Searcharxiv⌕ Search

arXiv subjects

Yi Hu

Publications and source records attributed to Yi Hu.

At least 91 records · Page 5Linked to original sources
arXiv2023

Metacognition-Enhanced Few-Shot Prompting With Positive Reinforcement

Few-shot prompting elicits the remarkable abilities of large language models by equipping them with a few demonstration examples in the input. However, the traditional method of providing large language models with all demonstration input-output pairs at once may not effectively guide large language models to learn the specific input-output mapping relationship. In this paper, inspired by the regulatory and supportive role of metacognition in students' learning, we propose a novel metacognition-enhanced few-shot prompting, which guides large language models to reflect on their thought processes to comprehensively learn the given demonstration examples. Furthermore, considering that positive reinforcement can improve students' learning motivation, we introduce positive reinforcement into our metacognition-enhanced few-shot prompting to promote the few-shot learning of large language models by providing response-based positive feedback. The experimental results on two real-world datasets show that our metacognition-enhanced few-shot prompting with positive reinforcement surpasses traditional few-shot prompting in classification accuracy and macro F1.

cs.CL↗
arXiv2023

T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering

Large Language Models (LLMs) have recently demonstrated exceptional performance in various Natural Language Processing (NLP) tasks. They have also shown the ability to perform chain-of-thought (CoT) reasoning to solve complex problems. Recent studies have explored CoT reasoning in complex multimodal scenarios, such as the science question answering task, by fine-tuning multimodal models with high-quality human-annotated CoT rationales. However, collecting high-quality COT rationales is usually time-consuming and costly. Besides, the annotated rationales are hardly accurate due to the external essential information missed. To address these issues, we propose a novel method termed T-SciQ that aims at teaching science question answering with LLM signals. The T-SciQ approach generates high-quality CoT rationales as teaching signals and is advanced to train much smaller models to perform CoT reasoning in complex modalities. Additionally, we introduce a novel data mixing strategy to produce more effective teaching data samples for simple and complex science question answer problems. Extensive experimental results show that our T-SciQ method achieves a new state-of-the-art performance on the ScienceQA benchmark, with an accuracy of 96.18%. Moreover, our approach outperforms the most powerful fine-tuned baseline by 4.5%. The code is publicly available at https://github.com/T-SciQ/T-SciQ.

cs.CL↗
arXiv2023

Dynamics and fluctuations of minimally-structured glass formers

The mean-field theory (MFT) of simple glasses, which is exact in the limit of infinite spatial dimensions, $d\rightarrow\infty$, offers theoretical insight as well as quantitative predictions about certain features of $d=3$ systems. In order to more systematically relate the behavior of physical systems to MFT, however, various finite-$d$ corrections need to be accounted for. Although some efforts along this direction have already been undertaken, theoretical and technical challenges hinder progress. A general approach to sidestep many of these difficulties consists of simulating minimally-structured models whose behavior smoothly converges to that described by the MFT as $d$ increases, so as to permit a dimensional extrapolation. Using this approach, we here extract the small fluctuations around the dynamical MFT captured by a standard liquid-state observable the non-Gaussian parameter $α_2$. The results provide insight into the physical origin of these fluctuations as well as a quantitative reference with which to compare observations in more realistic glass formers.

cond-mat.dis-nn↗
arXiv2023

Threshold for Blowup and Stability for Nonlinear Schrödinger Equation with Rotation

We consider the focusing NLS with an angular momentum and a harmonic potential, which models Bose-Einstein condensate under a rotating magnetic trap. We give a sharp condition on the global existence and blowup in the mass-critical case. We further consider the stability of such systems via variational method. We determine that at the critical exponent $p=1+4/n$, the mass of $Q$, the ground state for the NLS with zero potential, is the threshold for both finite time blowup and orbital instability. Moreover, we prove a sharp threshold theorem for the rotational NLS with an inhomogeneous nonlinearity. The analysis relies on the existence of ground state as well as a virial identity for the associated kinetic-magnetic operator.

