Will Merrill: The Illusion of State in State-Space Models

  Рет қаралды 1,880

Formal Languages and Neural Networks Seminar

Formal Languages and Neural Networks Seminar

Күн бұрын

Talk given by Will Merrill to the Formal Languages and Neural Networks discord on April 1st 2024. Thank you, Will!
Their paper will be available on ArXiv soon and will be updated here once online!

Пікірлер: 4
@stephengibert4722
@stephengibert4722 3 ай бұрын
It is difficult to avoid being distracted by perpetual question marks.
@BuFu1O1
@BuFu1O1 10 ай бұрын
what about feedback transformers?
Yash Sarrof: The Expressive Capacity of State Space Models: A Formal Language Perspective
48:38
Yash Sarrof: The Expressive Capacity of State Space Models: A Formal Language Perspective
Formal Languages and Neural Networks Seminar
Рет қаралды 353
What if all the world's biggest problems have the same solution?
24:52
What if all the world's biggest problems have the same solution?
Veritasium
Рет қаралды 2 МЛН
притворился дедом и проверил шаурмечные на человечность ч10
01:01
притворился дедом и проверил шаурмечные на человечность ч10
ABRACADABRA TV
Рет қаралды 3,2 МЛН
If Your Hair is Super Long
00:53
If Your Hair is Super Long
im_siowei
Рет қаралды 30 МЛН
БАЙГАЙСТАН | 3 СЕРИЯ | ДУБАЙ |bayGUYS
44:17
БАЙГАЙСТАН | 3 СЕРИЯ | ДУБАЙ |bayGUYS
bayGUYS
Рет қаралды 1,8 МЛН
Squid game
00:17
Squid game
Giuseppe Barbuto
Рет қаралды 37 МЛН
Mulla Sadra’s Theory of Substantial Motion (harakat jawhariya) Explained
12:18
Mulla Sadra’s Theory of Substantial Motion (harakat jawhariya) Explained
Rumi's Echoes & Other Philosophies
Рет қаралды 24
The moment we stopped understanding AI [AlexNet]
17:38
The moment we stopped understanding AI [AlexNet]
Welch Labs
Рет қаралды 1,6 МЛН
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
Grant Sanderson
Рет қаралды 441 М.
Hattie Zhou: What Algorithms can Transformers Learn? A Study in Length Generalization
53:49
Hattie Zhou: What Algorithms can Transformers Learn? A Study in Length Generalization
Formal Languages and Neural Networks Seminar
Рет қаралды 649
How Sociopaths Actually Work | Authorized Account | Insider
48:02
How Sociopaths Actually Work | Authorized Account | Insider
Insider
Рет қаралды 576 М.
Will Merrill: The Expressive Power of Transformers with Chain of Though
39:41
Will Merrill: The Expressive Power of Transformers with Chain of Though
Formal Languages and Neural Networks Seminar
Рет қаралды 283
Group theory, abstraction, and the 196,883-dimensional monster
21:58
Group theory, abstraction, and the 196,883-dimensional monster
3Blue1Brown
Рет қаралды 3,2 МЛН
Why don't movies look like *movies* anymore?
7:55
Why don't movies look like *movies* anymore?
Patrick Tomasso
Рет қаралды 960 М.
The Shape of AI to Come! Yann LeCun at AI Action Summit 2025
50:40
The Shape of AI to Come! Yann LeCun at AI Action Summit 2025
DSAI by Dr. Osbert Tay
Рет қаралды 14 М.
Insane Theoretical Physics Discussion with ChatGPT and DeepSeek
4:59
Insane Theoretical Physics Discussion with ChatGPT and DeepSeek
Unzicker's Real Physics
Рет қаралды 32 М.
притворился дедом и проверил шаурмечные на человечность ч10
01:01
притворился дедом и проверил шаурмечные на человечность ч10
ABRACADABRA TV
Рет қаралды 3,2 МЛН