Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — mentioned by pico_creator

Thu, 02 Jan 2025 12:35:37 GMT

There is work done for Vision RWKV, and audio RWKV, an example paper is here: https://arxiv.org/abs/2403.02308 Its the same principle as open transformer models where an adapter is used to generate the embedding However currently the core team focus is in scaling the core text model, as this would be the key performance driver, before adapting multi-modal. The tech is there, the base model needs to be better

Paper and discussion history. A mention is not an endorsement.

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures · HackerPapers discussions

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — mentioned by pico_creator