Learn and Burn
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Measuring a model's understanding — starting with path-finding
[Paper: Evaluating the World Model Implicit in a Generative Model]
Nov 26
•
Unbox Research
Share this post
Learn and Burn
Measuring a model's understanding — starting with path-finding
Copy link
Facebook
Email
Notes
More
Making LLMs scalable by replacing weights with learnable tokens
[Paper: Tokenformer: Rethinking Transformer Scaling with Tokenized Model Parameters]
Nov 19
•
Unbox Research
2
Share this post
Learn and Burn
Making LLMs scalable by replacing weights with learnable tokens
Copy link
Facebook
Email
Notes
More
Image generation for infinite games
[Paper: Unbounded: A Generative Infinite Game of Character Life Simulation]
Nov 10
•
Unbox Research
1
Share this post
Learn and Burn
Image generation for infinite games
Copy link
Facebook
Email
Notes
More
Do LLMs rely on data contamination to solve math problems?
[Paper: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models]
Nov 2
•
Unbox Research
1
Share this post
Learn and Burn
Do LLMs rely on data contamination to solve math problems?
Copy link
Facebook
Email
Notes
More
1
October 2024
Running an LLM on a small customizable chip
[Paper: LlamaF: An Efficient Llama2 Architecture Accelerator on Embedded FPGAs]
Oct 30
•
Unbox Research
2
Share this post
Learn and Burn
Running an LLM on a small customizable chip
Copy link
Facebook
Email
Notes
More
Better language models with negative attention
[Paper: Differential Transformer]
Oct 18
•
Unbox Research
2
Share this post
Learn and Burn
Better language models with negative attention
Copy link
Facebook
Email
Notes
More
A serious look at the future of AI medical advice
[Paper: A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?]
Oct 12
•
Unbox Research
1
Share this post
Learn and Burn
A serious look at the future of AI medical advice
Copy link
Facebook
Email
Notes
More
LLMs have original, research-worthy ideas
[Paper: Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers]
Oct 8
•
Unbox Research
2
Share this post
Learn and Burn
LLMs have original, research-worthy ideas
Copy link
Facebook
Email
Notes
More
September 2024
OpenAI's o1 model
[Article: Learning to Reason with LLMs]
Sep 27
•
Unbox Research
1
Share this post
Learn and Burn
OpenAI's o1 model
Copy link
Facebook
Email
Notes
More
The subgoals of attention units in LLMs
[Paper: Attention Heads of Large Language Models: A Survey]
Sep 20
•
Unbox Research
1
Share this post
Learn and Burn
The subgoals of attention units in LLMs
Copy link
Facebook
Email
Notes
More
A model to parse body language
[Paper: Sapiens: Foundation Model for Human Vision Models]
Sep 16
•
Unbox Research
1
Share this post
Learn and Burn
A model to parse body language
Copy link
Facebook
Email
Notes
More
Stable diffusion can simulate video games
[Paper: Diffusion Models are Real-Time Game Engines]
Sep 6
•
Unbox Research
1
Share this post
Learn and Burn
Stable diffusion can simulate video games
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts