Traditional Holiday Live Stream
Yannic Kilcher
Traditional Holiday Live Stream
1:28:17
Byte Latent Transformer: Patches Scale Better Than Tokens (Paper Explained)
Yannic Kilcher
Byte Latent Transformer: Patches Scale Better Than Tokens (Paper Explained)
36:15
Safety Alignment Should be Made More Than Just a Few Tokens Deep (Paper Explained)
Yannic Kilcher
Safety Alignment Should be Made More Than Just a Few Tokens Deep (Paper Explained)
48:53
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (Paper Explained)
Yannic Kilcher
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (Paper Explained)
28:23
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Yannic Kilcher
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
37:06
Were RNNs All We Needed? (Paper Explained)
Yannic Kilcher
Were RNNs All We Needed? (Paper Explained)
27:48
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)
Yannic Kilcher
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)
53:02
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)
Yannic Kilcher
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)
1:03:56
Scalable MatMul-free Language Modeling (Paper Explained)
Yannic Kilcher
Scalable MatMul-free Language Modeling (Paper Explained)
49:45
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
Yannic Kilcher
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
1:11:58
xLSTM: Extended Long Short-Term Memory
Yannic Kilcher
xLSTM: Extended Long Short-Term Memory
57:00
[ML News] OpenAI is in hot waters (GPT-4o, Ilya Leaving, Scarlett Johansson legal action)
Yannic Kilcher
[ML News] OpenAI is in hot waters (GPT-4o, Ilya Leaving, Scarlett Johansson legal action)
29:22
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
Yannic Kilcher
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
33:26
[ML News] Chips, Robots, and Models
Yannic Kilcher
[ML News] Chips, Robots, and Models
39:14
TransformerFAM: Feedback attention is working memory
Yannic Kilcher
TransformerFAM: Feedback attention is working memory
37:01
[ML News] Devin exposed | NeurIPS track for high school students
Yannic Kilcher
[ML News] Devin exposed | NeurIPS track for high school students
17:47
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Yannic Kilcher
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
37:17
[ML News] Llama 3 changes the game
Yannic Kilcher
[ML News] Llama 3 changes the game
31:19
Hugging Face got hacked
Yannic Kilcher
Hugging Face got hacked
18:01
[ML News] Microsoft to spend 100 BILLION DOLLARS on supercomputer (& more industry news)
Yannic Kilcher
[ML News] Microsoft to spend 100 BILLION DOLLARS on supercomputer (& more industry news)
9:55
[ML News] Jamba, CMD-R+, and other new models (yes, I know this is like a week behind 🙃)
Yannic Kilcher
[ML News] Jamba, CMD-R+, and other new models (yes, I know this is like a week behind 🙃)
27:32
Flow Matching for Generative Modeling (Paper Explained)
Yannic Kilcher
Flow Matching for Generative Modeling (Paper Explained)
56:16
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping (Searchformer)
Yannic Kilcher
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping (Searchformer)
