OccDirector uses a VLM-guided Spatio-Temporal MMDiT model with history anchoring to generate physically plausible 4D occupancy from language scripts, supported by the new OccInteract-85k dataset.
Advances in neural information pro- cessing systems30(2017) 2
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Aligning adversarial perturbations with the near-null singular directions of intermediate linear layers in transformer VLMs yields stronger attacks than existing feature- and output-space methods.
citing papers explorer
-
OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space
OccDirector uses a VLM-guided Spatio-Temporal MMDiT model with history anchoring to generate physically plausible 4D occupancy from language scripts, supported by the new OccInteract-85k dataset.
-
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces
Aligning adversarial perturbations with the near-null singular directions of intermediate linear layers in transformer VLMs yields stronger attacks than existing feature- and output-space methods.