Все публикации

0:27:48

Were RNNs All We Needed? (Paper Explained)

0:53:02

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

1:03:56

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

0:49:45

Scalable MatMul-free Language Modeling (Paper Explained)

1:11:58

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

0:57:00

xLSTM: Extended Long Short-Term Memory

0:29:22

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

0:33:26

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

0:39:14

[ML News] Chips, Robots, and Models

0:37:01

TransformerFAM: Feedback attention is working memory

0:17:47

[ML News] Devin exposed | NeurIPS track for high school students

0:37:17

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

0:31:19

[ML News] Llama 3 changes the game

0:18:01

Hugging Face got hacked

0:09:55

[ML News] Microsoft to spend 100 BILLION DOLLARS on supercomputer (& more industry news)

0:27:32

[ML News] Jamba, CMD-R+, and other new models (yes, I know this is like a week behind 🙃)

0:56:16

Flow Matching for Generative Modeling (Paper Explained)

0:44:05

Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping (Searchformer)

0:27:00

[ML News] Grok-1 open-sourced | Nvidia GTC | OpenAI leaks model names | AI Act

0:26:50

[ML News] Devin AI Software Engineer | GPT-4.5-Turbo LEAKED | US Gov't Report: Total Extinction

0:53:15

[ML News] Elon sues OpenAI | Mistral Large | More Gemini Drama

0:01:00

On Claude 3

0:15:12

No, Anthropic's Claude 3 is NOT sentient

0:42:34

[ML News] Groq, Gemma, Sora, Gemini, and Air Canada's chatbot troubles