arXiv subjects

Xu Hu

Publications and source records attributed to Xu Hu.

28 records · Page 2Linked to original sources

arXiv2025

Can Large Language Models Be Trusted Paper Reviewers? A Feasibility Study

Academic paper review typically requires substantial time, expertise, and human resources. Large Language Models (LLMs) present a promising method for automating the review process due to their extensive training data, broad knowledge base, and relatively low usage cost. This work explores the feasibility of using LLMs for academic paper review by proposing an automated review system. The system integrates Retrieval Augmented Generation (RAG), the AutoGen multi-agent system, and Chain-of-Thought prompting to support tasks such as format checking, standardized evaluation, comment generation, and scoring. Experiments conducted on 290 submissions from the WASA 2024 conference using GPT-4o show that LLM-based review significantly reduces review time (average 2.48 hours) and cost (average \$104.28 USD). However, the similarity between LLM-selected papers and actual accepted papers remains low (average 38.6\%), indicating issues such as hallucination, lack of independent judgment, and retrieval preferences. Therefore, it is recommended to use LLMs as assistive tools to support human reviewers, rather than to replace them.

cs.CY↗

arXiv2025

SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition

3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.

cs.CV↗

arXiv2024

A constant potential reactor framework for electrochemical reaction simulations

Understanding the evolution of electrified solid-liquid interfaces during electrochemical reactions is crucial. However, capturing the dynamic behavior of the interfaces with high temporal resolution and accuracy over long timescales remains a major challenge for both experimental and computational techniques. Here, we present a constant potential reactor framework that enables the simulation of electrochemical reactions with ab initio accuracy over extended timescales, allowing for real-time atomic scale observations for the electrified solid-liquid interface evolution. By implementing an enhanced sampling active learning protocol, we develop fast, accurate, and scalable neural network potentials that generalize across systems with varying electron counts, based on high-throughput density functional theory computations within an explicit-implicit hybrid solvent model. The simulation of reactions in realistic electrochemical environments uncovers the intrinsic mechanisms through which alkali metal cations promote CO2 adsorption and suppress the hydrogen evolution reaction. These findings align with previous experimental results and clarify previously elusive observations, offering valuable computational insights. Our framework lay the groundwork for future studies exploring the dynamic interplay between interfacial structure and reactivity in electrochemical environments.

physics.chem-ph↗

arXiv2024

Watt-level all polarization-maintaining femtosecond fiber laser source at 1100 nm for multicolor two-photon fluorescence excitation of fluorescent proteins

We demonstrate a compact watt-level all polarization-maintaining (PM) femtosecond fiber laser source at 1100 nm. The fiber laser source is seeded by an all PM fiber mode-locked laser employing a nonlinear amplifying loop mirror. The seed laser can generate stable pulses at a fundamental repetition rate of 40.71 MHz with a signal-to-noise rate of >100 dB and an integrated relative intensity noise of only ~0.061%. After two-stage external amplification and pulse compression, an output power of ~1.47 W (corresponding to a pulse energy of ~36.1 nJ) and a pulse duration of ~251 fs are obtained. The 1100 nm femtosecond fiber laser is then employed as the excitation light source for multicolor multi-photon fluorescence microscopy of Chinese hamster ovary (CHO) cells stably expressing red fluorescent proteins.

physics.optics↗

arXiv2023

Zero-shot Text-driven Physically Interpretable Face Editing

This paper proposes a novel and physically interpretable method for face editing based on arbitrary text prompts. Different from previous GAN-inversion-based face editing methods that manipulate the latent space of GANs, or diffusion-based methods that model image manipulation as a reverse diffusion process, we regard the face editing process as imposing vector flow fields on face images, representing the offset of spatial coordinates and color for each image pixel. Under the above-proposed paradigm, we represent the vector flow field in two ways: 1) explicitly represent the flow vectors with rasterized tensors, and 2) implicitly parameterize the flow vectors as continuous, smooth, and resolution-agnostic neural fields, by leveraging the recent advances of implicit neural representations. The flow vectors are iteratively optimized under the guidance of the pre-trained Contrastive Language-Image Pretraining~(CLIP) model by maximizing the correlation between the edited image and the text prompt. We also propose a learning-based one-shot face editing framework, which is fast and adaptable to any text prompt input. Our method can also be flexibly extended to real-time video face editing. Compared with state-of-the-art text-driven face editing methods, our method can generate physically interpretable face editing results with high identity consistency and image quality. Our code will be made publicly available.

