arXiv subjects

Yilun Jiang

Publications and source records attributed to Yilun Jiang.

6 recordsLinked to original sources

arXiv2026

FlashFolio: A GPU-Accelerated Solver for Portfolio Optimization

We present FlashFolio, a GPU-accelerated solver for single-period and multi-period portfolio optimization with factor-based risk modeling, bid-offer spread costs, and nonlinear market impact. These models are widely used in portfolio construction and optimal execution, but become computationally challenging at large scale, especially in the multi-period setting. We benchmark FlashFolio against MOSEK on instances constructed from realistic market inputs. FlashFolio delivers consistent runtime improvements, achieving speedups of up to 12.9x in the single-period setting and 48x in the multi-period setting, while also exhibiting stronger robustness on challenging multi-period instances. Our results show that GPU-based optimization can help improve the practicality of large-scale portfolio optimization.

math.OC↗

arXiv2026

Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation

The growing ubiquity of Extended Reality (XR) is driving Conversational Recommendation Systems (CRS) toward visually immersive experiences. We formalize this paradigm as Immersive CRS (ICRS), where recommended items are highlighted directly in the user's scene-based visual environment and augmented with in-situ labels. While item recommendation has been widely studied, the problem of how to select and evaluate which information to present as immersive labels remains an open problem. To this end, we introduce a principled categorization of information needs into explicit intent satisfaction and proactive information needs and use these to define novel evaluation metrics for item label selection. We benchmark IR-, LLM-, and VLM-based methods across three datasets and ICRS scenarios: fashion, movie recommendation, and retail shopping. Our evaluation reveals three important limitations of existing methods: (1) they fail to leverage scenario-specific information modalities (e.g., visual cues for fashion, meta-data for retail), (2) they present redundant information that is visually inferable, and (3) they poorly anticipate users' proactive information needs from explicit dialogue alone. In summary, this work provides both a novel evaluation paradigm for in-situ item labeling in ICRS and highlights key challenges for future work.

cs.IR↗

arXiv2025

VOGUE: A Multimodal Dataset for Conversational Recommendation in Fashion

Multimodal conversational recommendation has recently emerged as a promising paradigm for delivering personalized experiences through natural dialogue enriched by visual and contextual grounding. Yet currently available multimodal conversational recommendation datasets remain limited: existing resources either simulate conversations, omit user history or fail to collect sufficiently detailed feedback, which constrain the types of research and evaluation they support. To address these gaps we introduce VOGUE, a dataset of 60 human human dialogues containing 2100 granularly labeled utterances in realistic fashion shopping scenarios. Each dialogue is paired with a shared visual catalogue, item metadata, user fashion profiles and post conversation ratings from both users (Seekers) and recommenders (Assistants). This design enables rigorous evaluation of conversational inference, including not only alignment between predicted and ground truth preferences but also calibration against full rating distributions and comparison with explicit and implicit user satisfaction signals. Our analyses of VOGUE reveal distinctive dynamics of visually grounded dialogue, e.g. recommenders frequently recommend items simultaneously in feature based groups, which creates distinct conversational phases bridged by Seeker critiques and refinements. Benchmarking Multimodal Large Language Models against human Recommenders shows that while MLLMs approach human level alignment in aggregate they exhibit systematic distribution errors in reproducing human ratings and struggle to generalize preference inference beyond explicitly discussed items. These findings establish VOGUE as both a unique resource for studying multimodal conversational systems and a challenge dataset beyond the current recommendation capabilities of existing top tier multimodal foundation models such as GPT-5-mini and Gemini-2.5-Flash.

cs.IR↗

arXiv2022

Electron transport in the single-layer semiconductor

Two-dimensional (2D) materials are a new class of materials with interesting physical properties and applications ranging from nanoelectronics to sensing and photonics. In addition to graphene, the most studied 2D material, monolayers of other layered materials such as semiconducting dichalcogenides MoS2 or WSe2 are gaining in importance as promising channel materials for field-effect transistors (FETs) and phototransistors. However, it is unclear that how the specific process of electron transport is affected by temperature. So, nowadays the electron dynamics of single-layer semiconductor cannot be understood fundamentally. Here, we develop an analytical theory distinguishing from traditional energy band theory, backed up by Monte-Carlo simulations, that predicts the process of electron transport and the effect of temperature on the electron transport in the single-layer semiconductor. In this paper, A new model is built to deal with electron transporting in the sing-layer semiconductor. The resistance is decided by the barrier rather than the electron scattering in the single-layer semiconductor, which is macroscopic quantum effect. Electron transport in FETs with different dielectric configurations are investigated at different temperatures and a new control factor that is decided by top-gate voltage or bottom-gate voltage is introduced to describe the effect of gate voltage on the electron transport in 2D semiconductor. The results of simulation show the drain current is mainly determined by some elements, such as temperature, top-gate voltage, bottom-gate voltage and source-drain voltage.

cond-mat.mtrl-sci↗

arXiv2022

Charge transport in monolayers of metal nanoparticles

Two-dimensional (2D) nanoparticle films are a new class of materials with interesting physical properties and applications ranging from nanoelectronics to sensing and photonics. The importance of conducting nanoparticle films makes the fundamental understanding of their charge transport extremely important for materials and process design. Various hopping and transport mechanisms have been proposed and the nanoparticle monolayer is consistent with the electrical equivalent RC circuit, but their theoretical methods are limited to the model of the single electron tunneling between capacitively coupled nanoparticles with a characteristic time constant RC and the conductivity of thin film is the experimental conductivity, which cannot be deduced from these theoretical models. It is also unclear that how the specific process of electron transpot is affected by temperature. So, nowadays the electron dynamics of thin film cannot be understood fundamentally. Here, we develop an analytical theory based on the model of Sommerfeld, backed up by Monte-Carlo simulations, that predicts the process of charge transport and the effect of temperature on the electron transport in the thin film. In this paper two different nanoparticle models were built to cope with different types of morphology: triangular array and rectangular array. The transport properties of these different kinds of arrays including 2D ordered nanoparticle arrays with/without local structural disorder and 2D gradient nanoparticle arrays were investigated at different temperatures. For 2D well-ordered nanoparticle array without local structural disorder, the I-V curves are non-linear and highly symmetric.

cond-mat.mtrl-sci↗

arXiv2019

A bank salvage model by impulse stochastic controls

The present paper is devoted to the study of a bank salvage model with finite time horizon and subjected to stochastic impulse controls. In our model, the bank's default time is a completely inaccessible random quantity generating its own filtration, then reflecting the unpredictability of the event itself. In this framework the main goal is to minimize the total cost of the central controller who can inject capital to save the bank from default. We address the latter task showing that the corresponding quasi-variational inequality (QVI) admits a unique viscosity solution, Lipschitz continuous in space and Holder continuous in time. Furthermore, under mild assumptions on the dynamics the smooth-fit $W^{(1,2),p}_{loc}$ property is achieved for any $1<p<+\infty$.

q-fin.MF↗