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

6.2%12.4%18.6%24.7% · Feb 202619922001200920172026
48 results for nucleus sampling

We introduce a new sampling method for large language models that balances diversity and parallelism.

problem Balancing diversity and parallelism in decoding for large language models.
method Arithmetic sampling framework compatible with various sampling variations.
result Improves estimation of expected BLEU score reward and reduces the gap with beam search.

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some post-hoc fixes have been proposed, in particular top-kk and nucleus sampling, they …

2019-08-12abs ↗pdf ↗

Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success sho…

2018-06-29abs ↗pdf ↗

Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.

problem Decoding strategies exclude contextually appropriate but statistically rare tokens, creating a detectable gap in generated text.
method Analysis of 1.8 million texts across 8 language models, 5 decoding strategies, and 53 hyperparameter configurations.
result 8-18% of human-selected tokens fall outside typical truncation boundaries, indicating a detectable gap.

End-to-end audio recognition system improves accuracy.

problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.

With ongoing developments and innovations in single-cell RNA sequencing methods, advancements in sequencing performance could empower significant discoveries as well as new emerging possibilities to address biological and medical investigations. In the study, we will be using the dataset collected by the authors of Sys…

2019-12-18abs ↗pdf ↗

This work improved clustering methods by analyzing various datasets and dendrograms.

problem Avoiding false positives in clustering, especially for unimodal and bimodal data.
method Applied agglomerative clustering methods (single, average, median, complete, centroid, Ward's) to various datasets.
result Many methods detected two clusters in unimodal data, with single-linkage being more resilient.

Best performing nuclear segmentation methods are based on deep learning algorithms that require a large amount of annotated data. However, collecting annotations for nuclear segmentation is a very labor-intensive and time-consuming task. Thereby, providing a tool that can facilitate and speed up this procedure is very …

2019-09-07abs ↗pdf ↗

Adaptive contrastive search improves text generation quality and diversity.

problem Decoding high-quality text from language model outputs.
method Adaptive contrastive search incorporating uncertainty-guided degeneration penalty.
result Enhanced text generation quality and diversity across different models and datasets.

The region of heavy calcium isotopes forms the frontier of experimental and theoretical nuclear structure research where the basic concepts of nuclear physics are put to stringent test. The recent discovery of the extremely neutron-rich nuclei around 60^{60}Ca [Tarasov, 2018] and the experimental determination of masse…

2019-01-22abs ↗pdf ↗

Study limits of circadian synchronization under different light signals.

problem Disruption of circadian rhythms due to misalignment with external light signals.
method Matrix-free approach for locating periodic steady states, numerical continuation, bifurcation diagrams, unsupervised learning.
result Limits of circadian synchronization to external light signals of different frequency and duty cycle.

NucleusDiff models atomic nuclei interactions to prevent separation violations in drug design.

problem Maintaining minimum pairwise distance between atoms to avoid separation violations in drug design.
method Enforces distance constraint between atomic nuclei and manifolds in a diffusion model.
result Reduces separation violations by up to 100.00% and enhances binding affinity by up to 22.16%.

Mogami introduced in 1995 a large class of triangulated 3-dimensional pseudomanifolds, henceforth called "Mogami pseudomanifolds". He proved an exponential bound for the size of this class in terms of the number of tetrahedra. The question of whether all 3-balls are Mogami has remained open since, a positive answer wou…

2016-08-06abs ↗pdf ↗

A new sampler for FLMs improves token-level decoding controls.

problem Sampling from FLMs using standard methods collapses marginals and produces invalid sequences.
method Samples clean one-hot endpoints from FLM token marginals and uses Ornstein-Uhlenbeck bridges conditioned on these endpoints.
result The method preserves token-wise posterior-predictive marginals and improves quality-diversity tradeoff.

AI systems need reliable testing to ensure safety and trustworthiness.

problem Current AI Act lacks functional trustworthiness for AI systems.
method Define technical application distribution, set risk-based performance, and conduct statistically valid testing.
result Reliable functional trustworthiness is essential for AI systems.

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.

Adds a precortical module to CNNs for improved robustness to light variations.

problem Robustness of CNNs to global light intensity and contrast variations.
method Developed a mathematical model of the mammalian visual pathway, inspired by CNNs, and added a preliminary convolutional module.
result Significantly more robust CNNs achieved with added module on MNIST, FashionMNIST, and SVHN databases.

