StableV2V: AI video editing that maintains object shapes across framesalonzoleeeooo.github.io·3 pts·taikon·0
SAM2Long: Sam 2 for Long Video Segmentation with a Training-Free Memory Treegithub.com·1 pts·taikon·0
Mini-Omni2: Towards Open-Source GPT-4o with Vision, Speech, Duplex Capabilitiesgithub.com·2 pts·taikon·0
Eagle: Vision-Centric High-Resolution Multimodal LLMs with Mixture of Encodersgithub.com·1 pts·taikon·0
QA-MDT: Quality-Aware Masked Diffusion Transformer for Enhanced Music Generationgithub.com·1 pts·taikon·0