The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2407. 20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities.
We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
arXiv:2607. 14543v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions.
arXiv:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.
arXiv:2607. 01153v1 Announce Type: cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or misreported progress in an agentic task.
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.