Safety Alignment Should be Made More Than Just a Few Tokens Deep (Paper Explained)
48:53
Safety Alignment Should be Made More Than Just a Few Tokens Deep (Paper Explained)
Ай бұрын
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (Paper Explained)
28:23
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (Paper Explained)
2 ай бұрын
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
37:06
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
3 ай бұрын
Were RNNs All We Needed? (Paper Explained)
27:48
Were RNNs All We Needed? (Paper Explained)
3 ай бұрын
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)
53:02
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)
3 ай бұрын
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)
1:03:56
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)
5 ай бұрын
Scalable MatMul-free Language Modeling (Paper Explained)
49:45
Scalable MatMul-free Language Modeling (Paper Explained)
6 ай бұрын
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
1:11:58
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
6 ай бұрын
xLSTM: Extended Long Short-Term Memory
57:00
xLSTM: Extended Long Short-Term Memory
7 ай бұрын
[ML News] OpenAI is in hot waters (GPT-4o, Ilya Leaving, Scarlett Johansson legal action)
29:22
[ML News] OpenAI is in hot waters (GPT-4o, Ilya Leaving, Scarlett Johansson legal action)
8 ай бұрын
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
33:26
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
8 ай бұрын
[ML News] Chips, Robots, and Models
39:14
[ML News] Chips, Robots, and Models
8 ай бұрын
TransformerFAM: Feedback attention is working memory
37:01
TransformerFAM: Feedback attention is working memory
8 ай бұрын
[ML News] Devin exposed | NeurIPS track for high school students
17:47
[ML News] Devin exposed | NeurIPS track for high school students
8 ай бұрын
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
37:17
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
9 ай бұрын
[ML News] Llama 3 changes the game
31:19
[ML News] Llama 3 changes the game
9 ай бұрын
Hugging Face got hacked
18:01
Hugging Face got hacked
9 ай бұрын
[ML News] Microsoft to spend 100 BILLION DOLLARS on supercomputer (& more industry news)
9:55
[ML News] Microsoft to spend 100 BILLION DOLLARS on supercomputer (& more industry news)
9 ай бұрын
[ML News] Jamba, CMD-R+, and other new models (yes, I know this is like a week behind 🙃)
27:32
[ML News] Jamba, CMD-R+, and other new models (yes, I know this is like a week behind 🙃)
9 ай бұрын
Flow Matching for Generative Modeling (Paper Explained)
56:16
Flow Matching for Generative Modeling (Paper Explained)
9 ай бұрын
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping (Searchformer)
44:05
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping (Searchformer)
9 ай бұрын
[ML News] Grok-1 open-sourced | Nvidia GTC | OpenAI leaks model names | AI Act
27:00
[ML News] Grok-1 open-sourced | Nvidia GTC | OpenAI leaks model names | AI Act
9 ай бұрын
[ML News] Devin AI Software Engineer | GPT-4.5-Turbo LEAKED | US Gov't Report: Total Extinction
26:50
[ML News] Devin AI Software Engineer | GPT-4.5-Turbo LEAKED | US Gov't Report: Total Extinction
10 ай бұрын
[ML News] Elon sues OpenAI | Mistral Large | More Gemini Drama
53:15
[ML News] Elon sues OpenAI | Mistral Large | More Gemini Drama
10 ай бұрын
No, Anthropic's Claude 3 is NOT sentient
15:12
No, Anthropic's Claude 3 is NOT sentient
10 ай бұрын
[ML News] Groq, Gemma, Sora, Gemini, and Air Canada's chatbot troubles
42:34
[ML News] Groq, Gemma, Sora, Gemini, and Air Canada's chatbot troubles
10 ай бұрын
Gemini has a Diversity Problem
17:36
Gemini has a Diversity Problem
11 ай бұрын
V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video (Explained)
50:03
V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video (Explained)
11 ай бұрын
What a day in AI! (Sora, Gemini 1.5, V-JEPA, and lots of news)
1:23:59
What a day in AI! (Sora, Gemini 1.5, V-JEPA, and lots of news)
11 ай бұрын
Пікірлер