arXiv subjects

Yanhan Liu

Publications and source records attributed to Yanhan Liu.

3 recordsLinked to original sources

arXiv2026

Graphing Inline: Understanding Word-scale Graphics Use in Scientific Papers

Graphics (e.g., figures and charts) are ubiquitous in scientific papers, yet separating graphics from text increases cognitive load in understanding text-graphic connections. Research has found that word-scale graphics, or visual embellishments at typographic size, can augment original text, making it more expressive and easier to understand. However, whether, if so, how scientific papers adopt word-scale graphics for scholarly communication remains unclear. To address this gap, we conducted a corpus study reviewing 909 word-scale graphics extracted from 126,797 scientific papers. Through analysis, we propose a framework that characterizes where (positioning), why (communicative function), and how (visual representation) authors apply word-scale graphics in scientific papers. Our findings reveal that word-scale graphics are rarely used, that icons dominate visual representation, and that visual representation connects with communicative function (e.g., using quantitative graphs for data annotation). We further discuss opportunities to enhance scholarly communication with word-scale graphics through technical and administrative innovations.

cs.HC↗

arXiv2025

Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization

The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and the cloud to reduce latency and protect user privacy. However, recent advances in Data Reconstruction Attacks (DRAs) reveal that intermediate features exchanged in SI can be exploited to recover sensitive input data, posing significant privacy risks. Existing DRAs are typically effective only on shallow models and fail to fully leverage semantic priors, limiting their reconstruction quality and generalizability across datasets and model architectures. In this paper, we propose a novel GAN-based DRA framework with Progressive Feature Optimization (PFO), which decomposes the generator into hierarchical blocks and incrementally refines intermediate representations to enhance the semantic fidelity of reconstructed images. To stabilize the optimization and improve image realism, we introduce an L1-ball constraint during reconstruction. Extensive experiments show that our method outperforms prior attacks by a large margin, especially in high-resolution scenarios, out-of-distribution settings, and against deeper and more complex DNNs.

cs.CV↗

arXiv2017

Legendrian Satellites and Decomposable Concordances

We investigate the ramifications of the Legendrian satellite construction on the relation of Lagrangian cobordism between Legendrian knots. Under a simple hypothesis, we construct a Lagrangian concordance between two Legendrian satellites by stacking up a sequence of elementary cobordisms. This construction narrows the search for "non-decomposable" Lagrangian cobordisms and yields new families of decomposable Lagrangian slice knots. Finally, we show that the maximum Thurston-Bennequin number of a smoothly slice knot provides an obstruction to any Legendrian satellite of that knot being Lagrangian slice.

math.SG↗