Explore the vast range of titles available.

There is one thing I hold dear is the notion that narrative desire, in any circumstances, arises most strongly once historical erasure takes place, a local, personal reckoning naturally forming against the global, sweeping forces. After the American War in Vietnam, after generations lost to and were displaced by violence, the search for an identity in each individual becomes more sacred, symbolic and urgent, but as quiet as it can be. This critical essay is an amalgamation of autobiographical and critical writing on craft, survival, and language through a transnational lens informed by Vietnamese and Vietnamese American experiences. I look at the notion of mất gốc as a personal trauma and a generative space for craft. I look at the gaps and silences within the literary and historical canon. The works by Ocean Vuong, Nguyễn Phan Quế Mai, Aimee Phan are relevant here as they facilitate my inquiries into the queer, diasporic, and transnational magnitudes of Vietnamese and Vietnamese American narrative works. I imagine a future for a novel that resists the assimilationist gaze and places the fragmented, haunted lives of Vietnamese Amerasians at the center stage. Ultimately, I argue for a literature and storytelling as an embodied act that sees the \"art of staying afloat\" as craft.

A deep convolutional neural network has been developed to denoise atomic-resolution transmission electron microscope image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training the network. The proposed network outperforms state-of-the-art denoising methods on both simulated and experimental test data. Factors contributing to the performance are identified, including (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits both extended and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.

We present PyXtal_FF-a package based on Python programming language-for developing machine learning potentials (MLPs). The aim of PyXtal_FF is to promote the application of atomistic simulations through providing several choices of atom-centered descriptors and machine learning regressions in one platform. Based on the given choice of descriptors (including the atom-centered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal_FF can train MLPs with either generalized linear regression or neural network models, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from ab-initio simulations. The trained MLP model from PyXtal_FF is interfaced with the Atomic Simulation Environment (ASE) package, which allows different types of light-weight simulations such as geometry optimization, molecular dynamics simulation, and physical properties prediction. Finally, we will illustrate the performance of PyXtal_FF by applying it to investigate several material systems, including the bulk SiO2, high entropy alloy NbMoTaW, and elemental Pt for general purposes. Full documentation of PyXtal_FF is available at https://pyxtal-ff.readthedocs.io.

Despite significant advances in deep learning, probabilistic modeling of sequential data has remained challenging due to the interplay of high-dimensional inputs and temporal dynamics across long-distance time steps. In this dissertation, we propose deep probabilistic methods that model the temporal interactions between sequential inputs while accounting for the inherent uncertainty of future predictions. First, we study the problem of continual learning where samples of different classes arrive sequentially and incrementally, and propose a discriminative approach that uses random graphs to model sample similarities and guard against catastrophic forgetting. Second, we marry state space models with recent advances in deep learning architectures for the task of time series prediction, aiming to capture non-Markovian dynamics via latent variable models. Third, we extend such generative models to the challenging domain of videos in which both spatial and temporal signals are key to multi-frame video predictions. Empirical results show that our models perform competitively against recent baselines, bringing us one step closer to unlocking the underexplored potentials of sequential data.

We present PyXtal FF, a package based on Python programming language, for developing machine learning potentials (MLPs). The aim of PyXtal FF is to promote the application of atomistic simulations by providing several choices of structural descriptors and machine learning regressions in one platform. Based on the given choice of structural descriptors (including the atom-centered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal FF can train the MLPs with either the generalized linear regression or neural networks model, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from the ab-initio simulation. The trained MLP model from PyXtal FF is interfaced with the Atomic Simulation Environment (ASE) package, which allows different types of light-weight simulations such as geometry optimization, molecular dynamics simulation, and physical properties prediction. Finally, we will illustrate the performance of PyXtal FF by applying it to investigate several material systems, including the bulk SiO2, high entropy alloy NbMoTaW, and elemental Pt for general purposes. Full documentation of PyXtal FF is available at https://pyxtal-ff.readthedocs.io.

Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and replaying a small episodic memory of previous samples, often implemented as an array of independent memory slots. In this work, we propose to augment such an array with a learnable random graph that captures pairwise similarities between its samples, and use it not only to learn new tasks but also to guard against forgetting. Empirical results on several benchmark datasets show that our model consistently outperforms recently proposed baselines for task-free continual learning.

A deep convolutional neural network has been developed to denoise atomic-resolution TEM image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training and testing the network. The proposed network outperforms state-of-the-art denoising methods by a significant margin both on simulated and experimental test data. Factors contributing to the performance are identified, including most importantly (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits global and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.

The explosion of high-performing conversational language models (LMs) has spurred a shift from classic natural language processing (NLP) benchmarks to expensive, time-consuming and noisy human evaluations - yet the relationship between these two evaluation strategies remains hazy. In this paper, we conduct a large-scale study of four Chat Llama 2 models, comparing their performance on 160 standard NLP benchmarks (e.g., MMLU, ARC, BIG-Bench Hard) against extensive human preferences on more than 11k single-turn and 2k multi-turn dialogues from over 2k human annotators. Our findings are striking: most NLP benchmarks strongly correlate with human evaluations, suggesting that cheaper, automated metrics can serve as surprisingly reliable predictors of human preferences. Three human evaluations, such as adversarial dishonesty and safety, are anticorrelated with NLP benchmarks, while two are uncorrelated. Moreover, through overparameterized linear regressions, we show that NLP scores can accurately predict human evaluations across different model scales, offering a path to reduce costly human annotation without sacrificing rigor. Overall, our results affirm the continued value of classic benchmarks and illuminate how to harness them to anticipate real-world user satisfaction - pointing to how NLP benchmarks can be leveraged to meet evaluation needs of our new era of conversational AI.

We present a theory for the previously unexplained divergent behavior noticed in the training of large language models. We argue that the phenomenon is an artifact of the dominant optimization algorithm used for training, called Adam. We observe that Adam can enter a state in which the parameter update vector has a relatively large norm and is essentially uncorrelated with the direction of descent on the training loss landscape, leading to divergence. This artifact is more likely to be observed in the training of a deep model with a large batch size, which is the typical setting of large-scale language model training. To argue the theory, we present observations from the training runs of the language models of different scales: 7 billion, 30 billion, 65 billion, and 546 billion parameters.