44:05
[ML News] Grok-1 open-sourced | Nvidia GTC | OpenAI leaks model names | AI Act
Yannic Kilcher
[ML News] Grok-1 open-sourced | Nvidia GTC | OpenAI leaks model names | AI Act
27:00
[ML News] Devin AI Software Engineer | GPT-4.5-Turbo LEAKED | US Gov't Report: Total Extinction
Yannic Kilcher
[ML News] Devin AI Software Engineer | GPT-4.5-Turbo LEAKED | US Gov't Report: Total Extinction
26:50
[ML News] Elon sues OpenAI | Mistral Large | More Gemini Drama
Yannic Kilcher
[ML News] Elon sues OpenAI | Mistral Large | More Gemini Drama
53:15
On Claude 3
Yannic Kilcher
On Claude 3
1:00
No, Anthropic's Claude 3 is NOT sentient
Yannic Kilcher
No, Anthropic's Claude 3 is NOT sentient
15:12
[ML News] Groq, Gemma, Sora, Gemini, and Air Canada's chatbot troubles
Yannic Kilcher
[ML News] Groq, Gemma, Sora, Gemini, and Air Canada's chatbot troubles
42:34
Gemini has a Diversity Problem
Yannic Kilcher
Gemini has a Diversity Problem
17:36
V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video (Explained)
Yannic Kilcher
V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video (Explained)
50:03
What a day in AI! (Sora, Gemini 1.5, V-JEPA, and lots of news)
Yannic Kilcher
What a day in AI! (Sora, Gemini 1.5, V-JEPA, and lots of news)
1:23:59
Lumiere: A Space-Time Diffusion Model for Video Generation (Paper Explained)
Yannic Kilcher
Lumiere: A Space-Time Diffusion Model for Video Generation (Paper Explained)
54:24
AlphaGeometry: Solving olympiad geometry without human demonstrations (Paper Explained)
Yannic Kilcher
AlphaGeometry: Solving olympiad geometry without human demonstrations (Paper Explained)
35:27
Mixtral of Experts (Paper Explained)
Yannic Kilcher
Mixtral of Experts (Paper Explained)
34:32
Until the Litter End
Yannic Kilcher
Until the Litter End
3:40
LLaMA Pro: Progressive LLaMA with Block Expansion (Paper Explained)
Yannic Kilcher
LLaMA Pro: Progressive LLaMA with Block Expansion (Paper Explained)
31:45
I created an AI-powered Social Network
Yannic Kilcher
I created an AI-powered Social Network
8:17
NeurIPS 2023 Poster Session 4 (Thursday Morning)
Yannic Kilcher
NeurIPS 2023 Poster Session 4 (Thursday Morning)
57:52
Traditional X-Mas Stream
Yannic Kilcher
Traditional X-Mas Stream
2:16:00
Art @ NeurIPS 2023
Yannic Kilcher
Art @ NeurIPS 2023
8:26
Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Paper Explained)
Yannic Kilcher
Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Paper Explained)
40:40
Another Hit Piece on Open-Source AI
Yannic Kilcher
Another Hit Piece on Open-Source AI
33:22
NeurIPS 2023 Poster Session 3 (Wednesday Evening)
Yannic Kilcher
NeurIPS 2023 Poster Session 3 (Wednesday Evening)
33:53
NeurIPS 2023 Poster Session 2 (Wednesday Morning)
Yannic Kilcher
NeurIPS 2023 Poster Session 2 (Wednesday Morning)
44:17
NeurIPS 2023 Vendor Hall
Yannic Kilcher
NeurIPS 2023 Vendor Hall
8:20
NeurIPS 2023 Poster Session 1 (Tuesday Evening)
Yannic Kilcher
NeurIPS 2023 Poster Session 1 (Tuesday Evening)
19:03
NeurIPS Live Stream Vendor Hall
Yannic Kilcher
NeurIPS Live Stream Vendor Hall
16:39
Did Google fake their Gemini Video?
Yannic Kilcher
Did Google fake their Gemini Video?
