arXiv subjects

Hao Liang

Publications and source records attributed to Hao Liang.

At least 145 records · Page 8Linked to original sources

arXiv2024

Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising

Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising. Moreover, deep learning methods employ complex spectral learning mechanisms, thus introducing large computation costs. To address these problems, we propose a hybrid spatial-spectral denoising network (HSSD), in which we design a novel hybrid dual-path network inspired by CNN and Transformer characteristics, leading to capturing both local and non-local spatial details while suppressing noise efficiently. Furthermore, to reduce computational complexity, we adopt a simple but effective decoupling strategy that disentangles the learning of space and spectral channels, where multilayer perception with few parameters is utilized to learn the global correlations among spectra. The synthetic and real experiments demonstrate that our proposed method outperforms state-of-the-art methods on spatial and spectral reconstruction. The code and details are available on https://github.com/HLImg/HSSD.

eess.IV↗

arXiv2024

Are Bigger Encoders Always Better in Vision Large Models?

In recent years, multimodal large language models (MLLMs) have shown strong potential in real-world applications. They are developing rapidly due to their remarkable ability to comprehend multimodal information and their inherent powerful cognitive and reasoning capabilities. Among MLLMs, vision language models (VLM) stand out for their ability to understand vision information. However, the scaling trend of VLMs under the current mainstream paradigm has not been extensively studied. Whether we can achieve better performance by training even larger models is still unclear. To address this issue, we conducted experiments on the pretraining stage of MLLMs. We conduct our experiment using different encoder sizes and large language model (LLM) sizes. Our findings indicate that merely increasing the size of encoders does not necessarily enhance the performance of VLMs. Moreover, we analyzed the effects of LLM backbone parameter size and data quality on the pretraining outcomes. Additionally, we explored the differences in scaling laws between LLMs and VLMs.

cs.CV↗

arXiv2024

On the Equivalence of Demagnetization Tensors as Discrete Cell Size Approaches Zero in Three-Dimensional Space

The calculation of the demagnetization field is crucial in various disciplines, including magnetic resonance imaging (MRI) and micromagnetics. A standard method involves discretizing the spatial domain into finite difference cells and using demagnetization tensors to compute the field. Different demagnetization tensors can result in contributions from adjacent cells that do not approach zero, nor do their differences, even as the cell size decreases. This work demonstrates that in three-dimensional space, a specific set of magnetization tensors produces the same total demagnetization field as the Cauchy principal value when the cell size approaches zero. Additionally, we provide a lower bound for the convergence speed, validated through numerical experiments.

physics.app-ph↗

arXiv2024

A Survey of Multimodal Large Language Model from A Data-centric Perspective

Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments. Data plays a pivotal role in the development and refinement of these models. In this survey, we comprehensively review the literature on MLLMs from a data-centric perspective. Specifically, we explore methods for preparing multimodal data during the pretraining and adaptation phases of MLLMs. Additionally, we analyze the evaluation methods for the datasets and review the benchmarks for evaluating MLLMs. Our survey also outlines potential future research directions. This work aims to provide researchers with a detailed understanding of the data-driven aspects of MLLMs, fostering further exploration and innovation in this field.

cs.AI↗

arXiv2024

Homomorphisms to 3-manifold groups

We prove foundational results about the set of homomorphisms from a finitely generated group to the collection of all fundamental groups of compact 3-manifolds and answer questions of Reid-Wang-Zhou and Agol-Liu.

math.GT↗

arXiv2024

Enhancing Quantum Circuit Noise Robustness from a Geometric Perspective

Quantum errors in noisy environments remain a major obstacle to advancing quantum information technology. In this work, we expand a recently developed geometric framework, originally utilized for analyzing noise accumulation and creating dynamical error-correcting gates at the control pulse level, to now study noise dynamics at the quantum circuit level. Through a geometric perspective, we demonstrate how circuit noise robustness can be enhanced using twirling techniques. Additionally, we show that circuits modified by random twirling correspond to random walk trajectories in this geometric framework, and provide a fresh perspective on randomized compiling by analytically deriving the perturbative expression for the resultant Pauli noise channel. We also illustrate that combining robustness optimization strategies at both the control pulse and circuit levels can significantly boost overall circuit fidelity even further through numerical examples. This research illuminates pathways to achieving noise-resistant quantum control beyond mere optimization of control pulses.

quant-ph↗

arXiv2024

Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data

In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capability has become a crucial prerequisite. Consequently, managing and understanding large-scale video datasets has gained increasing importance. However, empathetic data are typically trained without any quality selection, leading to inefficient data usage and wasted computational resources. Additionally, using raw data can result in low performance in empathetic dialogues. In this work, we present Efficient-Empathy, a sensibility and rationality score-based data selection algorithm that automatically selects sensibility and rationality data while discarding low-quality data. With only the sensibility data (59% of the full dataset), our trained sensibility model efficiently achieves state-of-the-art (SoTA) performance. Furthermore, with multiple data selection hyperparameters, the sensibility model demonstrates SoTA performance, showcasing the robustness of our method. By integrating sensibility and rationality data with a MoE structure, we achieve even higher performance, demonstrating the effectiveness of our Efficient-Empathy algorithm.

