arXiv subjects

Fei Gao

Publications and source records attributed to Fei Gao.

At least 217 records · Page 12Linked to original sources

arXiv2024

PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry

Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering. However, the application of LLMs in specialized domains like biopharmaceuticals and chemistry remains largely unexplored. These fields are characterized by intricate terminologies, specialized knowledge, and a high demand for precision areas where general purpose LLMs often fall short. In this study, we introduce PharmaGPT, a suite of domain specilized LLMs with 13 billion and 70 billion parameters, specifically trained on a comprehensive corpus tailored to the Bio-Pharmaceutical and Chemical domains. Our evaluation shows that PharmaGPT surpasses existing general models on specific-domain benchmarks such as NAPLEX, demonstrating its exceptional capability in domain-specific tasks. Remarkably, this performance is achieved with a model that has only a fraction, sometimes just one-tenth-of the parameters of general-purpose large models. This advancement establishes a new benchmark for LLMs in the bio-pharmaceutical and chemical fields, addressing the existing gap in specialized language modeling. It also suggests a promising path for enhanced research and development, paving the way for more precise and effective NLP applications in these areas.

cs.CL↗

arXiv2024

The spin alignment of vector mesons with light front quarks

The global spin alignment of the vector meson has been observed in relativistic heavy ion collisions, but is still on hot debates in the theoretical community. Here we propose to apply the light front framework to explain this phenomenon since the light front form explicitly describes the hadron spin including both the quark spin and the orbital angular momentum. After applying the light front spinor, we find that the spin alignment in the polarization of vector mesons with $ρ_{00}>1/3$ can be naturally manifested and in particular, the obtained spin alignment for $ϕ$ meson is in good agreement with the experimental data. This implies that to explain the spin alignment it is important to properly include the contribution from the gluon interactions that are presented in terms of the orbital angular momentum of the hadron bound state.

hep-ph↗

arXiv2024

Active-Controlled Trial Design for HIV Prevention Trials with a Counterfactual Placebo

In the quest for enhanced HIV prevention methods, the advent of antiretroviral drugs as pre-exposure prophylaxis (PrEP) has marked a significant stride forward. However, the ethical challenges in conducting placebo-controlled trials for new PrEP agents against a backdrop of highly effective existing PrEP options necessitates innovative approaches. This manuscript delves into the design and implementation of active-controlled trials that incorporate a counterfactual placebo estimate - a theoretical estimate of what HIV incidence would have been without effective prevention. We introduce a novel statistical framework for regulatory approval of new PrEP agents, predicated on the assumption of an available and consistent counterfactual placebo estimate. Our approach aims to assess the absolute efficacy (i.e., against placebo) of the new PrEP agent relative to the absolute efficacy of the active control. We propose a two-step procedure for hypothesis testing and further develop an approach that addresses potential biases inherent in non-randomized comparison to counterfactual placebos. By exploring different scenarios with moderately and highly effective active controls and counterfactual placebo estimates from various sources, we demonstrate how our design can significantly reduce sample sizes compared to traditional non-inferiority trials and offer a robust framework for evaluating new PrEP agents. This work contributes to the methodological repertoire for HIV prevention trials and underscores the importance of adaptability in the face of ethical and practical challenges.

stat.ME↗

arXiv2024

Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation

Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods.

cs.CV↗

arXiv2024

UniQuad: A Unified and Versatile Quadrotor Platform Series for UAV Research and Application

As quadrotors take on an increasingly diverse range of roles, researchers often need to develop new hardware platforms tailored for specific tasks, introducing significant engineering overhead. In this article, we introduce the UniQuad series, a unified and versatile quadrotor platform series that offers high flexibility to adapt to a wide range of common tasks, excellent customizability for advanced demands, and easy maintenance in case of crashes. This project is fully open-source at https://hkust-aerial-robotics.github.io/UniQuad.

cs.RO↗

arXiv2024

Limited-View Photoacoustic Imaging Reconstruction Via High-quality Self-supervised Neural Representation

In practical applications within the human body, it is often challenging to fully encompass the target tissue or organ, necessitating the use of limited-view arrays, which can lead to the loss of crucial information. Addressing the reconstruction of photoacoustic sensor signals in limited-view detection spaces has become a focal point of current research. In this study, we introduce a self-supervised network termed HIgh-quality Self-supervised neural representation (HIS), which tackles the inverse problem of photoacoustic imaging to reconstruct high-quality photoacoustic images from sensor data acquired under limited viewpoints. We regard the desired reconstructed photoacoustic image as an implicit continuous function in 2D image space, viewing the pixels of the image as sparse discrete samples. The HIS's objective is to learn the continuous function from limited observations by utilizing a fully connected neural network combined with Fourier feature position encoding. By simply minimizing the error between the network's predicted sensor data and the actual sensor data, HIS is trained to represent the observed continuous model. The results indicate that the proposed HIS model offers superior image reconstruction quality compared to three commonly used methods for photoacoustic image reconstruction.

cs.CV↗

arXiv2024

Preserving Relative Localization of FoV-Limited Drone Swarm via Active Mutual Observation

Relative state estimation is crucial for vision-based swarms to estimate and compensate for the unavoidable drift of visual odometry. For autonomous drones equipped with the most compact sensor setting -- a stereo camera that provides a limited field of view (FoV), the demand for mutual observation for relative state estimation conflicts with the demand for environment observation. To balance the two demands for FoV limited swarms by acquiring mutual observations with a safety guarantee, this paper proposes an active localization correction system, which plans camera orientations via a yaw planner during the flight. The yaw planner manages the contradiction by calculating suitable timing and yaw angle commands based on the evaluation of localization uncertainty estimated by the Kalman Filter. Simulation validates the scalability of our algorithm. In real-world experiments, we reduce positioning drift by up to 65% and managed to maintain a given formation in both indoor and outdoor GPS-denied flight, from which the accuracy, efficiency, and robustness of the proposed system are verified.

cs.RO↗

arXiv2024

Edge Accelerated Robot Navigation With Collaborative Motion Planning

Low-cost distributed robots suffer from limited onboard computing power, resulting in excessive computation time when navigating in cluttered environments. This paper presents Edge Accelerated Robot Navigation (EARN), to achieve real-time collision avoidance by adopting collaborative motion planning (CMP). As such, each robot can dynamically switch between a conservative motion planner executed locally to guarantee safety (e.g., path-following) and an aggressive motion planner executed non-locally to guarantee efficiency (e.g., overtaking). In contrast to existing motion planning approaches that ignore the interdependency between low-level motion planning and high-level resource allocation, EARN adopts model predictive switching (MPS) that maximizes the expected switching gain with respect to robot states and actions under computation and communication resource constraints. The MPS problem is solved by a tightly-coupled decision making and motion planning framework based on bilevel mixed-integer nonlinear programming and penalty dual decomposition. We validate the performance of EARN in indoor simulation, outdoor simulation, and real-world environments. Experiments show that EARN achieves significantly smaller navigation time and higher success rates than state-of-the-art navigation approaches.

cs.RO↗

arXiv2024

Sparse-view Signal-domain Photoacoustic Tomography Reconstruction Method Based on Neural Representation

Photoacoustic tomography is a hybrid biomedical technology, which combines the advantages of acoustic and optical imaging. However, for the conventional image reconstruction method, the image quality is affected obviously by artifacts under the condition of sparse sampling. in this paper, a novel model-based sparse reconstruction method via implicit neural representation was proposed for improving the image quality reconstructed from sparse data. Specially, the initial acoustic pressure distribution was modeled as a continuous function of spatial coordinates, and parameterized by a multi-layer perceptron. The weights of multi-layer perceptron were determined by training the network in self-supervised manner. And the total variation regularization term was used to offer the prior knowledge. We compared our result with some ablation studies, and the results show that out method outperforms existing methods on simulation and experimental data. Under the sparse sampling condition, our method can suppress the artifacts and avoid the ill-posed problem effectively, which reconstruct images with higher signal-to-noise ratio and contrast-to-noise ratio than traditional methods. The high-quality results for sparse data make the proposed method hold the potential for further decreasing the hardware cost of photoacoustic tomography system.

eess.IV↗

arXiv2024

Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distribution

Deep learning models are widely recognized for their effectiveness in identifying medical image findings in disease classification. However, their limitations become apparent in the dynamic and ever-changing clinical environment, characterized by the continuous influx of newly annotated medical data from diverse sources. In this context, the need for continual learning becomes particularly paramount, not only to adapt to evolving medical scenarios but also to ensure the privacy of healthcare data. In our research, we emphasize the utilization of a network comprising expert classifiers, where a new expert classifier is added each time a new task is introduced. We present CTP, a task-id predictor that utilizes confidence scores, leveraging the probability distribution (logits) of the classifier to accurately determine the task-id at inference time. Logits are adjusted to ensure that classifiers yield a high-entropy distribution for data associated with tasks other than their own. By defining a noise region in the distribution and computing confidence scores, CTP achieves superior performance when compared to other relevant continual learning methods. Additionally, the performance of CTP can be further improved by providing it with a continuum of data at the time of inference.

cs.LG↗

arXiv2024

Scalable Distance-based Multi-Agent Relative State Estimation via Block Multiconvex Optimization

This paper explores the distance-based relative state estimation problem in large-scale systems, which is hard to solve effectively due to its high-dimensionality and non-convexity. In this paper, we alleviate this inherent hardness to simultaneously achieve scalability and robustness of inference on this problem. Our idea is launched from a universal geometric formulation, called \emph{generalized graph realization}, for the distance-based relative state estimation problem. Based on this formulation, we introduce two collaborative optimization models, one of which is convex and thus globally solvable, and the other enables fast searching on non-convex landscapes to refine the solution offered by the convex one. Importantly, both models enjoy \emph{multiconvex} and \emph{decomposable} structures, allowing efficient and safe solutions using \emph{block coordinate descent} that enjoys scalability and a distributed nature. The proposed algorithms collaborate to demonstrate superior or comparable solution precision to the current centralized convex relaxation-based methods, which are known for their high optimality. Distinctly, the proposed methods demonstrate scalability beyond the reach of previous convex relaxation-based methods. We also demonstrate that the combination of the two proposed algorithms achieves a more robust pipeline than deploying the local search method alone in a continuous-time scenario.

cs.RO↗

arXiv2024

Microsaccade-inspired Event Camera for Robotics

Neuromorphic vision sensors or event cameras have made the visual perception of extremely low reaction time possible, opening new avenues for high-dynamic robotics applications. These event cameras' output is dependent on both motion and texture. However, the event camera fails to capture object edges that are parallel to the camera motion. This is a problem intrinsic to the sensor and therefore challenging to solve algorithmically. Human vision deals with perceptual fading using the active mechanism of small involuntary eye movements, the most prominent ones called microsaccades. By moving the eyes constantly and slightly during fixation, microsaccades can substantially maintain texture stability and persistence. Inspired by microsaccades, we designed an event-based perception system capable of simultaneously maintaining low reaction time and stable texture. In this design, a rotating wedge prism was mounted in front of the aperture of an event camera to redirect light and trigger events. The geometrical optics of the rotating wedge prism allows for algorithmic compensation of the additional rotational motion, resulting in a stable texture appearance and high informational output independent of external motion. The hardware device and software solution are integrated into a system, which we call Artificial MIcrosaccade-enhanced EVent camera (AMI-EV). Benchmark comparisons validate the superior data quality of AMI-EV recordings in scenarios where both standard cameras and event cameras fail to deliver. Various real-world experiments demonstrate the potential of the system to facilitate robotics perception both for low-level and high-level vision tasks.

cs.RO↗

arXiv2024

Skater: A Novel Bi-modal Bi-copter Robot for Adaptive Locomotion in Air and Diverse Terrain

In this letter, we present a novel bi-modal bi-copter robot called Skater, which is adaptable to air and various ground surfaces. Skater consists of a bi-copter moving along its longitudinal direction with two passive wheels on both sides. Using a longitudinally arranged bi-copter as the unified actuation system for both aerial and ground modes, this robot not only keeps a concise and lightweight mechanism but also possesses exceptional terrain traversing capability and strong steering capacity. Moreover, leveraging the vectored thrust characteristic of bi-copters, the Skater can actively generate the centripetal force needed for steering, enabling it to achieve stable movement even on slippery surfaces. Furthermore, we model the comprehensive dynamics of the Skater, analyze its differential flatness, and introduce a controller using nonlinear model predictive control for trajectory tracking. The outstanding performance of the system is verified by extensive real-world experiments and benchmark comparisons.

cs.RO↗

arXiv2024

GS-Planner: A Gaussian-Splatting-based Planning Framework for Active High-Fidelity Reconstruction

Active reconstruction technique enables robots to autonomously collect scene data for full coverage, relieving users from tedious and time-consuming data capturing process. However, designed based on unsuitable scene representations, existing methods show unrealistic reconstruction results or the inability of online quality evaluation. Due to the recent advancements in explicit radiance field technology, online active high-fidelity reconstruction has become achievable. In this paper, we propose GS-Planner, a planning framework for active high-fidelity reconstruction using 3D Gaussian Splatting. With improvement on 3DGS to recognize unobserved regions, we evaluate the reconstruction quality and completeness of 3DGS map online to guide the robot. Then we design a sampling-based active reconstruction strategy to explore the unobserved areas and improve the reconstruction geometric and textural quality. To establish a complete robot active reconstruction system, we choose quadrotor as the robotic platform for its high agility. Then we devise a safety constraint with 3DGS to generate executable trajectories for quadrotor navigation in the 3DGS map. To validate the effectiveness of our method, we conduct extensive experiments and ablation studies in highly realistic simulation scenes.

