World Models

18:43 |

Download MP3

Related Videos

27:48

Were RNNs All We Needed? (Paper Explained)

53:02

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)

1:11:58

Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)

57:00

xLSTM: Extended Long Short-Term Memory

1:03:56

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)

49:45

Scalable MatMul-free Language Modeling (Paper Explained)

29:22

[ML News] OpenAI is in hot waters (GPT-4o, Ilya Leaving, Scarlett Johansson legal action)

57:14

Yannic Kilcher Interview (Part 1)

27:07

Attention Is All You Need

29:56

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained)

59:38

JEPA - A Path Towards Autonomous Machine Intelligence (Paper Explained)

56:16

Flow Matching for Generative Modeling (Paper Explained)

48:07

OpenAI CLIP: ConnectingText and Images (Paper Explained)

40:40

Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Paper Explained)

29:47

Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained)

33:26

ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)

39:13

DINO: Emerging Properties in Self-Supervised Vision Transformers (Facebook AI Research Explained)

37:17

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

34:30

Big Bird: Transformers for Longer Sequences (Paper Explained)

15:12

No, Anthropic's Claude 3 is NOT sentient