Search

Detecting covariate drift is a common task of significant practical value in supervised learning. Once covariate drift occurs, the models may no longer be applicable, hence numerous studies have been devoted to the advancement of detection methods. However, current research methods are not particularly effective in handling subtle covariate drift when dealing with small proportions of drift samples. In this paper, inspired by the $k$-nearest neighbor (KNN) approach, a novel method called Half $k$-farthest neighbor (Half-KFN) is proposed in response to specific scenarios. Compared to traditional ones, Half-KFN exhibits higher power due to the inherent capability of the farthest neighbors which could better characterize the nature of drift. Furthermore, with larger sample sizes, the employment of the bootstrap for hypothesis testing is recommended. It is leveraged to calculate $p$-values dramatically faster than permutation tests, with speed undergoing an exponential growth as sample size increases. Numerical experiments on simulated and real data are conducted to evaluate our proposed method, and the results demonstrate that it consistently displays superior sensitivity and rapidity in covariate drift detection across various cases.

Microheterogeneity, as a fundamental natural property, is widely presented in a range of microscopic systems such as polymer systems, biomacromolecular systems, and nanosystems, however, the construction of molecular systems of this form has not yet been realized at the level of organic molecules with well-defined structural compositions.Inspired by the "chemical space"concept, I recently reported a study of the single-molecule mixture state, In this preprint,a detailed discussion of microheterogeneity and the concept of "single-molecule mixture" has been provided.

We briefly analyzed the equation of state and critical points of the quantum-corrected Schwarzschild-like black hole and used the Melnikov method to study its thermal chaotic behavior in the extended phase space of flat, closed, and open universes. The results show that the black hole's thermodynamic behavior is similar to that of the Van der Waals system. Although the critical ratios at the critical points differ among the three universes, they are all independent of the quantum correction parameter. For chaos, time perturbations will lead to chaotic behavior when their amplitude exceeds a critical value that depends on the quantum correction parameter and the radius of the dust sphere in the FRW model. Based on this, we found that the chaotic behavior of the black hole varies across different universes depending on the quantum correction parameter, but this parameter always makes chaos more likely. Using the value of the quantum correction parameter determined by Meissner, chaos is always more difficult to occur in an open universe compared to the other two types of universes. Which universe is most prone to chaos depends on the radius of the dust sphere. Finally, chaotic behavior is always present under spatial perturbations., Comment: 22 pages, 10 figures

Pion condensation is a theoretical prediction, where pions form a special state of matter under certain extreme conditions in heavy ion collisions or neutron stars. However, there is currently no solid experimental evidence confirming the existence of pion condensation. We present a near-direct evidence for the existence of pion condensation. In actively changing galactic processes protons can be accelerated to very high energies and collide with the medium (protons or nuclei). The kinetic energy of the protons is mainly used to produce a large number of pions in the central region via gluons. When the collision energy exceeds a certain threshold, the huge amount of soft gluons condensed in protons pour into the central region, the number of pion increases abruptly to the saturation limit, and almost all the available collision energy is used to make pions, creating a dense, low-temperature pion condensation environment. Due to energy conservation and relativistic covariance, the gamma ray spectra produced by condensed pions exhibit recognizable broken power law with the gluon condensation characteristics. We find that they are already present in many recorded gamma ray spectra. Our findings reveal a novel mechanism for the generation of pion condensation, which is prevalent in the formation of high-energy cosmic rays, and deepen our understanding of related topics in a variety of disciplines, including particle physics, astrophysics, condensed matter physics and nuclear physics., Comment: 27 pages, 12 Figures

With the development of autonomous driving technology, there are increasing demands for vehicle control, and MPC has become a widely researched topic in both industry and academia. Existing MPC control methods based on vehicle kinematics or dynamics have challenges such as difficult modeling, numerous parameters, strong nonlinearity, and high computational cost. To address these issues, this paper adapts an existing Data-driven MPC control method and applies it to autonomous vehicle steering control. This method avoids the need for complex vehicle system modeling and achieves trajectory tracking with relatively low computational time and small errors. We validate the control effectiveness of the algorithm in specific scenario through CarSim-Simulink simulation and perform comparative analysis with PID and vehicle kinematics MPC, confirming the feasibility and superiority of it for vehicle steering control.

Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy (aAcc) and last-task averaged accuracy (lAcc) as the evaluation metrics. However, we reveal that such evaluation metrics may not provide adequate emphasis on the novel class performance, and the continual learning ability of FSCIL methods could be ignored under this benchmark. In this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of the performance under the guidance of a parameter $\alpha$. We also present an overall metric in the form of the area under the curve (AUC) along the $\alpha$. Under the guidance of gAcc, we release the potential of intermediate features of the vision transformers to boost the novel-class performance. Taking information from intermediate layers which are less class-specific and more generalizable, we manage to rectify the final features, leading to a more generalizable transformer-based FSCIL framework. Without complex network designs or cumbersome training procedures, our method outperforms existing FSCIL methods at aAcc and gAcc on three datasets. See codes at https://github.com/iSEE-Laboratory/Revisting_FSCIL, Comment: Accepted to ECCV 2024

We obtained the metric of the Schwarzschild-like black hole with loop quantum gravity (LQG) corrections in anti-de Sitter (AdS) space-time, under the assumption that the cosmological constant is decoupled in LQG. We investigated its thermodynamics, including the equation of state, criticality, heat capacity, and Gibbs free energy. The $P-v$ graph was plotted, and the critical behavior was calculated. It was found that, due to the LQG effect, the quantum-corrected Schwarzschild-AdS black hole exhibits a critical point and a critical ratio of $7/18$, which differs from the Reissner-Nordstr$\ddot{\mathrm{o}}$m-AdS black hole's ratio of $3/8$ (the same as that of the Van der Waals system) slightly. However, there are still some similarities compared to the Van der Waals system, such as the same critical exponents and a similar $P-v$ graph. Moreover, it is concluded that the energy-momentum tensor related to the black hole's mass could violate the conventional first law of thermodynamics. This modified first law may violate the conservation of Gibbs free energy during the small black hole-large black hole phase transitions, potentially indicating the occurrence of the zeroth-order phase transition. The Joule-Thomson expansion was also studied. Interestingly, compared to the Schwarzschild-AdS black hole, the LQG effect leads to inversion points. The inversion curve divides the $\left(P,T\right)$ coordinate system into two regions: a heating region and a cooling region, as shown in detail by the inversion curves and isenthalpic curves. The results indicated that there is a minimum inversion mass, below which any black hole will not possess an inversion point., Comment: 38 pages, 8 figures, 1 table

We use a newly recognized gluon distribution in the nucleon, which was predicted by a QCD evolution equation to consistently explain several intriguing phenomena associated with gamma-ray bursts. They are the GeV-TeV spectra of GRB 221009A, the remarkably symmetrical explosion cloud in kilonova AT2017gfo, and the absence of a very high-energy gamma-ray signature in GRB 170817A. We find that these occurrences can be attributed to the gluon condensation within nucleons, i.e., a significant number of soft gluons within nucleons are condensed at a critical momentum, resulting in the emergence of a steep and high peak in the gluon distributions. Through this profound connection between microscopic and macroscopic phenomena, we have not only expanded the applications of the hadronic scenario in cosmic gamma-ray emissions but also presented new evidence for the existence of gluon condensation., Comment: 30 pages, 6 figures, submitted to JCAP

Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action recognition. Inspired by that humans perform actions in diverse environments, our work delves into an intriguing question: Can CLIP-based video learners effectively generalize to video domains they have not encountered during training? To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a comprehensive evaluation of five state-of-the-art CLIP-based video learners under various types of domain gaps. The evaluation demonstrates that previous methods exhibit limited action recognition performance in unseen video domains, revealing potential challenges of the cross-domain open-vocabulary action recognition task. In this paper, we focus on one critical challenge of the task, namely scene bias, and accordingly contribute a novel scene-aware video-text alignment method. Our key idea is to distinguish video representations apart from scene-encoded text representations, aiming to learn scene-agnostic video representations for recognizing actions across domains. Extensive experiments demonstrate the effectiveness of our method. The benchmark and code will be available at https://github.com/KunyuLin/XOV-Action/.

The Galactic Center Excess (GCE), one of the most remarkable discoveries by Fermi-LAT, has prompted extensive exploration over the past decade, often attributed to dark matter or millisecond pulsars. This work proposes a novel interpretation on the origin of the GCE, focusing on the observed spectral shape. Protons are accelerated at the Galactic center and collide with the neutron cluster on the surface of the non-rotating neutron stars. Due to the gluon condensation in nucleons, these collisions produce a large number of mesons, which have reached to the saturation state and subsequently generate the broken power law in the gamma ray spectra. We explained the spectral shape of GCE using the gluon condensation and an assumption of existing the non-rotating neutron stars at the Galactic center. This example of the gluon condensation mechanism not only expands the applications of the hadronic scenario in the cosmic gamma ray spectra but also provides a new evidence of the gluon condensation., Comment: 19 pages, 3 figures, 1 table; Accepted by PRD

The dialogue systems in customer services have been developed with neural models to provide users with precise answers and round-the-clock support in task-oriented conversations by detecting customer intents based on their utterances. Existing intent detection approaches have highly relied on adaptively pre-training language models with large-scale datasets, yet the predominant cost of data collection may hinder their superiority. In addition, they neglect the information within the conversational responses of the agents, which have a lower collection cost, but are significant to customer intent as agents must tailor their replies based on the customers' intent. In this paper, we propose RSVP, a self-supervised framework dedicated to task-oriented dialogues, which utilizes agent responses for pre-training in a two-stage manner. Specifically, we introduce two pre-training tasks to incorporate the relations of utterance-response pairs: 1) Response Retrieval by selecting a correct response from a batch of candidates, and 2) Response Generation by mimicking agents to generate the response to a given utterance. Our benchmark results for two real-world customer service datasets show that RSVP significantly outperforms the state-of-the-art baselines by 4.95% for accuracy, 3.4% for MRR@3, and 2.75% for MRR@5 on average. Extensive case studies are investigated to show the validity of incorporating agent responses into the pre-training stage., Comment: Accepted by EMNLP 2023 Findings

