Quantum machine learning (QML) has attracted growing interest for its potential to match large classical models with far fewer parameters. This derives from encoding classical data representations into a Hilbert space exponentially larger than the number of qubits. In practice, however, noise mitigation limits these mo...
S. Lee, Chaeyeon Kim, Seokshin Son et al.· Proceedings of the 35th ACM...· 0 citations
Despite the structural advantages for privacy in federated learning (FL), many gradient inversion attacks have widely appeared to endanger the privacy of participants, by exploiting the information during communications. This is still valid for the case where FL is extended to quantum FL (QFL) to utilize quantum advant...
Chaemoon Im, Soohyun Park, Joongheon Kim· IEEE Transactions on Network...· 0 citations
Self-keyed in-parameter memorization (SKIM), a closed-form method in which the model generates its own questions about each dialogue turn and writes those questions into its parameters as the keys that later retrieve the turn's content, is proposed.
Xin-Yu Piao, M. Ryu, Joongheon Kim et al.· 0 citations
The vision of sixth-generation (6G) communications aims to achieve global hyperconnectivity by integrating terrestrial, aerial, and maritime domains. Non-terrestrial networks (NTNs) are key enablers of this vision but face inherent challenges such as high mobility, long propagation delays, and limited onboard computati...
Soyi Jung, Huiyeon Jang, Seoyeong Park et al.· IEEE Communications Surveys...· 0 citations
Reinforcement learning (RL) has shown strong potential for autonomous decision-making in complex and dynamic environments. However, its direct application to military systems raises critical safety, reliability, accountability, and verification concerns. Unlike civilian domains, military applications require strict com...
Se-Ik Kim, Hyojun Ahn, Joongheon Kim· International Conference on...· 0 citations
This tutorial addresses the problem of explaining what data re-uploading adds to an amplitude-embedded model and how large the gain is and expresses sequential re-uploading and parallel re-uploading with two copies in one notation and shows that each upload raises the reachable polynomial order by two.
ProFILL, a method for transforming hoBIT, the authors' college's current rule-based advising chatbot, into a profile-aware retrieval-augmented generation (RAG) system, is presented, which outperforms diverse RAG baselines, is preferred by target users, and remains effective with open-weight models for cost-effective on...
Yoonseo Kim, S. Lee, Joongheon Kim et al.· 0 citations
Learning energy-efficient humanoid locomotion requires discovering mechanically economical gait coordination, not merely reducing actuator effort. Reinforcement learning promotes efficiency through effort-related reward penalties, which guide the step-to-step mechanics of walking only indirectly. This article proposes...
Hyeonjin Choi, Joongheon Kim, Daekyum Kim· 0 citations
Two-tiered organization provides a compact survey lens for autonomous control (AC): an upper tier supports learning, planning, and high-level (HL) mission reasoning, while a lower tier executes feedback control, safety filtering, and platform-specific constraints. This compact survey reviews hierarchical architectures...
Junseo Min, Hoyeong Lee, Hyojun Ahn et al.· International Conference on...· 0 citations
RobCompiler is presented, a graph-native framework that compiles a canonical mechanism graph into a shared mechanical interface that assembles feasible configurations through rank-checked continuation and correction and demonstrates task performance and model reuse under native contact.
Mehdi Heydari Shahna, Joongheon Kim, J. Mattila· 3 citations
Results indicate that the proposed framework offers a conservative and computationally deployable offline learning approach for safety-critical underwater autonomous systems, while the present validation is confined to a custom simulation environment, so that operational deployment remains contingent on the hardware-in...
Hyojun Ahn, Hoyeong Lee, Boseon Kang et al.· IEEE Access· 1 citation
Frozen language models (LMs) are increasingly used as fixed feature extractors for downstream reranking, scoring, and preference modeling, raising a practical question: how should a compact module represent interactions among features in a fixed low-dimensional bottleneck? Common linear and low-rank adapters remain lin...
E. Roh, Hyojun Ahn, Hoyeong Lee et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
