Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

16324864 · Sep 201919922001200920172026
48 results for text infilling

Recent years have seen remarkable progress of text generation in different contexts, such as the most common setting of generating text from scratch, and the emerging paradigm of retrieval-and-rewriting. Text infilling, which fills missing text portions of a sentence or paragraph, is also of numerous use in real life, …

2019-01-01abs ↗pdf ↗

ICP improves text infilling and POS tagging with valid confidence sets.

problem Statistical reliability of machine learning predictions.
method Inductive conformal prediction algorithms for text infilling and POS tagging.
result Valid set-valued predictions with small size for real-world applications.

Physical systems are modelled and investigated within simulation software in an increasing range of applications. In reality an investigation of the system is often performed by empirical test scenarios which are related to typical situations. Our aim is to derive a method which generates diverse test scenarios each re…

2018-10-04abs ↗pdf ↗

Model infers mineral locations from geospatial data, improving predictions with auxiliary data.

problem Challenges in characterizing hidden mineral deposits underground.
method Generative modeling approach using masked and infilled geospatial maps.
result Models achieve Dice coefficients of 0.31 and recalls of 0.22 at 1×1 mi² resolution.

Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.

problem Efficiently optimize expensive engineering and scientific problems with limited data.
method Unified framework linking Bayesian infill criteria and active learning criteria.
result Unified approach formalizes Bayesian infill criteria and active learning criteria.

A new method for high-dimensional Bayesian optimization.

problem Challenges in extending BO to high dimensions.
method Expected Coordinate Improvement (ECI) criterion for high-dimensional Bayesian optimization.
result Significantly better results than standard BO and competitive results with state-of-the-art methods.

Study improves accuracy of weather data for real-time building simulations.

problem Anomalous and missing weather data affect real-time building energy simulations.
method Introduces a framework for quality control of measured weather data using anomaly detection and neural network infilling.
result Neural Networks enhance the accuracy of data imputation compared to traditional methods.

New method boosts performance of diffusion models on discrete data like natural language.

problem Performance of diffusion models on discrete data like natural language is poor.
method Proposes score entropy, a novel loss that extends score matching to discrete spaces.
result Significantly boosts performance on language modeling tasks.

We use SMC with twist functions to improve probabilistic inference in LLMs.

problem Improving probabilistic inference in large language models.
method We use Sequential Monte Carlo with learned twist functions to estimate expected future values and focus inference on promising sequences.
result Twisted SMC improves the accuracy of language model inference and evaluation.

Paper introduces TtT, market-implied transition time, from greenium term structure.

problem Estimating market-implied transition time to a low-carbon economy.
method Develops inference theory for TtT, introduces two stochastic models.
result Combines two-layer analysis for consistent estimation of diffusion parameters.

Bayesian Optimization tackles hidden constraints in architecture optimization.

problem Optimizing system architectures with hidden constraints using expensive physics-based simulations.
method Surrogate-based optimization with Gaussian Process models, including strategies for handling failed evaluations.
result Best performance achieved with a mixed-discrete GP predicting Probability of Viability (PoV) and minimum PoV threshold selection.

Scalarizing functions have been widely used to convert a multiobjective optimization problem into a single objective optimization problem. However, their use in solving (computationally) expensive multi- and many-objective optimization problems in Bayesian multiobjective optimization is scarce. Scalarizing functions ca…

2019-04-11abs ↗pdf ↗

Diffusion models generate music sequences without autoregressive loops.

problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.

Sparse Gaussian process quantile regression tackles computational challenges in Bayesian quantile regression.

problem Nonconjugacy and computational cost in Gaussian process quantile regression.
method Sparse Gaussian process framework with Laplace approximation, adaptive inducing-input placement, and sequential data acquisition.
result Accuracy of Laplace approximation and effectiveness of adaptive mechanisms in reducing predictive uncertainty.

A scalable portfolio approach speeds up Bayesian optimization for noisy functions.

problem Efficiently selecting multiple designs in parallel for noisy, expensive black-box optimization.
method A portfolio approach that balances exploration and exploitation, using a scalable allocation strategy.
result Significant speed improvements over existing methods, with similar or better performance.

Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…

2019-06-17abs ↗pdf ↗

The paper classifies actions of a specific group on certain manifolds.

problem Classifying analytic actions of a specific semi-orthogonal group on manifolds.
method Adapting Uchida's construction, the paper explicitly constructs actions on specific manifolds and demonstrates that any action is covered by these.
result Any analytic action of the semi-orthogonal group on a closed, connected manifold is covered by the constructed actions.

The paper solves the Nielsen realization problem for high degree del Pezzo surfaces.

problem Which finite subgroups of the mapping class group of a del Pezzo surface lift to the diffeomorphism group?
method Classification and partial answers for d7d \geq 7, equivariant connected sum for d=6d = 6.
result Complete classification for d7d \geq 7, partial answer for d=6d = 6.

A new text representation model combines CNN and VAE for better semantic extraction.

problem Difficult to effectively extract semantic features and distinguish polysemy in text data.
method Integrates CNN for feature extraction and VAE for consistent Gaussian distribution.
result The model outperforms traditional classification algorithms in text classification tasks.

We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic nonconvex optimization. At the core of the proposed algorithms is One-epoch-SNVRG+\text{One-epoch-SNVRG}^+ using stochastic nested variance reduction (Zhou et al., 2018a), which outperforms the s…

2018-06-22abs ↗pdf ↗

Improved text summarization using belief propagation on weighted bipartite graphs.

problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.

Let Man\text{Man}_{*} denote the category of closed, connected, oriented and based 33-manifolds, with basepoint preserving diffeomorphisms between them. Juhász, Thurston and Zemke showed that the Heegaard Floer invariants are natural with respect to diffeomorphisms, in the sense that there are functors $HF^{\circ}: \te…

2019-08-17abs ↗pdf ↗

Paper generates diverse, readable adversarial texts from scratch.

problem Text classification models are easily fooled by adversarial examples.
method Trained a conditional variational autoencoder (VAE) with adversarial loss and utilized GANs to generate consistent adversarial texts.
result Successfully generates adversarial texts with higher success rate and acceptable quality.

The paper studies symplectic structures on character varieties of Sasakian threefolds.

problem Character varieties of Sasakian threefolds and their symplectic structures.
method Constructing a natural algebraic 2-form and showing its properties.
result The restriction of the 2-form to the space of irreducible SU(r) homomorphisms is symplectic.

Most of the information is stored as text, so text mining is regarded as having high commercial potential. Aiming at the semantic constraint problem of classification methods based on sparse representation, we propose a weighted recurrent neural network (W-RNN), which can fully extract text serialization semantic infor…

2019-09-28abs ↗pdf ↗

Joyce showed that for a classical knot KK, the involutory medial quandle IMQ(K)\text{IMQ}(K) is isomorphic to the core quandle of the homology group H1(X2)H_1(X_2), where X2X_2 is the cyclic double cover of S3\mathbb S ^3, branched over KK. It follows that IMQ(K)=detK|\text{IMQ}(K)| = | \det K |. In the present paper, the extension o…

2019-02-27abs ↗pdf ↗

Convolutional neural network improves assertion detection in multi-label clinical text.

problem Detecting assertions in multi-label clinical text with rich descriptions.
method Developed a CNN architecture for multi-label scope detection.
result At least 12% improvement over state-of-the-art on multi-label clinical text.

Proposes a flexible neural recommendation framework for better prediction performance.

problem Data sparsity, cold start problem, and long-tail distribution in recommendations.
method A modular neural recommendation framework that includes a neural collaborative filtering part and a text processing part as a regularizer.
result Achieves better prediction performance than state-of-the-art text-aware methods using a simple text processing approach.

Let G(n)\text{G}(n) be equal either to PO(n,1),PU(n,1)\text{PO}(n,1),\text{PU}(n,1) or PSp(n,1)\text{PSp}(n,1) and let ΓG(n)Γ\leq \text{G}(n) be a uniform lattice. Denote by HKn\mathbb{H}^n_K the hyperbolic space associated to G(n)\text{G}(n), where KK is a division algebra over the reals of dimension d=dimRKd=\dim_{\mathbb{R}} K. Assume $d(n-1) \ge…

2019-09-17abs ↗pdf ↗

Traditionally, text generation models take in a sequence of text as input, and iteratively generate the next most probable word using pre-trained parameters. In this work, we propose the architecture to use images instead of text as the input of the text generation model, called StoryGen. In the architecture, we design…

2020-01-16abs ↗pdf ↗

MoleculeSTM learns from molecule structures and texts for better drug design.

problem Lack of integration between chemical structures and textual knowledge in AI drug discovery.
method Jointly learns chemical structures and texts via contrastive learning, using a large dataset.
result MoleculeSTM achieves state-of-the-art performance in zero-shot tasks like structure-text retrieval and molecule editing.