math.AP↗
arXiv2023

Semantic Segmentation of Anomalous Diffusion Using Deep Convolutional Networks

Heterogeneous dynamics commonly emerges in anomalous diffusion with intermittent transitions of diffusion states but proves challenging to identify using conventional statistical methods. To effectively capture these transient changes of diffusion states, we propose a deep learning model (U-AnDi) for the semantic segmentation of anomalous diffusion trajectories. This model is developed with the dilated causal convolution (DCC), gated activation unit (GAU), and U-Net architecture. The study addresses two key subtasks related to trajectory segmentation and changepoint detection, concentrating on variations in diffusion exponents and dynamic models. Additionally, extended analyses are conducted on the segmentation of single-model trajectories, multi-state biological trajectories, and anomalous diffusion with added long-time correlations. By rationally designing comparative models and evaluating the performance of U-AnDi against these models, we discover that U-AnDi consistently outperforms other models across all segmentation tasks, thereby affirming its superiority in the field. This performance edge also sheds light on the interpretability of U-AnDi's core components: DCC, GAU, and U-Net. The clarity with which these components contribute to U-AnDi's success underscores their congruence with the intrinsic physics underlying anomalous diffusion. Furthermore, our model is examined using real-world anomalous diffusion data: the diffusion of transmembrane proteins on cell membrane surfaces, and the segmentation results are highly consistent with experimental observations. Our findings could offer a heuristic deep learning solution for the detection of heterogeneous dynamics in single-molecule/particle tracking experiments, and have the potential to be generalized as a universal scheme for time-series segmentation.

physics.bio-ph↗
arXiv2023

BERT-PIN: A BERT-based Framework for Recovering Missing Data Segments in Time-series Load Profiles

Inspired by the success of the Transformer model in natural language processing and computer vision, this paper introduces BERT-PIN, a Bidirectional Encoder Representations from Transformers (BERT) powered Profile Inpainting Network. BERT-PIN recovers multiple missing data segments (MDSs) using load and temperature time-series profiles as inputs. To adopt a standard Transformer model structure for profile inpainting, we segment the load and temperature profiles into line segments, treating each segment as a word and the entire profile as a sentence. We incorporate a top candidates selection process in BERT-PIN, enabling it to produce a sequence of probability distributions, based on which users can generate multiple plausible imputed data sets, each reflecting different confidence levels. We develop and evaluate BERT-PIN using real-world dataset for two applications: multiple MDSs recovery and demand response baseline estimation. Simulation results show that BERT-PIN outperforms the existing methods in accuracy while is capable of restoring multiple MDSs within a longer window. BERT-PIN, served as a pre-trained model, can be fine-tuned for conducting many downstream tasks, such as classification and super resolution.

eess.AS↗
arXiv2023

Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models

Large language models (LLMs) have scaled up to unlock a wide range of complex reasoning tasks with the aid of various prompting methods. However, current prompting methods generate natural language intermediate steps to help reasoning, which can cause imperfect task reduction and confusion. To mitigate such limitations, we explore code prompting, a neural symbolic prompting method with both zero-shot and few-shot versions which triggers code as intermediate steps. We conduct experiments on 7 widely-used benchmarks involving symbolic reasoning and arithmetic reasoning. Code prompting generally outperforms chain-of-thought (CoT) prompting. To further understand the performance and limitations of code prompting, we perform extensive ablation studies and error analyses, and identify several exclusive advantages of using symbolic promptings compared to natural language. We also consider the ensemble of code prompting and CoT prompting to combine the strengths of both. Finally, we show through experiments how code annotations and their locations affect code prompting.

cs.CL↗
arXiv2023

From Stoner to Local Moment Magnetism in Atomically Thin Cr2Te3

The field of two-dimensional (2D) ferromagnetism has been proliferating over the past few years, with ongoing interests in basic science and potential applications in spintronic technology. However, a high-resolution spectroscopic study of the 2D ferromagnet is still lacking due to the small size and air sensitivity of the exfoliated nanoflakes. Here, we report a thickness-dependent ferromagnetism in epitaxially grown Cr2Te3 thin films and investigate the evolution of the underlying electronic structure by synergistic angle-resolved photoemission spectroscopy, scanning tunneling microscopy, x-ray absorption spectroscopy, and first-principle calculations. A conspicuous ferromagnetic transition from Stoner to Heisenberg-type is directly observed in the atomically thin limit, indicating that dimensionality is a powerful tuning knob to manipulate the novel properties of 2D magnetism. Monolayer Cr2Te3 retains robust ferromagnetism, but with a suppressed Curie temperature, due to the drastic drop in the density of states near the Fermi level. Our results establish atomically thin Cr2Te3 as an excellent platform to explore the dual nature of localized and itinerant ferromagnetism in 2D magnets.

cond-mat.mtrl-sci↗
arXiv2023

PSF-based Analysis for Detecting Unresolved Wide Binaries

Wide binaries play a crucial role in analyzing the birth environment of stars and the dynamical evolution of clusters. When wide binaries are located at greater distances, their companions may overlap in the observed images, becoming indistinguishable and resulting in unresolved wide binaries, which are difficult to detect using traditional methods. Utilizing deep learning, we present a method to identify unresolved wide binaries by analyzing the point-spread function (PSF) morphology of telescopes. Our trained model demonstrates exceptional performance in differentiating between single stars and unresolved binaries with separations ranging from 0.1 to 2 physical pixels, where the PSF FWHM is ~2 pixels, achieving an accuracy of 97.2% for simulated data from the Chinese Space Station Telescope. We subsequently tested our method on photometric data of NGC 6121 observed by the Hubble Space Telescope. The trained model attained an accuracy of 96.5% and identified 18 wide binary candidates with separations between 7 and 140 au. The majority of these wide binary candidates are situated outside the core radius of NGC 6121, suggesting that they are likely first-generation stars, which is in general agreement with the results of Monte Carlo simulations. Our PSF-based method shows great promise in detecting unresolved wide binaries and is well suited for observations from space-based telescopes with stable PSF. In the future, we aim to apply our PSF-based method to next-generation surveys such as the China Space Station Optical Survey, where a larger-field-of-view telescope will be capable of identifying a greater number of such wide binaries.

astro-ph.SR↗
arXiv2023

Quasi 1D Nanobelts from the Sustainable Liquid Exfoliation of Terrestrial Minerals for Future Martian based Electronics

The sky is the limit with regards to the societal impact nanomaterials can have on our lives. However, in this study we show that their potential is out of this world. The planet Mars has an abundant source of calcium sulfate minerals and in our work, we show that these deposits can be the basis of transformative nanomaterials to potentially support future space endeavors. Through a scalable eco-friendly liquid processing technique performed on two common terrestrial gypsum, our simple method presented a cost-efficient procedure to yield the commercially valuable intermediate phase of gypsum, known as bassanite. Through the liquid exfoliation of bassanite powders, suspensions of large aspect ratio anhydrite nanobelts with long-term stability were characterized through scanning electron microscopy and Raman spectroscopy. Transmission electron microscopy showed nanobelts to have a mesocrystal structure, with distinct nanoparticle constituents making up the lattice. Unexpectedly, anhydrite nanobelts had remarkable electronic properties, namely a bandgap that was easily tuned between semiconducting (~2.2 eV) and insulating (~4 eV) behaviors through dimensional control measured via atomic force microscopy. To demonstrate the application potential of our nanobelts; optoelectronic, electrochemical and nanocomposite measurements were made. For the hydrogen evolution reaction and mechanical reinforcement, selenite-based anhydrite nanobelts displayed superlative performances.

physics.app-ph↗
arXiv2023

A multinode quantum network over a metropolitan area

Towards realizing the future quantum internet, a pivotal milestone entails the transition from two-node proof-of-principle experiments conducted in laboratories to comprehensive, multi-node setups on large scales. Here, we report on the debut implementation of a multi-node entanglement-based quantum network over a metropolitan area. We equipped three quantum nodes with atomic quantum memories and their telecom interfaces, and combined them into a scalable phase-stabilized architecture through a server node. We demonstrated heralded entanglement generation between two quantum nodes situated 12.5 km apart, and the storage of entanglement exceeding the round-trip communication time. We also showed the concurrent entanglement generation on three links. Our work provides a metropolitan-scale testbed for the evaluation and exploration of multi-node quantum network protocols and starts a new stage of quantum internet research.

quant-ph↗
arXiv2023

Gaussian Boson Sampling with Pseudo-Photon-Number Resolving Detectors and Quantum Computational Advantage

We report new Gaussian boson sampling experiments with pseudo-photon-number-resolving detection, which register up to 255 photon-click events. We consider partial photon distinguishability and develop a more complete model for the characterization of the noisy Gaussian boson sampling. In the quantum computational advantage regime, we use Bayesian tests and correlation function analysis to validate the samples against all current classical mockups. Estimating with the best classical algorithms to date, generating a single ideal sample from the same distribution on the supercomputer Frontier would take ~ 600 years using exact methods, whereas our quantum computer, Jiuzhang 3.0, takes only 1.27 us to produce a sample. Generating the hardest sample from the experiment using an exact algorithm would take Frontier ~ 3.1*10^10 years.

quant-ph↗
arXiv2023

MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. The novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial-temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad-GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area.

