Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: A classic 1961 Ferrari 250 GT California Spyder in Rosso Corsa red parked on a wet street in a modern Beijing tech district at golden hour, neon signs with Chinese characters and digital screens reflecting off the polished paint and chrome, cinematic automotive photography with warm highlights and soft shadows, elegant composition with shallow depth of field
ByteDance just released Sa2VA on Hugging Face. This MLLM marries SAM2 with LLaVA for dense grounded understanding of images & videos, offering SOTA performance in segmentation, grounding, and QA. https://x.com/HuggingPapers/status/1978745567258829153
