arXiv:2607.14543v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots…
arXiv:2607.13162v2 Announce Type: replace-cross Abstract: What a language model will and will not do is largely set during post-training, but…
arXiv:2607.13037v1 Announce Type: new Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require…
arXiv:2607.12752v2 Announce Type: replace-cross Abstract: While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely…
arXiv:2607.13587v1 Announce Type: cross Abstract: Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for…
arXiv:2607.13579v1 Announce Type: cross Abstract: Enabling quadrupedal robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration…
arXiv:2607.11997v2 Announce Type: replace-cross Abstract: Multi-task model merging combines separately trained expert models into a single model that handles all…
