Learn and Burn

Home
Archive
About
New
Top
Discussion
An open source AI that proves theorems
Paper: LLEMMA: An Open Language Model for Mathematics
 • 
Unbox Research
1
November 2023
A leap forward for text-to-3d generation
Paper: DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
 • 
Unbox Research
An elegant equivalence between LLMs and data compression
Paper: Language Modeling is Compression
 • 
Unbox Research
Generating better images without prompt engineering
Paper: Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
 • 
Unbox Research
LLMs with fast, infinite-length conversations
Paper: Efficient Streaming Language Models with Attention Sinks
 • 
Unbox Research
October 2023
One-shot text-to-image face accuracy: Into the PhotoVerse
Paper: PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
 • 
Unbox Research
Finding weak points in AI game players
Paper: Adversarial Policies Beat Superhuman Go AIs
 • 
Unbox Research
Neural models that build cities
Paper: CityDreamer: Compositional Generative Model of Unbounded 3D Cities
 • 
Unbox Research
September 2023
"My voice is my passport:" AI speaks in your voice without training
Paper: Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
 • 
Unbox Research
Real-time scene rendering from a few photos
Paper: 3D Gaussian Splatting for Real-Time Radiance Field Rendering
 • 
Unbox Research
Pull up a chair, type your password ... I won't peek
Paper: A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards
 • 
Unbox Research
LLMs can add hidden watermarks that survive human paraphrasing
Paper: On the Reliability of Watermarks for Large Language Models
 • 
Unbox Research
© 2023 Unbox Research
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing