JF
Jiyuan Fu
cs.CVcs.AIcs.CRcs.MMcs.CLcs.LGcs.RO
On Valency
published · living versionsW_ecdwuwe6·v1 · currentpublished
PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
with Junyu Lin, Mengjie Wu, Yonghao Dong, Yuchuan Fu +9
1 version
Preprints & journals
11 papers in the corpus · 2024–2026Neos: Learning to Interleave Search and Visual Reasoning2610.17043v1 · Ekko He, Jack Hong, Shilin Yan et al.2026 · 0 citationsarXiv
Slow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation2610.02324v1 · Xiaofei Yin, Tong Chu, Jiyuan Fu et al.2026 · 0 citationsarXiv
Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference2609.36967v1 · Jiayu Chen, Shuyong Gao, Jingkai Jia et al.2026 · 0 citationsarXiv
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking2605.28083v1 · Jiyuan Fu, Kaixun Jiang, Jingkai Jia et al.2026 · 0 citationsarXiv
RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations2512.24023v1 · Xingqi He, Yujie Zhang, Shuyong Gao et al.2025 · 0 citationsarXiv
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops2506.14493v3 · Jiyuan Fu, Kaixun Jiang, Lingyi Hong et al.2025 · 0 citationsarXiv
Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment2506.01511v1 · Kaixun Jiang, Zhaoyu Chen, Haijing Guo et al.2025 · 1 citationarXiv
VideoPure: Diffusion-based Adversarial Purification for Video Recognition2501.14999v1 · Kaixun Jiang, Zhaoyu Chen, Jiyuan Fu et al.2025 · 0 citationsarXiv
Boosting Adversarial Transferability with Spatial Adversarial Alignment2501.01015v2 · Zhaoyu Chen, Haijing Guo, Kaixun Jiang et al.2025 · 0 citationsarXiv
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving2407.13111v1 · Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang et al.2024 · 0 citationsarXiv
Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction2403.10883v2 · Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang et al.2024 · 0 citationsarXiv
Career total: 14 works. 11 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.