Source author record

Xin Shen

Xin Shen appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Computation and Language cond-mat.mtrl-sci math.NT Artificial Intelligence Computer Vision eess.IV Graphics math.RT physics.comp-ph quant-ph

Catalog footprint

What is connected

8works

10topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task.

preprint2022arXiv

Information fusion approach for biomass estimation in a plateau mountainous forest using a synergistic system comprising UAS-based digital camera and LiDAR

Forest land plays a vital role in global climate, ecosystems, farming and human living environments. Therefore, forest biomass estimation methods are necessary to monitor changes in the forest structure and function, which are key data in natural resources research. Although accurate forest biomass measurements are important in forest inventory and assessments, high-density measurements that involve airborne light detection and ranging (LiDAR) at a low flight height in large mountainous areas are highly expensive. The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve using a system that synergistically combines an unmanned aircraft system (UAS)-based digital aerial camera and LiDAR to leverage their complementary advantages. In this study, we utilized digital aerial photogrammetry (DAP), which has the unique advantages of speed, high spatial resolution, and low cost, to compensate for the deficiency of forestry inventory using UAS-based LiDAR that requires terrain-following flight for high-resolution data acquisition. Combined with the sparse LiDAR points acquired by using a high-altitude and high-speed UAS for terrain extraction, dense normalized DAP point clouds can be obtained to produce an accurate and high-resolution canopy height model (CHM). Based on the CHM and spectral attributes obtained from multispectral images, we estimated and mapped the AGB of the region of interest with considerable cost efficiency. Our study supports the development of predictive models for large-scale wall-to-wall AGB mapping by leveraging the complementarity between DAP and LiDAR measurements. This work also reveals the potential of utilizing a UAS-based digital camera and LiDAR synergistically in a plateau mountainous forest area.

preprint2022arXiv

Scalable production of single 2D van der Waals layers through atomic layer deposition: Bilayer silica on metal foils and films

The self-limiting nature of atomic layer deposition (ALD) makes it an appealing option for growing single layers of two-dimensional van der Waals (2D-VDW) materials. In this paper it is demonstrated that a single layer of a 2D-VDW form of SiO2 can be grown by ALD on Au and Pd polycrystalline foils and epitaxial films. The silica was deposited by two cycles of bis (diethylamino) silane and oxygen plasma exposure at 525 K. Initial deposition produced a three-dimensionally disordered silica layer; however, subsequent annealing above 950 K drove a structural rearrangement resulting in 2D-VDW; this annealing could be performed at ambient pressure. Surface spectra recorded after annealing indicated that the two ALD cycles yielded close to the silica coverage obtained for 2D-VDW silica prepared by precision SiO deposition in ultra-high vacuum. Analysis of ALD-grown 2D-VDW silica on a Pd(111) film revealed the co-existence of amorphous and incommensurate crystalline 2D phases. In contrast, ALD growth on Au(111) films produced predominantly the amorphous phase while SiO deposition in UHV led to only the crystalline phase, suggesting that the choice of Si source can enable phase control.

preprint2021arXiv

Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for multi-turn dialogue generation. However, existing methods cannot differentiate both useful words and utterances in long distances from a response. Besides, previous work just performs context selection based on a state in the decoder, which lacks a global guidance and could lead some focuses on irrelevant or unnecessary information. In this paper, we propose a novel model with hierarchical self-attention mechanism and distant supervision to not only detect relevant words and utterances in short and long distances, but also discern related information globally when decoding. Experimental results on two public datasets of both automatic and human evaluations show that our model significantly outperforms other baselines in terms of fluency, coherence, and informativeness.

preprint2019arXiv

Landau-Zener-Stückelberg Interferometry in $\mathcal{PT}$-symmetric Non-Hermitian models

We systematically investigate the non-Hermitian generalisations of the Landau-Zener (LZ) transition and the Landau-Zener-Stückelberg (LZS) interferometry. The LZ transition probabilities, or band populations, are calculated for a generic non-Hermitian model and their asymptotic behaviour analysed. We then focus on non-Hermitian systems with a real adiabatic parameter and study the LZS interferometry formed out of two identical avoided level crossings. Four distinctive cases of interferometry are identified and the analytic formulae for the transition probabilities are calculated for each case. The differences and similarities between the non-Hermitian case and its Hermitian counterpart are emphasised. In particular, the geometrical phase originated from the sign change of the mass term at the two level crossings is still present in the non-Hermitian system, indicating its robustness against the non-Hermiticity. We further apply our non-Hermitian LZS theory to describing the Bloch oscillation in one-dimensional parity-time $(\mathcal{PT})$ reversal symmetric non-Hermitian Su-Schrieffer-Heeger model and propose an experimental scheme to simulate such dynamics using photonic waveguide arrays. The Landau-Zener transition, as well as the LZS interferometry, can be visualised through the beam intensity profile and the transition probabilitiess measured by the centre of mass of the profile.

preprint2015arXiv

A Multi-variable Rankin-Selberg Integral for a Product of $GL_2$-twisted Spinor $L$-functions

We consider a new integral representation for $L(s_1, Π\times τ_1) L(s_2, Π\times τ_2),$ where $Π$ is a globally generic cuspidal representation of $GSp_4,$ and $τ_1$ and $τ_2$ are two cuspidal representations of $GL_2$ having the same central character. As and application, we find a new period condition for two such $L$ functions to have a pole simultaneously. This points to an intriguing connection between a Fourier coefficient of a residual representation on $GSO(12)$ and a theta function on $\widetilde{Sp}(16).$ A similar integral on $GSO(18)$ fails to unfold completely, but in a way that provides further evidence of a connection.

preprint2015arXiv

First-principles studies of multiferroic and magnetoelectric materials

Multiferroics are materials where two or more ferroic orders coexist owing to the interplay between spin, charge, lattice and orbital degrees of freedom. The explosive expansion of multiferroics literature in recent years demon-strates the fast growing interest in this field. In these studies, the first-principles calculation has played a pioneer role in the experiment explanation, mechanism discovery and prediction of novel multiferroics or magnetoelectric materials. In this review, we discuss, by no means comprehensively, the extensive applications and successful achievements of first-principles approach in the study of multiferroicity, magnetoelectric effect and tunnel junc-tions. In particular, we introduce some our recently developed methods, e.g., the orbital selective external potential (OSEP) method, which prove to be powerful tools in the finding of mechanisms responsible for the intriguing phe-nomena occurred in multiferroics or magnetoelectric materials. We also summarize first-principles studies on three types of electric control of magnetism, which is the common goal of both spintronics and multiferroics. Our review offers in depth understanding on the origin of ferroelectricity in transition metal oxides, and the coexistence of fer-roelectricity and ordered magnetism, and might be helpful to explore novel multiferroic or magnetoelectric materi-als in the future.

preprint2012arXiv

The Whittaker-Shintani functions for symplectic groups

In this note, we give a formula for the Whittaker-Shintani functions for the p-adic symplectic groups, which is a generalization of the Zonal spherical functions and Whittaker functions. We then use the formula to give an alternative proof of a conjecture given by T.Shintani on the unramified calculation of L-function for $Sp_{2n}\times GL_{1}$.