Author

Kangjun Liu

h-index 4 View on Semantic Scholar

We have 3 of 23 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

ControlRadio: Prompt-Driven Controllable Diffusion for Cross-Modal Radio Map Generation

ControlRadio is presented, a controllable generative framework that produces radio maps from natural-language descriptions and environmental layouts, including building structures and transmitter locations, while reducing computation time by more than four orders of magnitude compared with conventional simulation-based...

Kang-Jun Liu, Xiying Pan, Shu-Hang Zhang et al. · 0 citations

Open access 2026

Revisiting Adversarial Robustness in Large-Scale 3-D Vision–Language Models

Focusing on zero-shot classification, this study demonstrates that 3D vision-language models exhibit heightened sensitivity to small coordinate perturbations, highlighting the need for a more rigorous security evaluation of 3D vision-language models.

Xuanxiang Lin, Yan Huang, Longkun Zou et al. · IEEE Access · 0 citations

Preprint Aug 2026

Local Margin Restoration for Test-Time Adaptation of Vision-Language Models

Local Margin Restoration (LMR) is proposed, a lightweight, one-step TTA framework that consistently outperforms state-of-the-art TTA baselines, proving exceptionally robust and efficient even in challenging low-batch test-time regimes.

Yan Huang, Guowei Wang, Xu Wang et al. · 0 citations