arXiv subjects

Hyunjung Yi

Publications and source records attributed to Hyunjung Yi.

3 recordsLinked to original sources

arXiv2026

Maru: Information Architecture as a Shared Language for Generating Aligned and Persistent User Interfaces

Generative user interfaces (GenUIs) promise on-demand components tailored to users' needs. As users iterate on information tasks, they construct personal structures over information they encounter---how items are grouped, what gets prioritized, and what terms mean in their context. Yet, current systems leave these structural decisions to the model at each generation, ignoring the structural logic users have established. Without a persistent representational structure shared between user and system, GenUIs have no basis to remain aligned with what users have established. We draw on Information Architecture (IA), a design practice for organizing and structuring information, as a shared language to bridge user-constructed structure and system generation. We present a framework identifying four IA elements---partition, hierarchy, order, and vocabulary---and characterize how each maps to concrete UI generation decisions. We instantiate this framework in Maru, a conversational system that captures user prompts and interactions as IA preferences, persisting as rules both user and system draw on across generations. A user study revealed that IA persistence kept generated UIs aligned as sessions progressed, while alignment without it degraded, with diverse patterns emerging across users and contexts, pointing to the value of IA persistence in aligning GenUI to individual needs.

cs.HC↗

arXiv2025

DeepAries: Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection

We propose DeepAries , a novel deep reinforcement learning framework for dynamic portfolio management that jointly optimizes the timing and allocation of rebalancing decisions. Unlike prior reinforcement learning methods that employ fixed rebalancing intervals regardless of market conditions, DeepAries adaptively selects optimal rebalancing intervals along with portfolio weights to reduce unnecessary transaction costs and maximize risk-adjusted returns. Our framework integrates a Transformer-based state encoder, which effectively captures complex long-term market dependencies, with Proximal Policy Optimization (PPO) to generate simultaneous discrete (rebalancing intervals) and continuous (asset allocations) actions. Extensive experiments on multiple real-world financial markets demonstrate that DeepAries significantly outperforms traditional fixed-frequency and full-rebalancing strategies in terms of risk-adjusted returns, transaction costs, and drawdowns. Additionally, we provide a live demo of DeepAries at https://deep-aries.github.io/, along with the source code and dataset at https://github.com/dmis-lab/DeepAries, illustrating DeepAries' capability to produce interpretable rebalancing and allocation decisions aligned with shifting market regimes. Overall, DeepAries introduces an innovative paradigm for adaptive and practical portfolio management by integrating both timing and allocation into a unified decision-making process.

q-fin.PM↗

arXiv2006

Electrical spin injection and detection in an InAs quantum well

We demonstrate fully electrical detection of spin injection in InAs quantum wells. A spin polarized current is injected from a NiFe thin film to a two-dimensional electron gas (2DEG) made of InAs based epitaxial multi-layers. Injected spins accumulate and diffuse out in the 2DEG, and the spins are electrically detected by a neighboring NiFe electrode. The observed spin diffusion length is 1.8 um at 20 K. The injected spin polarization across the NiFe/InAs interface is 1.9% at 20 K and remains at 1.4% even at room temperature. Our experimental results will contribute significantly to the realization of a practical spin field effect transistor.

cond-mat.mes-hall↗