Learn and Burn
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Physical neural networks
[Paper: Training of Physical Neural Networks]
18 hrs ago
•
Unbox Research
1
Share this post
Physical neural networks
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Predicting depth data from a single image
[Paper: Depth Anything V2]
Jul 19
•
Unbox Research
1
Share this post
Predicting depth data from a single image
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Vision transformers can see in stereo
[Paper: Grounding Image Matching in 3D with MASt3R]
Jul 12
•
Unbox Research
1
Share this post
Vision transformers can see in stereo
learnandburn.ai
Copy link
Facebook
Email
Note
Other
How to tell if an LLM is just guessing
[Paper: Detecting hallucinations in large language models using semantic entropy]
Jul 5
•
Unbox Research
1
Share this post
How to tell if an LLM is just guessing
learnandburn.ai
Copy link
Facebook
Email
Note
Other
June 2024
A new weakness in LLMs: early vs late token importance
[Paper: Transformers need glasses! | Information over-squashing in language tasks]
Jun 28
•
Unbox Research
1
Share this post
A new weakness in LLMs: early vs late token importance
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Better LLM problem-solving without repeated prompting
[Paper: Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models]
Jun 24
•
Unbox Research
1
Share this post
Better LLM problem-solving without repeated prompting
learnandburn.ai
Copy link
Facebook
Email
Note
Other
AI can play chess well without using a search tree for future moves
[Paper: Grandmaster-Level Chess Without Search]
Jun 14
•
Unbox Research
1
Share this post
AI can play chess well without using a search tree for future moves
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Do AI models exhibit parallel evolution?
[Paper: The Platonic Representation Hypothesis]
Jun 7
•
Unbox Research
Share this post
Do AI models exhibit parallel evolution?
learnandburn.ai
Copy link
Facebook
Email
Note
Other
May 2024
Why don't large models overfit?
An exploration of the double descent phenomenon
May 31
•
Unbox Research
4
Share this post
Why don't large models overfit?
learnandburn.ai
Copy link
Facebook
Email
Note
Other
AlphaFold 3: The Turns of the Amino
[Paper: Accurate structure prediction of biomolecular interactions with AlphaFold 3]
May 24
•
Unbox Research
2
Share this post
AlphaFold 3: The Turns of the Amino
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Can we learn functions, not weights? Yes we KAN!
[Paper: KAN: Kolmogorov-Arnold Networks]
May 20
•
Unbox Research
2
Share this post
Can we learn functions, not weights? Yes we KAN!
learnandburn.ai
Copy link
Facebook
Email
Note
Other
LLMs that never forget
[Paper: Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention]
May 10
•
Unbox Research
1
Share this post
LLMs that never forget
learnandburn.ai
Copy link
Facebook
Email
Note
Other
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts