Embrace the journey into AI's capabilities – from generating text and enhancing images to recognizing early-stage cancer! Also, we question the notion of AI's true intelligence while distinguishing it from human cognition.
MULTIMODAL AI
-
MimicPlay: Long-Horizon Imitation Learning from Human Demonstrations
By
–
MimicPlay: Long-Horizon Imitation Learning by Watching Human Play Wang et al.: https://
arxiv.org/abs/2302.12422 #ArtificialIntelligence #DeepLearning #MachineLearning -
OpenAI Dev Day 2026: Customization, Multimodality, Collaboration, Mediums
By
–
Think BIG for OpenAI Dev Day. More customization and personalization More modalities More collaboration More mediums
-
OpenAI’s Vision: Audio, Retrieval, Safety, Education, and GPT-5
By
–
I’m imagining things like:
– audio (90% of my inputs are via voice) – retrieval, search – safety techniques – education initiatives, funding – multimodal mobile – early GPT-5 demo
– mini models / easier few shot learning – multi person collab – chip dev’t
– new frontends -
NOIR: Non-invasive EEG brain-robotic interface for robot control
By
–
Very excited by our new brain-robotic interface work @corl_conf — NOIR is a general-purpose, intelligent BRI system that enables humans to command robots, using non-invasive EEG signals. 🤩👇 https://t.co/qAwh6vDL7i
— Fei-Fei Li (@drfeifei) 4 novembre 2023Very excited by our new brain-robotic interface work @corl_conf — NOIR is a general-purpose, intelligent BRI system that enables humans to command robots, using non-invasive EEG signals.
-
Fine-tuning SDXL for Upside Down Image Generation
By
–
SDXL isn't very good at upside down images. I wanted to play on this, so I fine-tuned the model on some upside down people (but didn't caption them as upside down). It extrapolates the upside-down-edness in a fascinating way. https://
replicate.com/fofr/sdxl-upsi
de-down
… -
Halo Ring SDXL Fine-Tune Model Released for Image Generation
By
–
I had to take the bait from @SmokeAwayyy
. Here's a Halo Ring SDXL fine tune: https://
replicate.com/fofr/sdxl-halo
-ring
… Try with prompts like:
"A video game render of a TOK halo ring, low angle" -
SDXL Halo Ring: AI-Generated Video Game Renders
By
–
Have at it: https://
replicate.com/fofr/sdxl-halo
-ring
… Prompt with variations of:
"A video game render of a TOK halo ring" -
Racial Disparities in ML Medical Imaging for Dermatology
By
–
Researchers identify new forms of racial disparity in medical imaging for dermatology by analyzing ecosystems of ML models. @StanfordCRFM @RishiBommasani
-
Open Source Video Generation with AI Translation and Lip-Sync
By
–
This is a really clever combination of models to translate, generate audio and lip-sync a video.
— fofr (@fofrAI) 3 novembre 2023
It's like HeyGen, but open source. https://t.co/TiNxnEpDMnThis is a really clever combination of models to translate, generate audio and lip-sync a video. It's like HeyGen, but open source.