Learn and Burn

Home
Archive
About
A model to parse body language
[Paper: Sapiens: Foundation Model for Human Vision Models]
 • 
Unbox Research
Stable diffusion can simulate video games
[Paper: Diffusion Models are Real-Time Game Engines]
 • 
Unbox Research

August 2024

How to build a lensless camera
[Paper: DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model]
 • 
Unbox Research
LLMs are great geo-aware predictors
[Paper: GeoLLM: Extracting Geospatial Knowledge from Large Language Models]
 • 
Unbox Research
Spherical-graph based weather prediction
[Article: GraphCast: AI model for faster and more accurate global weather forecasting]
 • 
Unbox Research
AI is solving international-level math competition problems
[Article: AI achieves silver-medal standard solving International Mathematical Olympiad problems]
 • 
Unbox Research
How to use LLMs with spreadsheets
[Paper: SPREADSHEETLLM: Encoding Spreadsheets for Large Language Models
 • 
Unbox Research

July 2024

Physical neural networks
[Paper: Training of Physical Neural Networks]
 • 
Unbox Research
Predicting depth data from a single image
[Paper: Depth Anything V2]
 • 
Unbox Research
Vision transformers can see in stereo
[Paper: Grounding Image Matching in 3D with MASt3R]
 • 
Unbox Research
How to tell if an LLM is just guessing
[Paper: Detecting hallucinations in large language models using semantic entropy]
 • 
Unbox Research

June 2024

A new weakness in LLMs: early vs late token importance
[Paper: Transformers need glasses! | Information over-squashing in language tasks]
 • 
Unbox Research
© 2024 Unbox Research
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture