arXiv subjects

Hao Yan

Publications and source records attributed to Hao Yan.

At least 91 records · Page 5Linked to original sources

arXiv2024

IntelliExplain: Enhancing Conversational Code Generation for Non-Professional Programmers

Chat LLMs such as GPT-3.5-turbo and GPT-4 have shown promise in assisting humans in coding, particularly by enabling them to conversationally provide feedback. However, current approaches assume users have expert debugging skills, limiting accessibility for non-professional programmers. In this paper, we first explore Chat LLMs' limitations in assisting non-professional programmers with coding. Through a formative study, we identify two key elements affecting their experience: the way a Chat LLM explains its generated code and the structure of human-LLM interaction. We then propose IntelliExplain, a new conversational code generation framework with enhanced code explanations and a structured interaction paradigm, which enforces both better code understanding and a more effective feedback loop. In two programming tasks (SQL and Python), IntelliExplain yields significantly higher success rates and reduces task time compared to the vanilla Chat LLM. We also identify several opportunities that remain in effectively offering a chat-based programming experience for non-professional programmers.

cs.HC↗

arXiv2024

K-band LiNbO3 A3 Lamb-wave Resonators with Sub-wavelength Through-holes

Addressing critical challenges in Lamb wave resonators, this paper presents the first validation of resonators incorporating sub-wavelength through-holes. Using the A3 mode resonator based on a LiNbO3 single-crystal thin film and operating in the K band as a prominent example, we demonstrate the advantages of the through-hole design. In the absence of additional processing steps, and while maintaining device performance--including operating frequency, electromechanical coupling coefficient, and quality factor--without introducing extra spurious modes, this approach effectively reduces the ineffective suspension area of the piezoelectric LN film, potentially enhancing mechanical and thermal stability. It also standardizes etching distances (and times) across various Lamb wave resonators on a single wafer, facilitating the development of Lamb wave filters. The versatility of the through-hole technique, with relaxed constraints on hole geometry and arrangement, further highlights its significance. Together with the other advantages, these features underscore the transformative potential of through-holes in advancing the practical implementation of Lamb wave resonators and filters.

physics.app-ph↗

arXiv2024

Research on Autonomous Robots Navigation based on Reinforcement Learning

Reinforcement learning continuously optimizes decision-making based on real-time feedback reward signals through continuous interaction with the environment, demonstrating strong adaptive and self-learning capabilities. In recent years, it has become one of the key methods to achieve autonomous navigation of robots. In this work, an autonomous robot navigation method based on reinforcement learning is introduced. We use the Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models to optimize the path planning and decision-making process through the continuous interaction between the robot and the environment, and the reward signals with real-time feedback. By combining the Q-value function with the deep neural network, deep Q network can handle high-dimensional state space, so as to realize path planning in complex environments. Proximal policy optimization is a strategy gradient-based method, which enables robots to explore and utilize environmental information more efficiently by optimizing policy functions. These methods not only improve the robot's navigation ability in the unknown environment, but also enhance its adaptive and self-learning capabilities. Through multiple training and simulation experiments, we have verified the effectiveness and robustness of these models in various complex scenarios.

cs.RO↗

arXiv2024

A unified transition mechanism from shock to detonation waves

The transition of shock-to-detonation is of great significance for the investigation of supernova formation, disaster prevention and supersonic propulsion technology. In this paper, the influence Equation of shock-to-detonation transition is summarized for the oblique detonation problem from aerodynamic analysis. The Equation integrates the effects of parameters such as chemical reaction, shock intensity and wall conditions, which quantitatively explains the physical mechanism of shock-to-detonation transition in the form of mathematical expression. Comparison with numerical simulation results as well as their gradients verified the reliability of the influence Equation. Further, the influence Equation can also be used to predict the critical conditions for the transition from shock to detonation transition form. In addition to oblique detonation, the influence Equation is compatible with the deflagration-to-detonation problem for normal detonation, which shows a wide applicability.

physics.flu-dyn↗

arXiv2024

Advanced pure tilt actuator for testing tilt-to-length coupling in space-based gravitational wave detection

Tilt-to-length (TTL) coupling, caused by the jitter of test masses or satellites, is a significant noise source in space-based gravitational wave detection. Calibrating and suppressing TTL coupling noise at the sub-nanometer level is essential. One main challenge in current ground-based TTL coupling testing is the residual translational movement of the tilt actuator. This paper introduces the development of an advanced pure tilt actuator (APTA) specifically designed for testing TTL coupling. The APTA provides precise tilt motion and is monitored by a four-beam interferometer, which measures the displacement of attached array pyramids. We present a detailed theoretical model and experimental setup. Experimental results demonstrate that this optical test bed, equipped with the APTA, can achieve subnanometer-level TTL coupling calibration. In addition, a typical heterodyne interferometer was tested using the APTA test bed. Comparative testing demonstrated that the imaging system is capable of effectively suppressing TTL coupling errors. The TTL coupling coefficients were reduced from over plus-minus 30 micrometers per radian to within plus-minus 5 micrometers per radian across a range of plus-minus 200 microradians, meeting the preliminary requirements for the TianQin mission. This APTA test platform has the potential to be widely utilized for ground-based TTL coupling inspection.

astro-ph.IM↗

arXiv2024

Research on Image Super-Resolution Reconstruction Mechanism based on Convolutional Neural Network

Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable advancement has been observed in the domain of single-image super-resolution algorithms, particularly those based on deep learning techniques. Nevertheless, the extraction of image features and nonlinear mapping methods in the reconstruction process remain challenging for existing algorithms. These issues result in the network architecture being unable to effectively utilize the diverse range of information at different levels. The loss of high-frequency details is significant, and the final reconstructed image features are overly smooth, with a lack of fine texture details. This negatively impacts the subjective visual quality of the image. The objective is to recover high-quality, high-resolution images from low-resolution images. In this work, an enhanced deep convolutional neural network model is employed, comprising multiple convolutional layers, each of which is configured with specific filters and activation functions to effectively capture the diverse features of the image. Furthermore, a residual learning strategy is employed to accelerate training and enhance the convergence of the network, while sub-pixel convolutional layers are utilized to refine the high-frequency details and textures of the image. The experimental analysis demonstrates the superior performance of the proposed model on multiple public datasets when compared with the traditional bicubic interpolation method and several other learning-based super-resolution methods. Furthermore, it proves the model's efficacy in maintaining image edges and textures.

cs.CV↗

arXiv2024

Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework

Recent advances in large language models have demonstrated their potential for automated generation of hardware description language (HDL) code from high-level prompts. Researchers have utilized fine-tuning to enhance the ability of these large language models (LLMs) in the field of Chip Design. However, the lack of Verilog data hinders further improvement in the quality of Verilog generation by LLMs. Additionally, the absence of a Verilog and Electronic Design Automation (EDA) script data augmentation framework significantly increases the time required to prepare the training dataset for LLM trainers. This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. For Verilog generation, it translates Verilog files to an abstract syntax tree and then maps nodes to natural language with a predefined template. For Verilog repair, it uses predefined rules to generate the wrong verilog file and then pairs EDA Tool feedback with the right and wrong verilog file. For EDA Script generation, it uses existing LLM(GPT-3.5) to obtain the description of the Script. To evaluate the effectiveness of our data augmentation method, we finetune Llama2-13B and Llama2-7B models using the dataset generated by our augmentation framework. The results demonstrate a significant improvement in the Verilog generation tasks with LLMs. Moreover, the accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark. Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3.5 in Verilog generation and outperforms in EDA script (i.e., SiliconCompiler) generation with only 200 EDA script data.

cs.AR↗

arXiv2024

Advancing Prompt Recovery in NLP: A Deep Dive into the Integration of Gemma-2b-it and Phi2 Models

Prompt recovery, a crucial task in natural language processing, entails the reconstruction of prompts or instructions that language models use to convert input text into a specific output. Although pivotal, the design and effectiveness of prompts represent a challenging and relatively untapped field within NLP research. This paper delves into an exhaustive investigation of prompt recovery methodologies, employing a spectrum of pre-trained language models and strategies. Our study is a comparative analysis aimed at gauging the efficacy of various models on a benchmark dataset, with the goal of pinpointing the most proficient approach for prompt recovery. Through meticulous experimentation and detailed analysis, we elucidate the outstanding performance of the Gemma-2b-it + Phi2 model + Pretrain. This model surpasses its counterparts, showcasing its exceptional capability in accurately reconstructing prompts for text transformation tasks. Our findings offer a significant contribution to the existing knowledge on prompt recovery, shedding light on the intricacies of prompt design and offering insightful perspectives for future innovations in text rewriting and the broader field of natural language processing.

cs.CL↗

arXiv2024

Bayesian Entropy Neural Networks for Physics-Aware Prediction

This paper addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring flexible model behavior to incorporate non-data sample information. We introduce Bayesian Entropy Neural Networks (BENN), a framework grounded in Maximum Entropy (MaxEnt) principles, designed to impose constraints on Bayesian Neural Network (BNN) predictions. BENN is capable of constraining not only the predicted values but also their derivatives and variances, ensuring a more robust and reliable model output. To achieve simultaneous uncertainty quantification and constraint satisfaction, we employ the method of multipliers approach. This allows for the concurrent estimation of neural network parameters and the Lagrangian multipliers associated with the constraints. Our experiments, spanning diverse applications such as beam deflection modeling and microstructure generation, demonstrate the effectiveness of BENN. The results highlight significant improvements over traditional BNNs and showcase competitive performance relative to contemporary constrained deep learning methods.

stat.ML↗

arXiv2024

Smoothing Linear Codes by Rényi Divergence and Applications to Security Reduction

The concept of the smoothing parameter plays a crucial role in both lattice-based and code-based cryptography, primarily due to its effectiveness in achieving nearly uniform distributions through the addition of noise. Recent research by Pathegama and Barg has determined the optimal smoothing bound for random codes under Rényi Divergence for any order $α\in (1, \infty)$ \cite{pathegama2024r}. Considering the inherent complexity of encoding/decoding algorithms in random codes, our research introduces enhanced structural elements into these coding schemes. Specifically, this paper presents a novel derivation of the smoothing bound for random linear codes, maintaining the same order of Rényi Divergence and achieving optimality for any $α\in (1,\infty)$. We extend this framework under KL Divergence by transitioning from random linear codes to random self-dual codes, and subsequently to random quasi-cyclic codes, incorporating progressively more structures. As an application, we derive an average-case to average-case reduction from the Learning Parity with Noise (LPN) problem to the average-case decoding problem. This reduction aligns with the parameter regime in \cite{debris2022worst}, but uniquely employs Rényi divergence and directly considers Bernoulli noise, instead of combining ball noise and Bernoulli noise.

cs.IT↗

arXiv2024

Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model

Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates that each client labels their data for training, which can be both time-consuming and resource-intensive, and may even be impractical for edge devices. Moreover, the training and transmission of deep models present challenges to the computation and communication capabilities of the clients. To address these two inherent challenges in supervised federated learning, we propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication by harnessing pretrained vision-language models, such as CLIP. By capitalizing on the zero-shot prediction capability and the well-trained image encoder of the pre-trained CLIP model, we have carefully crafted an efficient and resilient self-training approach. This method refines the initial zero-shot predicted pseudo-labels of unlabeled instances through the sole training of a linear classifier on top of the fixed image encoder. Additionally, to address data heterogeneity within each client, we propose a class-balanced text feature sampling strategy for generating synthetic instances in the feature space to support local training. Experiments are conducted on multiple benchmark datasets. The experimental results demonstrate that our proposed method greatly enhances model performance in comparison to CLIP's zero-shot predictions and even outperforms supervised federated learning benchmark methods given limited computational and communication overhead.

cs.AI↗

arXiv2024

Low-Rank Robust Subspace Tensor Clustering for Metro Passenger Flow Modeling

Tensor clustering has become an important topic, specifically in spatio-temporal modeling, due to its ability to cluster spatial modes (e.g., stations or road segments) and temporal modes (e.g., time of the day or day of the week). Our motivating example is from subway passenger flow modeling, where similarities between stations are commonly found. However, the challenges lie in the innate high-dimensionality of tensors and also the potential existence of anomalies. This is because the three tasks, i.e., dimension reduction, clustering, and anomaly decomposition, are inter-correlated to each other, and treating them in a separate manner will render a suboptimal performance. Thus, in this work, we design a tensor-based subspace clustering and anomaly decomposition technique for simultaneously outlier-robust dimension reduction and clustering for high-dimensional tensors. To achieve this, a novel low-rank robust subspace clustering decomposition model is proposed by combining Tucker decomposition, sparse anomaly decomposition, and subspace clustering. An effective algorithm based on Block Coordinate Descent is proposed to update the parameters. Prudent experiments prove the effectiveness of the proposed framework via the simulation study, with a gain of +25% clustering accuracy than benchmark methods in a hard case. The interrelations of the three tasks are also analyzed via ablation studies, validating the interrelation assumption. Moreover, a case study in the station clustering based on real passenger flow data is conducted, with quite valuable insights discovered.

stat.ME↗

arXiv2024

Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels

One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based fault classifiers. Specifically, we propose a methodology on how, when available, labels regarding the fault taxonomy can be used to increase unknown fault detection performance without sacrificing model performance. To achieve this, we propose to utilize soft label techniques to improve the state-of-the-art deep novel fault detection techniques during the training process and novel hierarchically consistent detection statistics for online novel fault detection. Finally, we demonstrated increased detection performance on novel fault detection in inspection images from the hot steel rolling process, with results well replicated across multiple scenarios and baseline detection methods.

cs.LG↗

arXiv2024

Hierarchical Multi-label Classification for Fine-level Event Extraction from Aviation Accident Reports

A large volume of accident reports is recorded in the aviation domain, which greatly values improving aviation safety. To better use those reports, we need to understand the most important events or impact factors according to the accident reports. However, the increasing number of accident reports requires large efforts from domain experts to label those reports. In order to make the labeling process more efficient, many researchers have started developing algorithms to identify the underlying events from accident reports automatically. This article argues that we can identify the events more accurately by leveraging the event taxonomy. More specifically, we consider the problem a hierarchical classification task where we first identify the coarse-level information and then predict the fine-level information. We achieve this hierarchical classification process by incorporating a novel hierarchical attention module into BERT. To further utilize the information from event taxonomy, we regularize the proposed model according to the relationship and distribution among labels. The effectiveness of our framework is evaluated with the data collected by National Transportation Safety Board (NTSB). It has been shown that fine-level prediction accuracy is highly improved, and the regularization term can be beneficial to the rare event identification problem.

cs.AI↗

arXiv2024

DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes

Implicit neural representations for video (NeRV) have recently become a novel way for high-quality video representation. However, existing works employ a single network to represent the entire video, which implicitly confuse static and dynamic information. This leads to an inability to effectively compress the redundant static information and lack the explicitly modeling of global temporal-coherent dynamic details. To solve above problems, we propose DS-NeRV, which decomposes videos into sparse learnable static codes and dynamic codes without the need for explicit optical flow or residual supervision. By setting different sampling rates for two codes and applying weighted sum and interpolation sampling methods, DS-NeRV efficiently utilizes redundant static information while maintaining high-frequency details. Additionally, we design a cross-channel attention-based (CCA) fusion module to efficiently fuse these two codes for frame decoding. Our approach achieves a high quality reconstruction of 31.2 PSNR with only 0.35M parameters thanks to separate static and dynamic codes representation and outperforms existing NeRV methods in many downstream tasks. Our project website is at https://haoyan14.github.io/DS-NeRV.

cs.CV↗

arXiv2024

Learning-driven Physically-aware Large-scale Circuit Gate Sizing

Gate sizing plays an important role in timing optimization after physical design. Existing machine learning-based gate sizing works cannot optimize timing on multiple timing paths simultaneously and neglect the physical constraint on layouts. They cause sub-optimal sizing solutions and low-efficiency issues when compared with commercial gate sizing tools. In this work, we propose a learning-driven physically-aware gate sizing framework to optimize timing performance on large-scale circuits efficiently. In our gradient descent optimization-based work, for obtaining accurate gradients, a multi-modal gate sizing-aware timing model is achieved via learning timing information on multiple timing paths and physical information on multiple-scaled layouts jointly. Then, gradient generation based on the sizing-oriented estimator and adaptive back-propagation are developed to update gate sizes. Our results demonstrate that our work achieves higher timing performance improvements in a faster way compared with the commercial gate sizing tool.

cs.LG↗

arXiv2023

Quasi-monolithic Compact Interferometric Sensor Head Design with Laser Auto-alignment

Interferometers play a crucial role in high-precision displacement measurement such as gravitational-wave detection. Conventional interferometer designs require accurate laser alignment, including the laser pointing and the waist position, to maintain high interference contrast during motion. Although the corner reflector returns the reflected beam in parallel, there is still a problem of lateral beam shift which reduces the interference contrast. This paper presents a new compact interferometric sensor head design for measuring translations with auto-alignment. It works without laser beam alignment adjustment and maintains high interferometric contrast during arbitrary motion (tilts as well as lateral translation). Automatic alignment of the measuring beam with the reference beam is possible by means of a secondary reflection design with a corner reflector. A 20*10*10mm^3 all-glass quasi-monolithic sensor head is built based on UV adhesive bonding and tested by a piezoelectric (PZT) positioning stage. Our sensor head achieved a displacement sensitivity of 1 pm/Hz^1/2 at 1Hz with a tilt dynamic range over +/_200 mrad. This optical design can be widely used for high-precision displacement measurement over a large tilt dynamic range, such as torsion balances and seismometers.

physics.ins-det↗

arXiv2023

Epidemic extinction in a simplicial susceptible-infected-susceptible model

We study the extinction of epidemics in a simplicial susceptible-infected-susceptible model, where each susceptible individual becomes infected either by two-body interactions ($S+I \to 2I$) with a rate $β$ or by three-body interactions ($S+2I \to 3I$) with a rate $β(1+δ)$, and each infected individual spontaneously recovers ($I \to S$) with a rate $μ$. We focus on the case $δ>0$ that embodies a synergistic reinforcement effect in the group interactions. By using the theory of large fluctuations to solve approximately for the master equation, we reveal two different scenarios for optimal path to extinction, and derive the associated action $\mathcal{S}$ for $β_b<β<β_c$ and for $β>β_c$, where $β_b=4 (1+δ)/(2+δ)^2$ and $β_c=1$ are two different bifurcation points. The action $\mathcal{S}$ shows different scaling laws with the distance of the infectious rate to the transition points $β_b$ and $β_c$, characterized by two different exponents: 3/2 and 1, respectively. Interestingly, the second-order derivative of $\mathcal{S}$ with respect to $β$ is discontinuous at $β=β_c$, while $\mathcal{S}$ and its first-order derivative are both continuous, reminiscent of the second-order phase transitions in equilibrium systems. Finally, a rare-event simulation method is used to compute the mean extinction time, which depends exponentially on $\mathcal{S}$ and the size $N$ of the population. The simulations results are in well agreement with the proposed theory.

cond-mat.stat-mech↗