4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper β’ 2512.17012 β’ Published 8 days ago β’ 41
Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment Paper β’ 2512.04356 β’ Published 22 days ago β’ 9