arXiv subjects

Luyuan Wang

Publications and source records attributed to Luyuan Wang.

5 recordsLinked to original sources

arXiv2026

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader range of general computer-use tasks beyond coding. However, existing benchmarks do not adequately evaluate general-purpose terminal computer-use agents (TUAs): general computer-use benchmarks primarily target graphical user interfaces (GUIs), whereas terminal-based benchmarks largely emphasize technical and programming-centric workflows historically native to the shell. We introduce TUA-Bench, a general-purpose benchmark for terminal-use agents. TUA-Bench includes 120 real-world tasks across five task families, covering routine digital activities-including document editing, email management, and live-web information seeking-as well as scientific and engineering workflows co-designed with PhD-level domain experts that require specialized software. This breadth distinguishes TUA-Bench from prior shell-focused or domain-specific benchmarks. Each task is manually designed, runs in a real terminal with a deterministic setup script, and is evaluated by an execution-based scoring protocol. We find that the strongest frontier agent, Claude Code with Claude Opus 4.8 max reasoning effort, achieves 65.8% overall performance, with substantial gaps across both tracks. By providing a broad and realistic evaluation of terminal-use capabilities, TUA-Bench aims to accelerate the transition from narrow, task-specific assistants to general-purpose agents capable of operating reliably across diverse digital environments.

cs.SE↗

arXiv2026

WavFlow: Audio Generation in Waveform Space

Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-quality video-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmark VGGSound (FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmark AudioCaps (FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative for multimodal audio generation.

cs.SD↗

arXiv2024

MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

Large language model (LLM)-based mobile agents are increasingly popular due to their capability to interact directly with mobile phone Graphic User Interfaces (GUIs) and their potential to autonomously manage daily tasks. Despite their promising prospects in both academic and industrial sectors, little research has focused on benchmarking the performance of existing mobile agents, due to the inexhaustible states of apps and the vague definition of feasible action sequences. To address this challenge, we propose an efficient and user-friendly benchmark, MobileAgentBench, designed to alleviate the burden of extensive manual testing. We initially define 100 tasks across 10 open-source apps, categorized by multiple levels of difficulty. Subsequently, we evaluate several existing mobile agents, including AppAgent and MobileAgent, to thoroughly and systematically compare their performance. All materials are accessible on our project webpage: https://MobileAgentBench.github.io, contributing to the advancement of both academic and industrial fields.

cs.AI↗

arXiv2024

A Fast Percolation-Dijkstra Routing Method for Mega-Constellation Backbone Network

The real-time routing for satellite communication of the mega-constellations is being challenged due to the large-scale of network nodes, especially on devices with limited computation such as onboard embedded systems. In this paper, a fast routing method is proposed for mega-constellation backbone networks. Firstly, inspired by the regularity and sparse characteristics of mega-constellations, the 4-degree percolation theory is proposed to describe the node search process. Then, dynamic minimum search and mapping methods are used to narrow down the traversal range. The proposed method performs as well as the heap-optimized Dijkstra algorithm with less memory space and dynamic access. The experimental results show that the method proposed in this paper can significantly reduce routing computation time, especially on the onboard, edge-computing or other computation-limited devices.

cs.NI↗

arXiv2023

Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning

Despite rapid advances in computer graphics, creating high-quality photo-realistic virtual portraits is prohibitively expensive. Furthermore, the well-know ''uncanny valley'' effect in rendered portraits has a significant impact on the user experience, especially when the depiction closely resembles a human likeness, where any minor artifacts can evoke feelings of eeriness and repulsiveness. In this paper, we present a novel photo-realistic portrait generation framework that can effectively mitigate the ''uncanny valley'' effect and improve the overall authenticity of rendered portraits. Our key idea is to employ transfer learning to learn an identity-consistent mapping from the latent space of rendered portraits to that of real portraits. During the inference stage, the input portrait of an avatar can be directly transferred to a realistic portrait by changing its appearance style while maintaining the facial identity. To this end, we collect a new dataset, Daz-Rendered-Faces-HQ (DRFHQ), that is specifically designed for rendering-style portraits. We leverage this dataset to fine-tune the StyleGAN2 generator, using our carefully crafted framework, which helps to preserve the geometric and color features relevant to facial identity. We evaluate our framework using portraits with diverse gender, age, and race variations. Qualitative and quantitative evaluations and ablation studies show the advantages of our method compared to state-of-the-art approaches.

cs.CV↗