623509 research outputs found
Sort by
Trion Engineered Multimodal Transistors in Two dimensional Bilayer Semiconductor Lateral Heterostructures
No full textMultimodal device operations are essential to advancing the integration of 2D semiconductors in electronics, photonics, information and quantum technology. Precise control over carrier dynamics, particularly exciton generation and transport, is crucial for finetuning the functionality of optoelectronic devices based on 2D semiconductor heterostructure. However, the traditional exciton engineering methods in 2D semiconductors are mainly restricted to the artificially assembled vertical pn heterostructures with electrical or strain induced confinements. In this study, we utilized bilayer 2D lateral npn multijunction heterostructures with intrinsically spatially separated energy landscapes to achieve preferential exciton generation and manipulation without external confinement. In lateral npn FET geometry, we uncover unique and nontrivial properties, including dynamic tuning of channel photoresponsivity from positive to negative. The multimodal operation of these 2D FETs is achieved by carefully adjusting electrical bias and the impinging photon energy, enabling precise control over the trions generation and transport. Cryogenic photoluminescence measurement revealed the presence of trions in bilayer MoSe2 and intrinsic trap states in WSe2. Measurements in different FET device geometries show the multifunctionality of 2D lateral heterostructure phototransistors for efficient tuning and electrical manipulation of excitonic characteristics. Our findings pave the way for developing practical exciton-based transistors, sensors, multimodal optoelectronic and quantum technologie
An Innovative CGL-MHA Model for Sarcasm Sentiment Recognition Using the MindSpore Framework
No full textThe pervasive use of the Internet and social media introduces significant challenges to automated sentiment analysis, particularly for sarcastic expressions in user-generated content. Sarcasm conveys negative emotions through ostensibly positive or exaggerated language, complicating its detection within natural language processing tasks. To address this, we propose an innovative sarcasm detection model integrating Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Multi-Head Attention mechanisms. The CNN component captures local n-gram features, while GRU and LSTM layers model sequential dependencies and contextual information. Multi-Head Attention enhances the model\u27s focus on relevant parts of the input, improving interpretability. Experiments on two sarcasm detection datasets, Headlines and Riloff, demonstrate that the model achieves an accuracy of 81.20% and an F1 score of 80.77% on Headlines, and an accuracy of 79.72% with an F1 score of 61.39% on Riloff, outperforming traditional models. These results validate the effectiveness of our hybrid approach for sarcasm detection in social media texts
PARIS: A Practical, Adaptive Trace-Fetching and Real-Time Malicious Behavior Detection System
No full textThe escalating sophistication of cyber-attacks and the widespread utilization of stealth tactics have led to significant security threats globally. Nevertheless, the existing static detection methods exhibit limited coverage, and traditional dynamic monitoring approaches encounter challenges in bypassing evasion techniques. Thus, it has become imperative to implement nuanced and dynamic analysis to achieve precise behavior detection in real time. There are two pressing concerns associated with current dynamic malware behavior detection solutions. Firstly, the collection and processing of data entail a significant amount of overhead, making it challenging to be employed for real-time detection on the end host. Secondly, these approaches tend to treat malware as a singular entity, thereby overlooking varied behaviors within one instance. To fill these gaps, we propose PARIS, an adaptive trace fetching, lightweight, real-time malicious behavior detection system. Specifically, we monitor malicious behavior with Event Tracing for Windows (ETW) and learn to selectively collect maliciousness-related APIs or call stacks, significantly reducing the data collection overhead. As a result, we can monitor a wider range of APIs and detect more intricate attack behavior. We implemented a prototype of PARIS and evaluated the system overhead, the accuracy of comparative behavior recognition, and the impact of different models and parameters. The result demonstrates that PARIS can reduce over 98.8% of data compared to the raw ETW trace and hence decreases the overhead on the host in terms of memory, bandwidth, and CPU usage with a similar detection accuracy to the baselines that suffer from the high overhead. Furthermore, a breakdown evaluation shows that 80% of the memory and bandwidth savings and a complete reduction in CPU usage can be attributed to our adaptive trace-fetching collector
Task-Oriented Hierarchical Object Decomposition for Visuomotor Control
No full textGood pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these representations cannot effectively ignore any task-irrelevant information in the scene, and (2) They often lack the representational capacity to handle unconstrained/complex real-world scenes. Instead, we propose to train a large combinatorial family of representations organized by scene entities: objects and object parts. This hierarchical object decomposition for task-oriented representations (HODOR) permits selectively assembling different representations specific to each task while scaling in representational capacity with the complexity of the scene and the task. In our experiments, we find that HODOR outperforms prior pre-trained representations, both scene vector representations and object-centric representations, for sample-efficient imitation learning across 5 simulated and 5 real-world manipulation tasks. We further find that the invariances captured in HODOR are inherited into downstream policies, which can robustly generalize to out-of-distribution test conditions, permitting zero-shot skill chaining. Appendix, code, and videos: https://sites.google.com/view/hodor-corl24
Motivic principal value integrals for hyperplane arrangements
No full textA conjecture of Denef-Jacobs-Veys relates motivic principal value integrals of multivalued rational top-forms with cohomology support loci of rank one local systems. We give a stronger positive answer to this conjecture for hyperplane arrangements
Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles
No full textDeep learning models in medical contexts face challenges like data scarcity, inhomogeneity, and privacy concerns. This study focuses on improving ventricular segmentation in brain MRI images using synthetic data. We employed two latent diffusion models (LDMs): a mask generator trained using 10,000 masks, and a corresponding SPADE image generator optimized using 6,881 scans to create an MRI conditioned on a 3D brain mask. Conditioning the mask generator on ventricular volume in combination with classifier-free guidance enabled the control of the ventricular volume distribution of the generated synthetic images. Next, the performance of the synthetic data was tested using three nnU-Net segmentation models trained on a real, augmented and entirely synthetic data, respectively. The resulting models were tested on a completely independent hold-out dataset of patients with enlarged ventricles, with manual delineation of the ventricles used as ground truth. The model trained on real data showed a mean absolute error (MAE) of 9.09 \pm 12.18 mL in predicted ventricular volume, while the models trained on synthetic and augmented data showed MAEs of 7.52 \pm 4.81 mL and 6.23 \pm 4.33 mL, respectively. Both the synthetic and augmented model also outperformed the state-of-the-art model SynthSeg, which due to limited performance in cases of large ventricular volumes, showed an MAE of 7.73 \pm 12.12 mL with a factor of 3 higher standard deviation. The model trained on augmented data showed the highest Dice score of 0.892 \pm 0.05, slightly outperforming SynthSeg and on par with the model trained on real data. The synthetic model performed similar to SynthSeg. In summary, we provide evidence that guided synthesis of labeled brain MRI data using LDMs improves the segmentation of enlarged ventricles and outperforms existing state-of-the-art segmentation models
A rigidity result for axisymmetric toric Ricci solitons
No full textWe examine a non-axisymmetric perturbation of a family of axisymmetric toric Einstein manifolds and Ricci solitons studied in Firester-Tsiamis (2024). We establish a rigidity result stating that these axisymmetric Ricci solitons do not admit constant-angle non-axisymmetric perturbations except for conformally flat cases. For these new cases, our result leads to an explicit description of the Einstein metrics and a classification of the Ricci solitons under a volume-collapsing ansatz.7 page
Zero-Shot Self-Consistency Learning for Seismic Irregular Spatial Sampling Reconstruction
No full textSeismic exploration is currently the most important method for understanding subsurface structures. However, due to surface conditions, seismic receivers may not be uniformly distributed along the measurement line, making the entire exploration work difficult to carry out. Previous deep learning methods for reconstructing seismic data often relied on additional datasets for training. While some existing methods do not require extra data, they lack constraints on the reconstruction data, leading to unstable reconstruction performance. In this paper, we proposed a zero-shot self-consistency learning strategy and employed an extremely lightweight network for seismic data reconstruction. Our method does not require additional datasets and utilizes the correlations among different parts of the data to design a self-consistency learning loss function, driving a network with only 90,609 learnable parameters. We applied this method to experiments on the USGS National Petroleum Reserve-Alaska public dataset and the results indicate that our proposed approach achieved good reconstruction results. Additionally, our method also demonstrates a certain degree of noise suppression, which is highly beneficial for large and complex seismic exploration tasks.12 pages, 8 figure
Klein-Gordon and Schrödinger solutions in Lovelock quantum gravity
No full textThis study investigates the application of wave functions to explore various solutions of the Klein-Gordon and Schrödinger equations within the framework of Lovelock gravity. We also present the derived Smarr formula from the topological density. The Klein-Gordon solution leads to the Wheeler-de Witt Hamiltonian and quasinormal modes, and we demonstrate the connection between the potential and the black hole temperature within the Schwarzschild limit. Additionally, we discuss different solutions of the Schr% ödinger equation, with one solution highlighting the influence of the Airy solution on the wave function\u27s evolution over time.20 pages, 5 figure
Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning
No full textCurriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL finds popularity in deep learning research due to its promise of leveraging human-inspired curricula to achieve higher model performance. Yet, the subjectivity and biases that follow any necessary definition of difficulty, especially for those found in orderings derived from models or training statistics, have rarely been investigated. To shed more light on the underlying unanswered questions, we conduct an extensive study on the robustness and similarity of the most common scoring functions for sample difficulty estimation, as well as their potential benefits in CL, using the popular benchmark dataset CIFAR-10 and the acoustic scene classification task from the DCASE2020 challenge as representatives of computer vision and computer audition, respectively. We report a strong dependence of scoring functions on the training setting, including randomness, which can partly be mitigated through ensemble scoring. While we do not find a general advantage of CL over uniform sampling, we observe that the ordering in which data is presented for CL-based training plays an important role in model performance. Furthermore, we find that the robustness of scoring functions across random seeds positively correlates with CL performance. Finally, we uncover that models trained with different CL strategies complement each other by boosting predictive power through late fusion, likely due to differences in the learnt concepts. Alongside our findings, we release the aucurriculum toolkit (https://github.com/autrainer/aucurriculum), implementing sample difficulty and CL-based training in a modular fashion