arXiv subjects

Junyao Ye

Publications and source records attributed to Junyao Ye.

4 recordsLinked to original sources

arXiv2026

Towards Sustainable Learning in Online Education: A Reinforcement Learning Approach

Online education offers unprecedented scalability and accessibility to global learners from diverse backgrounds, but it often suffers from low engagement and poor long term learning effectiveness. To address these challenges, we introduce AI Tutor, a reinforcement learning based model designed to promote sustainable learning by optimizing both short and longterm learning outcomes. In the short term, AI-Tutor draws on cognitive theory to guide learners through a balance of acquiring new knowledge and reinforcing prior learning. In the long term, it models learner engagement to inform strategies that sustain motivation and reduce dropout. These enhancements enable AI-Tutor to provide personalized guidance that fosters both effective learning and sustained participation. Empirical evaluations on 23 million learning records from 33,700 learners show that AI Tutor consistently outperforms state-of-the-art baselines across engagement, knowledge retention, and final learning outcomes. Learning path analyses further reveal how AI-Tutor adapts its strategies to learners with diverse profiles, offering adaptive and human-centered support.

cs.AI↗

arXiv2025

Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on injection-based attacks, which insert anomalous patterns into software code. These attacks can be neutralized by standard sanitization techniques. This status quo may lead to a false sense of security regarding backdoor attacks. In this paper, we introduce a new kind of backdoor attacks, dubbed Semantically-Equivalent Transformation (SET)-based backdoor attacks, which use semantics-preserving low-prevalence code transformations to generate stealthy triggers. We propose a framework to guide the generation of such triggers. Our experiments across five tasks, six languages, and models like CodeBERT, CodeT5, and StarCoder show that SET-based attacks achieve high success rates (often >90%) while preserving model utility. The attack proves highly stealthy, evading state-of-the-art defenses with detection rates on average over 25.13% lower than injection-based counterparts. We evaluate normalization-based countermeasures and find they offer only partial mitigation, confirming the attack's robustness. These results motivate further investigation into scalable defenses tailored to SET-based attacks.

cs.SE↗

arXiv2024

Layered Kagome Compound Na$_2$Ni$_3$S$_4$ with Topological Flat Band

We report structural and electronic properties of Na$_2$Ni$_3$S$_4$, a quasi-two-dimensional compound composed of alternating layers of [Ni$_3$S$_4$]$^{2-}$ and Na$^{+}$. The compound features a remarkable Ni-based kagome lattice with a square planar configuration of four surrounding S atoms for each Ni atom. Magnetization and electrical measurements reveal a weak paramagnetic insulator with a gap of about 0.5 eV. Our band structure calculation highlights a set of topological flat bands of the kagome lattice derived from the rotated d$_{xz}$-orbital with $C_\mathrm{3}$ + $T$ symmetry in the presence of crystal-field splitting.

cond-mat.str-el↗

arXiv2022

Triangular Kondo lattice in $\mathrm{YbV_6Sn_6}$ and its quantum critical behaviors in magnetic field

We report magnetization, heat capacity and electrical resistivity for a newly discovered heavy fermion (HF) compound $\mathrm{YbV_6Sn_6}$ which is crystallized in a hexagonal $\mathrm{HfFe_6Ge_6}$-type structure, highlighted by the stacking of triangular ytterbium sublattice and kagome vanadium sublattice. Above 2 K, $\mathrm{YbV_6Sn_6}$ shows typical HF properties due to the Kondo effect on the Kramers doublet of $\mathrm{Yb^{3+}}$ ions in crystal electric field. A remarkable magnetic ordering occurs at $T_{\mathrm{N}}$ = 0.40 K in zero field while a weak external field suppresses the ordering and induces non-Fermi liquid (NFL) behavior. In strong magnetic field the compound shows a heavy Fermi liquid state. $\mathrm{YbV_6Sn_6}$ presents as one of the few examples of Yb-based HF compounds hosting triangular Kondo lattice on which a magnetic field induces quantum criticality near zero temperature.

cond-mat.str-el↗