Tag
InternVLA-A1.5 integrates pretrained vision-language models with future prediction in latent space to enable efficient robot manipulation with compositional generalization and long-horizon execution, achieving state-of-the-art results on simulation benchmarks.
This paper introduces DiHAL, a diffusion-transformer hybrid that uses geometry-based proxies to select a layer in a pretrained language model for hidden-state replacement with a diffusion bridge, improving continuous diffusion language modeling by avoiding direct token recovery.