DeepLatent: Think with Images via Parallel Latent Visual Reasoning 事件

DeepLatent: Think with Images via Parallel Latent Visual Reasoning arXiv:2606.00562v1 Announce Type: new Abstract: The emerging paradigm of "thinking with images" embeds visual states into intermediate reasoning steps, defining a new frontier for Vision-Language Models. Existing approaches diverge along two lines. Tool-assisted methods apply explicit visual operations but suffer from high latency and restricted manipulation types. Latent reasoning methods autoregressively produce implicit visua