cs.CL↗

arXiv2024

A Positivstellensatz on the Matrix Algebra of Finitely Generated Free Group

Positivstellens{ä}tze are a group of theorems on the positivity of involution algebras over $\mathbb{R}$ or $\mathbb{C}$. One of the most well-known Positivstellensatz is the solution to Hilbert's 17th problem given by E. Artin, which asserts that a real polynomial in $n$ commutative variables is nonnegative on real affine space if and only if it is a sum of fractional squares. Let $m$ and $n$ be two positive integers. For the free group $F_n$ generated by $n$ letters, and a symmetric polynomial $b$ with variables in $F_n$ and with $n$-by-$n$ complex matrices coefficients, we use real algebraic geometry to give a new proof showing that $b$ is a sum of Hermitian squares if and only if $b$ is mapped to a positive semidefinite matrix under any finitely dimensional unitary representation of $F_n$.

math.RT↗

arXiv2024

Jet-Origin Identification and Its Application at an Electron-Positron Higgs Factory

To enhance the scientific discovery power of high-energy collider experiments, we propose and realize the concept of jet origin identification that categorizes jets into 5 quark species $(b,c,s,u,d)$, 5 anti-quarks $(\bar{b},\bar{c},\bar{s},\bar{u},\bar{d})$, and the gluon. Using state-of-the-art algorithms and simulated $ν\barνH, H\rightarrow jj$ events at 240 GeV center-of-mass energy at the electron-positron Higgs factory, the jet origin identification simultaneously reaches jet flavor tagging efficiencies ranging from 67% to 92% for bottom, charm, and strange quarks, and jet charge flip rates of 7% to 24% for all quark species. We apply the jet origin identification to Higgs rare and exotic decay measurements at the nominal luminosity of the Circular Electron Positron Collider (CEPC), and conclude that the upper limits on the branching ratios of $H\rightarrow s \bar{s}, u\bar{u}, d\bar{d}$, and $H\rightarrow sb, db, uc, ds$ can be determined to $2\!\!\times\!\!10^{-4}$ to $1\!\!\times\!\!10^{-3}$ at 95% confidence level. The derived upper limit for $H\rightarrow s \bar{s}$ decay is approximately three times the prediction of the Standard Model.

hep-ex↗

arXiv2024

Unlabeled Sensing Using Rank-One Moment Matrix Completion

We study the unlabeled sensing problem that aims to solve a linear system of equations $A x =π(y) $ for an unknown permutation $π$. For a generic matrix $A$ and a generic vector $y$, we construct a system of polynomial equations whose unique solution satisfies $ Aξ^*=π(y)$. In particular, $ξ^*$ can be recovered by solving the rank-one moment matrix completion problem. We propose symbolic and numeric algorithms to compute the unique solution. Some numerical experiments are conducted to show the efficiency and robustness of the proposed algorithms.

math.OC↗

arXiv2024

Ultrafast Kapitza-Dirac effect

Similar to the optical diffraction of light passing through a material grating, the Kapitza-Dirac effect occurs when an electron is diffracted by a standing light wave. In its original description the effect is time-independent. In the present work, we extend the Kapitza-Dirac concept to the time domain. By tracking the spatiotemporal evolution of a pulsed electron wave packet diffracted by a femtosecond (10 15 second) standing wave pulse in a pump-probe scheme, we observe so far unseen time-dependent diffraction patterns. The fringe spacing in the observed pattern differs from that generated by the conventional Kapitza-Dirac effect, moreover it decreases as the pump-probe delay time increases. By exploiting this time-resolved diffraction scheme, we gather access to the time evolution of the previously inaccessible phase properties of a free electron.

physics.optics↗

arXiv2024

Jet charge identification in ee-Z-qq process at Z pole operation

Accurate jet charge identification is essential for precise electroweak and flavor measurements at the high-energy frontier. We propose a novel method called the Leading Particle Jet Charge method (LPJC) to determine the jet charge based on information about the leading charged particle. Tested on Z - bb and Z - cc samples at a center-of-mass energy of 91.2GeV, the LPJC achieves an effective tagging power of 20%/9% for the c/b jet, respectively. Combined with the Weighted Jet Charge method (WJC), we develop a Heavy Flavor Jet Charge method (HFJC), which achieves an effective tagging power of 39%/20% for c/b jet, respectively. This paper also discusses the dependencies between jet charge identification performance and the fragmentation process of heavy flavor jets, and critical detector performances.