In the area of traditional physics the atomic nucleus belongs to the most complex systems. It involves essentially all elements that characterize complexity including the most distinctive one whose essence is a permanent coexistence of coherent patterns and of randomness. From a more interdisciplinary perspective, thes…

2010-09-06abs ↗pdf ↗

Proposes a Varying-Coefficient MoE model for analyzing dynamic data.

problem Inadequate constant coefficients in MoE models for dynamic settings.
method Varying-Coefficient Mixture of Experts (VCMoE) model with varying coefficients in gating and expert models.
result Established identifiability and consistency of the VCMoE model.

Deep learning classifies autism vs controls with high accuracy using large fMRI dataset.

problem Classification difficulty of autism vs typically developing controls with fMRI data.
method Ensemble CNN model trained on 43,858 fMRI datapoints, employing class-balancing and visualization methods.
result Deep learning models achieve AUROCs of 0.6774, 0.7680, and 0.9222 for ASD vs TD, gender, and task vs rest classifications.

Innocent musing on geodesics on the surface of helical pasta shapes leads to a single continuous 4-parameter family of surfaces invariant under at least a 1-parameter symmetry group and which contains as various limits spheres, tori, helical tubes, and cylinders, all useful for illustrating various aspects of geometry …

2014-02-13abs ↗pdf ↗

Deep object detection improves mitotic nucleus detection in breast cancer biopsies.

problem Challenges in automated mitotic nucleus detection in breast cancer histopathological images.
method Adapted Mask R-CNN for deep object detection, initially selects candidate regions with maximum recall, refines them with multi-object loss function.
result Improved discrimination ability (F-score of 0.86) and significant precision (0.86) for mitotic nuclei compared to two-stage models.

The paper constructs non-smoothable actions on spin 4-manifolds.

problem Non-smoothability of Z/p\mathbb{Z}/p-actions on indefinite spin 4-manifolds.
method Constructs examples of non-smoothable actions using equivariant κκ-invariants and calculations of ηη-invariants.
result Non-smoothable actions remain non-smoothable under certain stabilizations.

The chart of the nuclides is limited by particle drip lines beyond which nuclear stability to proton or neutron emission is lost. Predicting the range of particle-bound isotopes poses an appreciable challenge for nuclear theory as it involves extreme extrapolations of nuclear masses beyond the regions where experimenta…

2020-01-16abs ↗pdf ↗

The mass, or binding energy, is the basis property of the atomic nucleus. It determines its stability, and reaction and decay rates. Quantifying the nuclear binding is important for understanding the origin of elements in the universe. The astrophysical processes responsible for the nucleosynthesis in stars often take …

2018-06-01abs ↗pdf ↗

Improves TTS accuracy by correcting context-dependent units.

problem Improves text-to-speech accuracy through speaker adaptation.
method Statistical model predicting context-dependent phonetic unit classes and their mean error values.
result Corrected boundaries of units improve TTS accuracy compared to HMM segmentation.

Enhanced Sampling Scheme improves masked generative modeling.

problem Limitations of existing sampling schemes in masked non-autoregressive generative modeling.
method ESS consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling.
result ESS achieves significant performance gains in unconditional and class-conditional sampling.

This paper reviews various sampling methods from statistics and machine learning.

problem Addressing sampling methods in statistics and machine learning.
method Explains and reviews simple random sampling, bootstrapping, stratified sampling, cluster sampling, multistage sampling, network sampling, snowball sampling, and sampling from cumulative distribution function.
result Summarizes characteristics, pros, and cons of different sampling methods.

RISA improves VFL by using imputed samples with low uncertainty.

problem Limited overlapping samples constrain VFL performance.
method Imputing non-overlapping samples and using evidence theory to select reliable imputed samples.
result Significant performance gains achieved, especially with limited overlapping samples.

Improved privacy-preserving methods for estimating multiple samples from distributions.

problem Estimating multiple samples from distributions while maintaining privacy.
method Developed new multi-sampling techniques for differentially private data estimation.
result Achieved significant reduction in sample complexity for multi-sampling from finite domains and Gaussian distributions.

Paper introduces a new sampling method combining Consistency Models with importance sampling.

problem Inherent errors in samples and high NFEs for high-quality samples in Boltzmann distributions.
method Combines Consistency Models with importance sampling to produce unbiased samples with minimal NFEs.
result Produces unbiased samples using only 6-25 NFEs, comparable to 100 NFEs for DDPMs.

Neural network accuracy improves with denser training samples.

problem Improving neural network accuracy on unseen test samples.
method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.
result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.