We call this Concept Association Bias (CAB). We’ve found that models trained using contrastive loss (e.g. parts of BLIP and BLIP-2) also have CAB. However, models trained with autoregressive loss (e.g. OFA and BLIP-2-FlanT5) don't exhibit this bias. 4/5
GENERATIVE AI
-
CLIP Training: Maximizing Image-Text Embedding Similarity
By
–
This is because CLIP is trained using contrastive loss, where the goal is to maximize the similarity between the embeddings of images and text.
2/5 -
CLIP’s Strategy for Handling Unmentioned Visual Concepts in Images
By
–
Thus, when an image includes two concepts (e.g. a lemon and an eggplant) while the text prompt only mentions one concept (e.g. lemon), CLIP attempts to account for the unmentioned concept (like the eggplant) by saying 'purple', a color commonly associated with eggplants.
3/5 -
Google Autodraw: AI-Powered Drawing Tool for Creative Expression
By
–
Possibly Autodraw from Google?
-
Warning: Do Not Confuse Demo and Reality for Gemini
By
–
As a reminder: believing that the Gemini video is reality and that it will really be like that is like believing that the images from the GTA VI trailer are real gameplay. Don't be fooled. (It's like believing 5 years ago that we could do that with our Google
-
Chain of Code: LLM-Augmented Reasoning and Code Emulation
By
–
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator Li et al.: https://
arxiv.org/abs/2312.04474 #ArtificialIntelligence #ChatGPT #LLM -
AI-Generated Games Create Unique Personalized Experiences
By
–
Makes a lot of sense. I can see that for sure. Interesting because those games will likely create a slightly different experience for every single player.
-
AI-Generated Digital Art Minted as NFT on Ethereum
By
–
Crypto AI Art #557 MINTED: Today EDITION 1/1 Collection: "Becoming" Historical Significance: A digital AI artwork with a unique NFT. Asset : https://
opensea.io/assets/ethereu
m/0x4f652d9ac6095756574b2254246f121b1042f278/278
… #MontrealAI #NFT #NFTs #NFTCommunity
