RESEARCH

→ View original post on X — @mrgreen

AI Predicts Breast Cancer Spread for Personalized Treatment

By

@mrgreen

–

02 June 2023 13h09

Scientists create ‘life-saving’ AI that predicts if cancer will spread. Doctors are now able to see more clearly whether an aggressive type of breast cancer will spread by using AI. This will then allow super personalized treatment to help to save lives. http://
independent.co.uk/news/science/b
reast-cancer-ai-lymph-nodes-b2345906.html
…

→ View original post on X — @mrgreen

AI Healthcare Breakthroughs: Cancer Detection Disease Management

By

@mrgreen

–

02 June 2023 13h09

Why is no one talking about AI in healthcare? AI is now giving doctors superpowers & saving lives. It now plays a role in: -Identifying & treating cancer
-Diagnosing & managing diseases
-Combating deadly pathogens (h/t @PotentProzac
) Here are 5 incredible AI breakthroughs:

→ View original post on X — @thom_wolf

Falcon 40B Outperforms LLaMa 65B With Half Training Compute

By

@thom_wolf

–

02 June 2023 11h40

Nobody's been talking about it but it's rather *mind-blowing* imo that the open-source Flacon 40B model is topping LLaMa 65B on leaderboards and many evals while having required not even half the compute of LLaMa to train from scratch Quick back of the envelop calculations:
–

ObjectFolder Benchmark: Multisensory Learning Neural Real Objects

By

–

02 June 2023 8h41

The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects paper page: https://
huggingface.co/papers/2306.00
956
… introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction,

GenMM: Generative Motion Matching from Example Sequences

By

–

02 June 2023 8h38

Example-based Motion Synthesis via Generative Motion Matching

paper page: https://t.co/3w0A1i8wWS

present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which… pic.twitter.com/bS0rGVCJJ1
— AK (@_akhaliq) 2 juin 2023

Example-based Motion Synthesis via Generative Motion Matching paper page: https://
huggingface.co/papers/2306.00
378
… present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which

StableRep: Learning Visual Representations from Synthetic Text-to-Image Models

By

–

02 June 2023 7h37

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners paper page: https://
huggingface.co/papers/2306.00
984
… We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural

ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation

By

–

02 June 2023 7h30

ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation paper page: https://
huggingface.co/papers/2306.00
971
… present a plug-in method, named ViCo, for fast and lightweight personalized generation. Specifically, we propose an image attention module to condition the

Inserting Any Person into Diffusion Models with Single Photo

By

–

02 June 2023 7h24

Inserting Anybody in Diffusion Models via Celeb Basis paper page: https://
huggingface.co/papers/2306.00
926
… propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just one facial photograph and only 1024

Wuerstchen: Efficient Text-to-Image Model Pretraining Technique

By

–

02 June 2023 7h19

Wuerstchen: Efficient Pretraining of Text-to-Image Models paper page: https://
huggingface.co/papers/2306.00
637
… introduce Wuerstchen, a novel technique for text-to-image synthesis that unites competitive performance with unprecedented cost-effectiveness and ease of training on constrained