CityRAG: Stepping Into a City via Spatially-Grounded Video Generation Paper โข 2604.19741 โข Published 3 days ago โข 11
openai/clip-vit-base-patch16 Zero-Shot Image Classification โข Updated Oct 4, 2022 โข 1.71M โข 158
LLM2CLIP Collection LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. โข 10 items โข Updated Mar 2 โข 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 ยท ๐ 7 7 ๐ 2 2 + Reply