CityRAG: Stepping Into a City via Spatially-Grounded Video Generation Paper β’ 2604.19741 β’ Published 5 days ago β’ 16
openai/clip-vit-base-patch16 Zero-Shot Image Classification β’ Updated Oct 4, 2022 β’ 1.68M β’ 158
LLM2CLIP Collection LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. β’ 10 items β’ Updated Mar 2 β’ 67
view post Post 2440 Fun dataset added last week by @esind from Anthropic to compare persuasiveness between AI and human outputs: Anthropic/persuasion 2 replies Β· π 7 7 π 2 2 + Reply