cs.RO↗

arXiv2024

The effective potential of composite operator in the first order region of QCD phase transition

We propose a method to determine the effective potential of QCD from the gap equation, by introducing the homotopy method between the solutions of the equation of motion. Via this method, the effective potential beyond the bare vertex approximation is obtained, which then generalizes the Cornwall, Jackiw and Tomboulis (CJT) effective potential for the bilocal composite operators. Moreover, the extended effective potential is set to be a function of self energy instead of the propagator, which is the key point for the potential to be bounded from below. We then investigate the extended effective potential in the cases of phase transition of the QCD vacuum with a small current quark mass, and the first-order phase transition of QCD at finite temperature and high baryon chemical potential. In the former case, the effective potential shows as an inflection point at the critical mass where the multiple solutions of the Dyson-Schwinger equation (DSE) vanishes, which is consistent with that obtained by solving the DSE directly. For the latter case, the in-medium properties, such as the latent heat and the difference of trace anomaly, of QCD is obtained.

hep-ph↗

arXiv2024

A first-order deconfinement phase transition in the early universe and gravitational waves

We clarify the conditions of the cosmic quantum chromodynamics (QCD) first-order phase transition in the early universe by carefully distinguishing the chiral and deconfinement phase transitions. While the chiral one with light quarks at zero chemical potential is unlikely to be first order based on the recent lattice QCD calculations, the latter one can be naturally extended with one extra rolling scalar to be first order. The argument is also valid for the dark QCD theory with arbitrary $N_c$ with a wide range of phase transition temperatures, which can be from hundreds of MeV up to beyond TeV. Notably, here we derive the general formula for the deconfinement phase transition potential of SU($N_c$) gauge theory characterized by the Polyakov loop. With the effective potential in hand, the gravitational wave spectrum is then determined via the sound shell model, which then enables us to give for the first time the quantitative analysis of the gravitational wave signals coming from the QCD deconfinement phase transition and awaits the check from future space interferometers.

hep-ph↗

arXiv2024

Implicit Swept Volume SDF: Enabling Continuous Collision-Free Trajectory Generation for Arbitrary Shapes

In the field of trajectory generation for objects, ensuring continuous collision-free motion remains a huge challenge, especially for non-convex geometries and complex environments. Previous methods either oversimplify object shapes, which results in a sacrifice of feasible space or rely on discrete sampling, which suffers from the "tunnel effect". To address these limitations, we propose a novel hierarchical trajectory generation pipeline, which utilizes the Swept Volume Signed Distance Field (SVSDF) to guide trajectory optimization for Continuous Collision Avoidance (CCA). Our interdisciplinary approach, blending techniques from graphics and robotics, exhibits outstanding effectiveness in solving this problem. We formulate the computation of the SVSDF as a Generalized Semi-Infinite Programming model, and we solve for the numerical solutions at query points implicitly, thereby eliminating the need for explicit reconstruction of the surface. Our algorithm has been validated in a variety of complex scenarios and applies to robots of various dynamics, including both rigid and deformable shapes. It demonstrates exceptional universality and superior CCA performance compared to typical algorithms. The code will be released at https://github.com/ZJU-FAST-Lab/Implicit-SVSDF-Planner for the benefit of the community.

cs.RO↗

arXiv2024

Quantum Federated Learning for Distributed Quantum Networks

Federated learning is a framework that can learn from distributed networks. It attempts to build a global model based on virtual fusion data without sharing the actual data. Nevertheless, the traditional federated learning process encounters two main challenges: high computational cost and message transmission security. To address these challenges, we propose a quantum federated learning for distributed quantum networks by utilizing interesting characteristics of quantum mechanics. First, we give two methods to extract the data information to the quantum state. It can cope with different acquisition frequencies of data information. Next, a quantum gradient descent algorithm is provided to help clients in the distributed quantum networks to train local models. In other words, the algorithm gives the clients a mechanism to estimate the gradient of the local model in parallel. Compared with the classical counterpart, the proposed algorithm achieves exponential acceleration in dataset scale and quadratic speedup in data dimensionality. And, a quantum secure multi-party computation protocol is designed, which utilizes the Chinese residual theorem. It could avoid errors and overflow problems that may occur in the process of large number operation. Security analysis shows that this quantum protocol can resist common external and internal attacks. Finally, to demonstrate the effectiveness of the proposed framework, we use it to the train federated linear regression model and execute essential computation steps on the Qiskit quantum computing framework.

quant-ph↗