hep-ex↗

arXiv2024

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games

This work tackles the complexities of multi-player scenarios in \emph{unknown games}, where the primary challenge lies in navigating the uncertainty of the environment through bandit feedback alongside strategic decision-making. We introduce Thompson Sampling (TS)-based algorithms that exploit the information of opponents' actions and reward structures, leading to a substantial reduction in experimental budgets -- achieving over tenfold improvements compared to conventional approaches. Notably, our algorithms demonstrate that, given specific reward structures, the regret bound depends logarithmically on the total action space, significantly alleviating the curse of multi-player. Furthermore, we unveil the \emph{Optimism-then-NoRegret} (OTN) framework, a pioneering methodology that seamlessly incorporates our advancements with established algorithms, showcasing its utility in practical scenarios such as traffic routing and radar sensing in the real world.

cs.LG↗

arXiv2024

The 120Gbps VCSEL Array Based Optical Transmitter (ATx) Development for the High-Luminosity LHC (HL-LHC) Experiments

The integration of a Verticle Cavity Surface-Emitting Laser (VCSEL) array and a driving Application-Specific Integrated Circuit (ASIC) in a custom optical array transmitter module (ATx) for operation in the detector front-end is constructed, assembled and tested. The ATx provides 12 parallel channels with each channel operating at 10 Gbps. The optical transmitter eye diagram passes the eye mask and the bit-error rate (BER) less than 1E-12 transmission is achieved at 10 Gbps/ch. The overall insertion loss including the radiation induced attenuation is sufficiently low to meet the proposed link budget requirement.

physics.ins-det↗

arXiv2024

Optical Data Transmission ASICs for the High-Luminosity LHC (HL-LHC) Experiments

We present the design and test results of two optical data transmission ASICs for the High-Luminosity LHC (HL-LHC) experiments. These ASICs include a two-channel serializer (LOCs2) and a single-channel Vertical Cavity Surface Emitting Laser (VCSEL) driver (LOCld1V2). Both ASICs are fabricated in a commercial 0.25-um Silicon-on-Sapphire (SoS) CMOS technology and operate at a data rate up to 8 Gbps per channel. The power consumption of LOCs2 and LOCld1V2 are 1.25 W and 0.27 W at 8-Gbps data rate, respectively. LOCld1V2 has been verified meeting the radiation-tolerance requirements for HL-LHC experiments.

physics.ins-det↗

arXiv2024

The VCSEL-based Array Optical Transmitter (ATx) Development Towards 120-Gbps Link for Collider Detector: Development Update

A compact radiation-tolerant array optical transmitter module (ATx) is developed to provide data transmission up to 10Gbps per channel with 12 parallel channels for collider detector applications. The ATx integrates a Vertical Cavity Surface-Emitting Laser (VCSEL) array and driver circuitry for electrical to optical conversion, an edge warp substrate for the electrical interface and a micro-lens array for the optical interface. This paper reports the continuing development of the ATx custom package. A simple, high-accuracy and reliable active-alignment method for the optical coupling is introduced. The radiation-resistance of the optoelectronic components is evaluated and the inclusion of a custom-designed array driver is discussed.

physics.ins-det↗

arXiv2024

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic risk measure (EntRM) of return. By leveraging a key property of the EntRM, the independence property, we establish the risk-sensitive distributional dynamic programming framework. We then propose two novel DRL algorithms that implement optimism through two different schemes, including a model-free one and a model-based one. We prove that they both attain $\tilde{\mathcal{O}}(\frac{\exp(|β| H)-1}{|β|}H\sqrt{S^2AK})$ regret upper bound, where $S$, $A$, $K$, and $H$ represent the number of states, actions, episodes, and the time horizon, respectively. It matches RSVI2 proposed in \cite{fei2021exponential}, with novel distributional analysis. To the best of our knowledge, this is the first regret analysis that bridges DRL and RSRL in terms of sample complexity. Acknowledging the computational inefficiency associated with the model-free DRL algorithm, we propose an alternative DRL algorithm with distribution representation. This approach not only maintains the established regret bounds but also significantly amplifies computational efficiency. We also prove a tighter minimax lower bound of $Ω(\frac{\exp(βH/6)-1}{βH}H\sqrt{SAT})$ for the $β>0$ case, which recovers the tight lower bound $Ω(H\sqrt{SAT})$ in the risk-neutral setting.

cs.LG↗

arXiv2023

Linking convolutional kernel size to generalization bias in face analysis CNNs

Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network architecture have largely been ignored even though different network parameterizations are known to induce different implicit biases over learned features. For example, convolutional kernel size is known to affect the frequency content of features learned in CNNs. In this work, we present a causal framework for linking an architectural hyperparameter to out-of-distribution algorithmic bias. Our framework is experimental, in that we train several versions of a network with an intervention to a specific hyperparameter, and measure the resulting causal effect of this choice on performance bias when a particular out-of-distribution image perturbation is applied. In our experiments, we focused on measuring the causal relationship between convolutional kernel size and face analysis classification bias across different subpopulations (race/gender), with respect to high-frequency image details. We show that modifying kernel size, even in one layer of a CNN, changes the frequency content of learned features significantly across data subgroups leading to biased generalization performance even in the presence of a balanced dataset.

cs.CV↗