5 papers
GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions
Hongbo Wang, Zihan Lin, Wenkui Yang +5
Vision-language models (VLMs) can contradict themselves across views of the same spatial relation and fail to respond when that relation changes. Addressing these failures requires…
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hongbo Wang, Huaibo Huang, Jie Cao +3
While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric c…
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
Hongbo Wang, Huaibo Huang, Pin Wang +3
Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic object…
Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning
Lianghao Luo, Xizhou Bu, Ruyan Liu +5
Robotic imitation learning typically assumes access to optimal demonstrations, yet real-world data collection often yields suboptimal, exploratory, or even failed trajectories. Dis…
Marmot: Object-Level Self-Correction via Multi-Agent Reasoning
Jiayang Sun, Hongbo Wang, Jie Cao +2
While diffusion models excel at generating high-quality images, they often struggle with accurate counting, attributes, and spatial relationships in complex multi-object scenes. On…