cs.CV↗

arXiv2020

EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition

We present EasyASR, a distributed machine learning platform for training and serving large-scale Automatic Speech Recognition (ASR) models, as well as collecting and processing audio data at scale. Our platform is built upon the Machine Learning Platform for AI of Alibaba Cloud. Its main functionality is to support efficient learning and inference for end-to-end ASR models on distributed GPU clusters. It allows users to learn ASR models with either pre-defined or user-customized network architectures via simple user interface. On EasyASR, we have produced state-of-the-art results over several public datasets for Mandarin speech recognition.

cs.CL↗

arXiv2020

Weakly Supervised Construction of ASR Systems with Massive Video Data

Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, we consider videos as an important knowledge source, and propose an effective approach to extract high-quality audios aligned with transcripts from videos based on Optical Character Recognition (OCR). The underlying ASR model can be fine-tuned to fit any domain-specific target training datasets after weakly supervised pre-training. Extensive experiments show that our framework can easily produce state-of-the-art results on six public datasets for Mandarin speech recognition.

eess.AS↗

arXiv2020

Modeling Spontaneous Exit Choices in Intercity Expressway Traffic with Quantum Walk

In intercity expressway traffic, a driver frequently makes decisions to adjust driving behavior according to time, location and traffic conditions, which further affects when and where the driver will leave away from the expressway traffic. Spontaneous exit choices by drivers are hard to observe and thus it is a challenge to model intercity expressway traffic sufficiently. In this paper, we developed a Spontaneous Quantum Traffic Model (SQTM), which models the stochastic traffic fluctuation caused by spontaneous exit choices and the residual regularity fluctuation with Quantum Walk and Autoregressive Moving Average model (ARMA), respectively. SQTM considers the spontaneous exit choice of a driver as a quantum stochastic process with a dynamical probability function varies according to time, location and traffic conditions. A quantum walk is applied to update the probability function, which simulates when and where a driver will leave the traffic affected by spontaneous exit choices. We validate our model with hourly traffic data from 7 exits from the Nanjing-Changzhou expressway in Eastern China. For the 7 exits, the coefficients of determination of SQTM ranged from 0.5 to 0.85. Compared with classical random walk and ARMA model, the coefficients of determination were increased by 21.28% to 104.98%, and relative mean square error decreased by 11.61% to 32.92%. We conclude that SQTM provides new potential for modeling traffic dynamics with consideration of unobservable spontaneous driver's decision-making.

physics.soc-ph↗

arXiv2019

Artificial Intelligence for Prosthetics - challenge solutions

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.

cs.LG↗

arXiv2017

PS-DBSCAN: An Efficient Parallel DBSCAN Algorithm Based on Platform Of AI (PAI)

We present PS-DBSCAN, a communication efficient parallel DBSCAN algorithm that combines the disjoint-set data structure and Parameter Server framework in Platform of AI (PAI). Since data points within the same cluster may be distributed over different workers which result in several disjoint-sets, merging them incurs large communication costs. In our algorithm, we employ a fast global union approach to union the disjoint-sets to alleviate the communication burden. Experiments over the datasets of different scales demonstrate that PS-DBSCAN outperforms the PDSDBSCAN with 2-10 times speedup on communication efficiency. We have released our PS-DBSCAN in an algorithm platform called Platform of AI (PAI - https://pai.base.shuju.aliyun.com/) in Alibaba Cloud. We have also demonstrated how to use the method in PAI.

cs.DB↗