Direct Nash Optimization: Teaching language models to self-improve with general preferences

  Рет қаралды 1,962

Microsoft Research

Microsoft Research

Күн бұрын

Пікірлер: 8
Coding Was HARD Until I Learned These 5 Things...
8:34
Coding Was HARD Until I Learned These 5 Things...
Elsa Scola
Рет қаралды 865 М.
Project Aurora: The first large-scale foundation model of the atmosphere
6:36
Project Aurora: The first large-scale foundation model of the atmosphere
Microsoft Research
Рет қаралды 1,3 М.
When you have a very capricious child 😂😘👍
00:16
When you have a very capricious child 😂😘👍
Like Asiya
Рет қаралды 18 МЛН
Quilt Challenge, No Skills, Just Luck#Funnyfamily #Partygames #Funny
00:32
Quilt Challenge, No Skills, Just Luck#Funnyfamily #Partygames #Funny
Family Games Media
Рет қаралды 55 МЛН
Don’t Choose The Wrong Box 😱
00:41
Don’t Choose The Wrong Box 😱
Topper Guild
Рет қаралды 62 МЛН
We Attempted The Impossible 😱
00:54
We Attempted The Impossible 😱
Topper Guild
Рет қаралды 56 МЛН
Should You Use Open Source Large Language Models?
6:40
Should You Use Open Source Large Language Models?
IBM Technology
Рет қаралды 368 М.
7 Outside The Box Puzzles
12:16
7 Outside The Box Puzzles
MindYourDecisions
Рет қаралды 198 М.
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 308 М.
What is Prompt Tuning?
8:33
What is Prompt Tuning?
IBM Technology
Рет қаралды 230 М.
Как работает ChatGPT: объясняем нейросети просто
39:04
Как работает ChatGPT: объясняем нейросети просто
RationalAnswer | Павел Комаровский
Рет қаралды 1,4 МЛН
How I Would Learn Python FAST (if I could start over)
12:19
How I Would Learn Python FAST (if I could start over)
Thu Vu data analytics
Рет қаралды 692 М.
Stanford Computer Scientist Answers Coding Questions From Twitter | Tech Support | WIRED
17:13
Stanford Computer Scientist Answers Coding Questions From Twitter | Tech Support | WIRED
WIRED
Рет қаралды 4,1 МЛН
AI for Business Transformation: Multimodal Models
31:13
AI for Business Transformation: Multimodal Models
Microsoft Research
Рет қаралды 3,1 М.
Why Does Diffusion Work Better than Auto-Regression?
20:18
Why Does Diffusion Work Better than Auto-Regression?
Algorithmic Simplicity
Рет қаралды 422 М.
MIT 6.S191: Deep Generative Modeling
56:19
MIT 6.S191: Deep Generative Modeling
Alexander Amini
Рет қаралды 75 М.
When you have a very capricious child 😂😘👍
00:16
When you have a very capricious child 😂😘👍
Like Asiya
Рет қаралды 18 МЛН