15:47
Text Embeddings Reveal (Almost) As Much As Text
Yannic Kilcher
Text Embeddings Reveal (Almost) As Much As Text
37:06
Scalable Extraction of Training Data from (Production) Language Models (Paper Explained)
Yannic Kilcher
Scalable Extraction of Training Data from (Production) Language Models (Paper Explained)
47:38
Just Chatting (OpenAssistant Goodbye Stream)
Yannic Kilcher
Just Chatting (OpenAssistant Goodbye Stream)
1:04:45
What is Q-Learning (back to basics)
Yannic Kilcher
What is Q-Learning (back to basics)
45:44
Greg & Sam are BACK! (+ Q-Star is AGI) (Also Memes)
Yannic Kilcher
Greg & Sam are BACK! (+ Q-Star is AGI) (Also Memes)
18:10
Is Sam Altman coming back? (OpenAI drama continues)
Yannic Kilcher
Is Sam Altman coming back? (OpenAI drama continues)
9:59
OpenAI just fired CEO Sam Altman
Yannic Kilcher
OpenAI just fired CEO Sam Altman
20:08
I built the most expensive CPU ever! (Every instruction is a prompt)
Yannic Kilcher
I built the most expensive CPU ever! (Every instruction is a prompt)
21:51
OpenAssistant is Completed
Yannic Kilcher
OpenAssistant is Completed
11:49
Efficient Streaming Language Models with Attention Sinks (Paper Explained)
Yannic Kilcher
Efficient Streaming Language Models with Attention Sinks (Paper Explained)
32:27
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (Paper Explained)
Yannic Kilcher
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (Paper Explained)
46:45
Retentive Network: A Successor to Transformer for Large Language Models (Paper Explained)
Yannic Kilcher
Retentive Network: A Successor to Transformer for Large Language Models (Paper Explained)
28:26
Reinforced Self-Training (ReST) for Language Modeling (Paper Explained)
Yannic Kilcher
Reinforced Self-Training (ReST) for Language Modeling (Paper Explained)
53:07
[ML News] LLaMA2 Released | LLMs for Robots | Multimodality on the Rise
Yannic Kilcher
[ML News] LLaMA2 Released | LLMs for Robots | Multimodality on the Rise
44:11
How Cyber Criminals Are Using ChatGPT (w/ Sergey Shykevich)
Yannic Kilcher
How Cyber Criminals Are Using ChatGPT (w/ Sergey Shykevich)
29:10
Recipe AI suggests FATAL CHLORINE GAS Recipe
Yannic Kilcher
Recipe AI suggests FATAL CHLORINE GAS Recipe
7:07
DeepFloyd IF - Pixel-Based Text-to-Image Diffusion (w/ Authors)
Yannic Kilcher
DeepFloyd IF - Pixel-Based Text-to-Image Diffusion (w/ Authors)
53:32
[ML News] GPT-4 solves MIT Exam with 100% ACCURACY | OpenLLaMA 13B released
Yannic Kilcher
[ML News] GPT-4 solves MIT Exam with 100% ACCURACY | OpenLLaMA 13B released
31:05
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust (Explained)
Yannic Kilcher
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust (Explained)
35:45
RWKV: Reinventing RNNs for the Transformer Era (Paper Explained)
Yannic Kilcher
RWKV: Reinventing RNNs for the Transformer Era (Paper Explained)
1:02:17
Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Full Paper Review)
Yannic Kilcher
Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Full Paper Review)
29:29
OpenAI suggests AI licenses (US Senate hearing on AI regulation w/ Sam Altman)
Yannic Kilcher
OpenAI suggests AI licenses (US Senate hearing on AI regulation w/ Sam Altman)
16:13
[ML News] Geoff Hinton leaves Google | Google has NO MOAT | OpenAI down half a billion
Yannic Kilcher
[ML News] Geoff Hinton leaves Google | Google has NO MOAT | OpenAI down half a billion
39:07
Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)
Yannic Kilcher
Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)
24:34
OpenAssistant RELEASED! The world's best open-source Chat AI!
Yannic Kilcher
OpenAssistant RELEASED! The world's best open-source Chat AI!
21:06
AI Alignment Livestream (aka OpenAssistant "Just Chatting")
Yannic Kilcher
AI Alignment Livestream (aka OpenAssistant "Just Chatting")
54:42
OpenAssistant First Models are here! (Open-Source ChatGPT)
Yannic Kilcher
OpenAssistant First Models are here! (Open-Source ChatGPT)
16:53
The biggest week in AI (GPT-4, Office Copilot, Google PaLM, Anthropic Claude & more)
Yannic Kilcher
The biggest week in AI (GPT-4, Office Copilot, Google PaLM, Anthropic Claude & more)
41:02
GPT-4 is here! What we know so far (Full Analysis)
Yannic Kilcher
GPT-4 is here! What we know so far (Full Analysis)
34:10
This ChatGPT Skill will earn you $10B (also, AI reads your mind!) | ML News
Yannic Kilcher
This ChatGPT Skill will earn you $10B (also, AI reads your mind!) | ML News
43:28
LLaMA: Open and Efficient Foundation Language Models (Paper Explained)
Yannic Kilcher
LLaMA: Open and Efficient Foundation Language Models (Paper Explained)
41:07
Open Assistant Inference Backend Development (Hands-On Coding)
Yannic Kilcher
Open Assistant Inference Backend Development (Hands-On Coding)
1:21:24
OpenAssistant - ChatGPT's Open Alternative (We need your help!)
