Institution profile

Shandong Normal University

Academic institutionasia · cn
Official website
Research library73linked papers
Opportunities0open roles
Selected work

Representative Papers

Inferring 1-Minimal Trigger Configurations for Assessing Linux Kernel CVE Triggerability

Aug 15, 2026

This study addresses the lack of CVE trigger assessment and configuration redundancy in Linux kernels by proposing FCC, a framework that automatically infers 1-minimal trigger configurations satisfying both build-time and runtime constraints. Integrating Kconfig constraint solving, implicit dependency completion, and topology-guided minimization, FCC is the first to generate auditable trigger boundaries validated via olddefconfig. Experimental results demonstrate that the configuration success rate increases from 62.5% to 96.6%, while the average candidate size is reduced by 78.7%. These improvements significantly lower evaluation overhead and effectively enable vendors to precisely determine CVE triggerability within specific deployments.

0 citationsRead paper

Deliberate Before You Fly: Vision-Guided Spatial Deliberation for UAV See-and-Reach Navigation

Aug 05, 2026

This work addresses the challenges of semantic-control misalignment, action inconsistency, and unreliable termination in language-guided drone navigation within target-visible environments. To this end, the authors propose DBFly, a novel framework that introduces an explicit vision-guided spatial reasoning chain prior to waypoint generation. This chain comprises target-direction anchoring, spatial diagnosis, and maneuver decision-making, complemented by implicit flight corridor modeling and a terminal convergence-aware stopping strategy to reliably bridge high-level linguistic intent with continuous low-level control. Experimental results demonstrate that DBFly achieves a 25.07 percentage point improvement in average success rate over the strongest baseline across both seen and unseen objects and scenes, significantly enhancing navigation stability and reliability.

0 citationsRead paper

Hierarchical Flow Matching for 3D Point Cloud Generation

Aug 05, 2026

Existing 3D point cloud generation methods struggle to simultaneously capture global topology and fine local details, often relying on computationally expensive ODE solvers or multi-step denoising procedures. This work proposes a Hierarchical Flow Matching (HFM) framework that extends flow matching into a two-level structure: it first models the global shape manifold via implicit flow matching in a compact latent space, then performs conditional point flow matching—conditioned on the learned latent code—to reconstruct detailed geometry. Both stages are trained with simple MSE regression and leverage optimal transport paths with Euler integration for efficient sampling. The method achieves state-of-the-art or comparable generation quality on ShapeNet and ModelNet, producing high-fidelity point clouds with only 15 sampling steps per level, while also yielding a structured latent space amenable to downstream tasks.

0 citationsRead paper
Recent publications

Latest Papers

Inferring 1-Minimal Trigger Configurations for Assessing Linux Kernel CVE Triggerability

Aug 15, 2026

This study addresses the lack of CVE trigger assessment and configuration redundancy in Linux kernels by proposing FCC, a framework that automatically infers 1-minimal trigger configurations satisfying both build-time and runtime constraints. Integrating Kconfig constraint solving, implicit dependency completion, and topology-guided minimization, FCC is the first to generate auditable trigger boundaries validated via olddefconfig. Experimental results demonstrate that the configuration success rate increases from 62.5% to 96.6%, while the average candidate size is reduced by 78.7%. These improvements significantly lower evaluation overhead and effectively enable vendors to precisely determine CVE triggerability within specific deployments.

0 citationsRead paper

Deliberate Before You Fly: Vision-Guided Spatial Deliberation for UAV See-and-Reach Navigation

Aug 05, 2026

This work addresses the challenges of semantic-control misalignment, action inconsistency, and unreliable termination in language-guided drone navigation within target-visible environments. To this end, the authors propose DBFly, a novel framework that introduces an explicit vision-guided spatial reasoning chain prior to waypoint generation. This chain comprises target-direction anchoring, spatial diagnosis, and maneuver decision-making, complemented by implicit flight corridor modeling and a terminal convergence-aware stopping strategy to reliably bridge high-level linguistic intent with continuous low-level control. Experimental results demonstrate that DBFly achieves a 25.07 percentage point improvement in average success rate over the strongest baseline across both seen and unseen objects and scenes, significantly enhancing navigation stability and reliability.

0 citationsRead paper

Hierarchical Flow Matching for 3D Point Cloud Generation

Aug 05, 2026

Existing 3D point cloud generation methods struggle to simultaneously capture global topology and fine local details, often relying on computationally expensive ODE solvers or multi-step denoising procedures. This work proposes a Hierarchical Flow Matching (HFM) framework that extends flow matching into a two-level structure: it first models the global shape manifold via implicit flow matching in a compact latent space, then performs conditional point flow matching—conditioned on the learned latent code—to reconstruct detailed geometry. Both stages are trained with simple MSE regression and leverage optimal transport paths with Euler integration for efficient sampling. The method achieves state-of-the-art or comparable generation quality on ShapeNet and ModelNet, producing high-fidelity point clouds with only 15 sampling steps per level, while also yielding a structured latent space amenable to downstream tasks.

0 citationsRead paper