eess.SP↗
arXiv2023

ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction

Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations for benefiting all test instances. We design demonstrations describing relationships that enable LLMs to understand positional relationships. We introduce formatting demonstrations for easy answer extraction. Additionally, the framework improves diverse demonstrations by updating them iteratively. Our experiments on three widely used benchmark datasets demonstrate that the ICL-D3IE framework enables Davinci-003/ChatGPT to achieve superior performance when compared to previous pre-trained methods fine-tuned with full training in both the in-distribution (ID) setting and in the out-of-distribution (OOD) setting. Code is available at https://github.com/MAEHCM/ICL-D3IE.

cs.CL↗
arXiv2023

Intelligent Communication Planning for Constrained Environmental IoT Sensing with Reinforcement Learning

Internet of Things (IoT) technologies have enabled numerous data-driven mobile applications and have the potential to significantly improve environmental monitoring and hazard warnings through the deployment of a network of IoT sensors. However, these IoT devices are often power-constrained and utilize wireless communication schemes with limited bandwidth. Such power constraints limit the amount of information each device can share across the network, while bandwidth limitations hinder sensors' coordination of their transmissions. In this work, we formulate the communication planning problem of IoT sensors that track the state of the environment. We seek to optimize sensors' decisions in collecting environmental data under stringent resource constraints. We propose a multi-agent reinforcement learning (MARL) method to find the optimal communication policies for each sensor that maximize the tracking accuracy subject to the power and bandwidth limitations. MARL learns and exploits the spatial-temporal correlation of the environmental data at each sensor's location to reduce the redundant reports from the sensors. Experiments on wildfire spread with LoRA wireless network simulators show that our MARL method can learn to balance the need to collect enough data to predict wildfire spread with unknown bandwidth limitations.

cs.MA↗
arXiv2023

DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data

Despite the tremendous advances achieved over the past years by deep learning techniques, the latest risk prediction models for industrial applications still rely on highly handtuned stage-wised statistical learning tools, such as gradient boosting and random forest methods. Different from images or languages, real-world financial data are high-dimensional, sparse, noisy and extremely imbalanced, which makes deep neural network models particularly challenging to train and fragile in practice. In this work, we propose DeRisk, an effective deep learning risk prediction framework for credit risk prediction on real-world financial data. DeRisk is the first deep risk prediction model that outperforms statistical learning approaches deployed in our company's production system. We also perform extensive ablation studies on our method to present the most critical factors for the empirical success of DeRisk.

cs.LG↗
arXiv2023

Damped nonlinear Schrödinger equation with Stark effect

We study the $L^2$-critical damped NLS with a Stark potential. We prove that the threshold for global existence and finite time blowup of this equation is given by $\|Q\|_2$, where $Q$ is the unique positive radial solution of $ΔQ + |Q|^{4/d} Q = Q$ in $H^1(\mathbb{R}^d)$. Moreover, in any small neighborhood of $Q$, there exists an initial data $u_0$ above the ground state such that the solution flow admits the log-log blowup speed. This verifies the structural stability for the ``$\log$-$\log$ law'' associated to the NLS mechanism under the perturbation by a damping term and a Stark potential. The proof of our main theorem is based on the Avron-Herbst formula and the analogous result for the unperturbed damped NLS.

math.AP↗
arXiv2023

Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models

Numerous pre-training techniques for visual document understanding (VDU) have recently shown substantial improvements in performance across a wide range of document tasks. However, these pre-trained VDU models cannot guarantee continued success when the distribution of test data differs from the distribution of training data. In this paper, to investigate how robust existing pre-trained VDU models are to various distribution shifts, we first develop an out-of-distribution (OOD) benchmark termed Do-GOOD for the fine-Grained analysis on Document image-related tasks specifically. The Do-GOOD benchmark defines the underlying mechanisms that result in different distribution shifts and contains 9 OOD datasets covering 3 VDU related tasks, e.g., document information extraction, classification and question answering. We then evaluate the robustness and perform a fine-grained analysis of 5 latest VDU pre-trained models and 2 typical OOD generalization algorithms on these OOD datasets. Results from the experiments demonstrate that there is a significant performance gap between the in-distribution (ID) and OOD settings for document images, and that fine-grained analysis of distribution shifts can reveal the brittle nature of existing pre-trained VDU models and OOD generalization algorithms. The code and datasets for our Do-GOOD benchmark can be found at https://github.com/MAEHCM/Do-GOOD.

cs.CV↗