Attitude tracking on the unit sphere of dimension $3$ based on sliding mode is considered in this paper. The tangent bundle of Lagrangian dynamics that describes the rotational motion of a rigid body is first shown to be a Lie group, and then a sliding surface that emerged on it is defined. Next, a sliding-mode controller is designed for attitude tracking that relies on an intrinsic error defined on the Lie group. Almost global asymptotic stability of the closed loop is demonstrated using the Lyapunov analysis. Numerical simulations are included to compare the performance of the sliding mode controller designed on the Lie group with that designed in the embedding Euclidean space.

Visual bird's eye view (BEV) semantic segmentation helps autonomous vehicles understand the surrounding environment only from images, including static elements (e.g., roads) and dynamic elements (e.g., vehicles, pedestrians). However, the high cost of annotation procedures of full-supervised methods limits the capability of the visual BEV semantic segmentation, which usually needs HD maps, 3D object bounding boxes, and camera extrinsic matrixes. In this paper, we present a novel semi-supervised framework for visual BEV semantic segmentation to boost performance by exploiting unlabeled images during the training. A consistency loss that makes full use of unlabeled data is then proposed to constrain the model on not only semantic prediction but also the BEV feature. Furthermore, we propose a novel and effective data augmentation method named conjoint rotation which reasonably augments the dataset while maintaining the geometric relationship between the front-view images and the BEV semantic segmentation. Extensive experiments on the nuScenes and Argoverse datasets show that our semi-supervised framework can effectively improve prediction accuracy. To the best of our knowledge, this is the first work that explores improving visual BEV semantic segmentation performance using unlabeled data. The code is available at https://github.com/Junyu-Z/Semi-BEVseg, Comment: Accepted by ICRA2024

Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by learning task-specific prompts. However, existing prompt-based methods heavily rely on strong pretraining (typically trained on ImageNet-21k), and we find that their models could be trapped if the potential gap between the pretraining task and unknown future tasks is large. In this work, we develop a learnable Adaptive Prompt Generator (APG). The key is to unify the prompt retrieval and prompt learning processes into a learnable prompt generator. Hence, the whole prompting process can be optimized to reduce the negative effects of the gap between tasks effectively. To make our APG avoid learning ineffective knowledge, we maintain a knowledge pool to regularize APG with the feature distribution of each class. Extensive experiments show that our method significantly outperforms advanced methods in exemplar-free incremental learning without (strong) pretraining. Besides, under strong retraining, our method also has comparable performance to existing prompt-based models, showing that our method can still benefit from pretraining. Codes can be found at https://github.com/TOM-tym/APG, Comment: Accepted to ICCV 2023

Our research focuses on solving the zero-shot text classification problem in NLP, with a particular emphasis on innovative self-training strategies. To achieve this objective, we propose a novel self-training strategy that uses labels rather than text for training, significantly reducing the model's training time. Specifically, we use categories from Wikipedia as our training set and leverage the SBERT pre-trained model to establish positive correlations between pairs of categories within the same text, facilitating associative training. For new test datasets, we have improved the original self-training approach, eliminating the need for prior training and testing data from each target dataset. Instead, we adopt Wikipedia as a unified training dataset to better approximate the zero-shot scenario. This modification allows for rapid fine-tuning and inference across different datasets, greatly reducing the time required for self-training. Our experimental results demonstrate that this method can adapt the model to the target dataset within minutes. Compared to other BERT-based transformer models, our approach significantly reduces the amount of training data by training only on labels, not the actual text, and greatly improves training efficiency by utilizing a unified training set. Additionally, our method achieves state-of-the-art results on both the Yahoo Topic and AG News datasets.

Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed base on optimization methods. In this paper, we propose a novel physics-informed, learning-based calibration approach that achieves performances comparable to and even better than those of optimization-based methods. To this end, we combine the classical deep autoencoder, an unsupervised machine learning model consisting of one encoder and one decoder, with traffic flow models. Our approach informs the decoder of the physical traffic flow models and thus induces the encoder to yield reasonable traffic parameters given flow and speed measurements. We also introduce the denoising autoencoder into our method so that it can handles not only with normal data but also with corrupted data with missing values. We verified our approach with a case study of I-210 E in California.

Optical bistability is fundamental for all-optical switches, but typically requires high-Q cavities with micrometer sizes. Through boosting nonlinearity with photo-thermo-optical effects, we achieve bistability in a silicon Mie resonator with a volume size of 10-3 um3 and Q-factor < 10, both are record-low. Furthermore, bistable scattering naturally leads to large super-linear emission-excitation power dependence, which we applied to enhance optical resolution by more than 3 times. Our work paves the way toward nanoscale photonics computation and label-free semiconductor nano-inspection.