitHub Copilot
Oxen
Write an Encoder-Decoder Transformer Model in less than 5 minutes with GitHub Copilot
4:45
How LoRA Fine-Tuning works - 🐂 🌾 Arxiv Dives with Oxen.ai
Oxen
How LoRA Fine-Tuning works - 🐂 🌾 Arxiv Dives with Oxen.ai
42:54
Generate Speech from Text with Fast Speech 2 - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
Generate Speech from Text with Fast Speech 2 - 🐂 🌾 Arxiv Dives w/ Oxen.ai
50:28
Llama 2 Explained - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
Llama 2 Explained - 🐂 🌾 Arxiv Dives w/ Oxen.ai
53:41
How Stable Diffusion Works - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
How Stable Diffusion Works - 🐂 🌾 Arxiv Dives w/ Oxen.ai
40:52
The Segment Anything Computer Vision Model from Meta - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
The Segment Anything Computer Vision Model from Meta - 🐂 🌾 Arxiv Dives w/ Oxen.ai
41:15
GGML Segment Anything in C++ Demo
Oxen
GGML Segment Anything in C++ Demo
1:06
Retrieval Augmented Generation (RAG) - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
Retrieval Augmented Generation (RAG) - 🐂 🌾 Arxiv Dives w/ Oxen.ai
38:03
How InstructGPT works - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
How InstructGPT works - 🐂 🌾 Arxiv Dives w/ Oxen.ai
54:24
How GPT-2 was trained - 🐂 🌾 Arxiv Dives w/ Oxen.ai
Oxen
How GPT-2 was trained - 🐂 🌾 Arxiv Dives w/ Oxen.ai
41:07