Yannic Kilcher
OpenAssistant - ChatGPT's Open Alternative (We need your help!)
35:48
Open Assistant Live Coding (Open-Source ChatGPT Replication)
Yannic Kilcher
Open Assistant Live Coding (Open-Source ChatGPT Replication)
2:27:19
AI Essay Competition (lab42)
Yannic Kilcher
AI Essay Competition (lab42)
0:58
Open Assistant Live Coding (Open-Source ChatGPT Replication)
Yannic Kilcher
Open Assistant Live Coding (Open-Source ChatGPT Replication)
2:05:47
ChatGPT: This AI has a JAILBREAK?! (Unbelievable AI Progress)
Yannic Kilcher
ChatGPT: This AI has a JAILBREAK?! (Unbelievable AI Progress)
31:55
[ML News] GPT-4 Rumors | AI Mind Reading | Neuron Interaction Solved | AI Theorem Proving
Yannic Kilcher
[ML News] GPT-4 Rumors | AI Mind Reading | Neuron Interaction Solved | AI Theorem Proving
41:56
CICERO: An AI agent that negotiates, persuades, and cooperates with people
Yannic Kilcher
CICERO: An AI agent that negotiates, persuades, and cooperates with people
1:01:03
Galactica: A Large Language Model for Science (Drama & Paper Review)
Yannic Kilcher
Galactica: A Large Language Model for Science (Drama & Paper Review)
51:33
[ML News] Multiplayer Stable Diffusion | OpenAI needs more funding | Text-to-Video models incoming
Yannic Kilcher
[ML News] Multiplayer Stable Diffusion | OpenAI needs more funding | Text-to-Video models incoming
22:53
The New AI Model Licenses have a Legal Loophole (OpenRAIL-M of BLOOM, Stable Diffusion, etc.)
Yannic Kilcher
The New AI Model Licenses have a Legal Loophole (OpenRAIL-M of BLOOM, Stable Diffusion, etc.)
27:51
ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)
Yannic Kilcher
ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)
1:04:59
Is Stability turning into OpenAI?
Yannic Kilcher
Is Stability turning into OpenAI?
39:05
Neural Networks are Decision Trees (w/ Alexander Mattick)
Yannic Kilcher
Neural Networks are Decision Trees (w/ Alexander Mattick)
31:51
This is a game changer! (AlphaTensor by DeepMind explained)
Yannic Kilcher
This is a game changer! (AlphaTensor by DeepMind explained)
55:07
[ML News] OpenAI's Whisper | Meta Reads Brain Waves | AI Wins Art Fair, Annoys Humans
Yannic Kilcher
[ML News] OpenAI's Whisper | Meta Reads Brain Waves | AI Wins Art Fair, Annoys Humans
42:32
[ML News] Stable Diffusion Takes Over! (Open Source AI Art)
Yannic Kilcher
[ML News] Stable Diffusion Takes Over! (Open Source AI Art)
27:28
How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit
Yannic Kilcher
How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit
50:20
More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers (w/ Jacob Steinhardt)
Yannic Kilcher
More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers (w/ Jacob Steinhardt)
1:06:37
The hidden dangers of loading open-source AI models (ARBITRARY CODE EXPLOIT!)
Yannic Kilcher
The hidden dangers of loading open-source AI models (ARBITRARY CODE EXPLOIT!)
19:43