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.

169,341 papers · 148 categories

Trend · papers per month

18375573 · Jun 202019922001200920182026
48 results for face recall

Universal adversarial patches prevent face detection in various frameworks.

problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.

This paper introduces a new method to train normalizing flows using precision-recall divergences.

problem Training generative models with mode dropping and low-quality samples.
method Introduces PR-divergences and proposes a novel generative model to minimize precision-recall trade-offs.
result Normalizing flows can be trained to achieve specific precision-recall trade-offs using PR-divergences.

Revises precision-recall curves for generative models.

problem Improves evaluation of generative models by distinguishing mode-collapse and quality issues.
method Generalizes PR curve formulation to arbitrary measures, exposes a bridge to error rates, proposes a new algorithm to approximate precision-recall curves.
result Demonstrates the interest of the new formulation over the original approach on multi-modal datasets.

Recommender system improves recall of omitted foods in online dietary surveys.

problem Improving accuracy of online dietary assessment surveys through recall assistance.
method Developed a recommender algorithm to remind respondents of omitted foods based on past survey data.
result The recommender system captures more omitted foods than hand-coded prompts, but with lower precision.

The study formalizes temporal precision and recall for anomaly detection in sequences.

problem Insufficient understanding of precision and recall in sequential anomaly detection.
method Formalized temporal precision and recall measures, developed time-tolerant confusion matrices, and demonstrated statistical significance.
result Precision and recall may overestimate performance with temporal tolerance.

This paper proposes neural network-based undersampling techniques to improve model performance on class-imbalanced datasets.

problem Class imbalance problem in machine learning models leads to biased predictions and lower performance metrics.
method Neural network-based undersampling techniques applied to class-imbalanced datasets.
result Neural network-based undersampling outperforms other resampling techniques in terms of AUC, F1, and G-mean scores.

Transformers can store facts efficiently using associative memories.

problem Understanding how transformers store and recall factual information.
method Proved linear scaling of storage capacities for linear and MLP associative memories, introduced a synthetic task, and analyzed gradient flow.
result Shallow transformers can achieve near optimal storage capacity for factual recall tasks using associative memories.

Paper tackles imbalanced binary classification by optimizing precision and recall directly.

problem Imbalanced binary classification where standard accuracy is misleading.
method Exact constrained reformulations for precision and recall optimization.
result ERO framework outperforms state-of-the-art methods on multiple datasets.

LLMs can memorize economic data and recall exact values before their training cutoff.

problem Evaluating the trustworthiness of LLMs' economic forecasts during their training period.
method Demonstrated through counterfactual forecasting and analysis of LLMs' recall ability.
result LLMs have memorized economic and financial data, leading to recall-level accuracy before their knowledge cutoff.

RAGuard improves safety in LLMs for offshore wind maintenance.

problem Conventional LLMs fail with specialised or unexpected scenarios in offshore wind maintenance.
method Integrates safety-critical documents alongside technical manuals in RAG framework.
result RAGuard increases safety recall from almost 0% to over 50% while maintaining technical recall above 60%.

Paper proposes a human-algorithm approach to reduce medical device recall risk and workload.

problem High recall rate and regulatory workload in FDA's 510(k) pathway.
method Developed machine learning models to estimate recall risk and proposed a data-driven clearance policy.
result Conservative evaluation of policy shows a 32.9% improvement in recall rate and 40.5% reduction in workload.

Framework for precise recall control in spatial conflation tasks.

problem Precise recall control in large-scale spatial conflation tasks to avoid downstream analytics failures and excessive manual review.
method End-to-end framework using equigrid bounding-box filter, CSR representation, neural ranker, and inverse-variance weighted ensemble of threshold estimators.
result Achieves exact recall with sub-percent variance over tens of millions of geometry pairs, runs on a single TPU v3 core.

A new method for generating replay samples on the fly, optimizing for not forgetting.

problem Addressing the issue of forgetting in neural networks.
method Generates auxiliary samples on the fly using the model's implicit memory, specialized to each real training batch.
result Optimizing for not forgetting leads to more efficient and scalable generation of specialized samples.

Generative memory model avoids vanishing gradients to robustly retrieve patterns.

problem Robust retrieval of stored patterns in the presence of interference and noise.
method Training a generative distributed memory without explicitly simulating attractor dynamics, using a likelihood-based Lyapunov function.
result The model converges to correct patterns upon iterative retrieval and achieves competitive performance as a memory model and a generative model.

The paper critiques and expands on common evaluation metrics in machine learning.

problem The common evaluation metrics like Precision, Recall, F-Measure, and Rand Accuracy are biased and misleading.
method The paper introduces new measures like Informedness, Markedness, and Correlation to better reflect the quality of predictions.
result A system that performs worse in terms of Informedness can appear better using common measures like Precision and Recall.

Paper introduces a new evaluation framework for generative models using Rényi divergences.

problem Lack of tools to diagnose and assess generative models' performance.
method Develops a general evaluation framework using Rényi divergences to measure precision and recall.
result Extends existing techniques to continuous and discrete models with efficient algorithms.

New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.

problem Limitations of purely memorized models in recalling large amounts of factual information.
method Demonstrated the benefits of in-tool learning (external retrieval) over in-weight learning (memorization) for factual recall.
result Proved that tool-use enables unbounded factual recall via a simple and efficient circuit construction.

The optimal ranking score between precision and recall is rarely F1 and can be found using specific methods.

problem Finding a meaningful and optimal compromise between precision and recall scores.
method Established a shortest path between precision- and recall-induced rankings, framed the problem as an optimization problem, and provided theoretical tools to find the optimal β.
result F1 and its skew-insensitive version are not optimal tradeoffs between precision and recall scores.

DIAL learns embeddings to maximize recall and accuracy for entity resolution.

problem Low resource settings for entity resolution with large Cartesian product search space.
method DIAL uses an Index-By-Committee framework with pre-trained transformer language models to jointly learn embeddings for recall and accuracy.
result DIAL achieves high precision, recall, and efficiency on benchmark datasets.

Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.

problem Challenges in interpreting neural network decisions and learning in intermediate layers due to opacity and shared interactions.
method Proposes A-CAV to increase effectiveness and employs Gram-Schmidt process to improve robustness.
result Significant improvement in recall rate of concept images from 18.35% to 76.83% for VGG16, with reduced variance in recall across different random seeds.

Transformers recall from long distributions with statistical guarantees.

problem Designing Transformers that can recall from arbitrarily long, distributional contexts.
method Recast associative memory as probability measures, decomposing the task into recall and prediction.
result A shallow measure-theoretic Transformer learns the recall-and-predict map under spectral assumptions.

A new precision-recall method for evaluating generative models.

problem Lack of metrics distinguishing between different failure cases of generative models.
method Proposes a novel definition of precision and recall for distributions, disentangling divergence into two dimensions.
result Demonstrates the proposed metric can distinguish between quality of generated samples and coverage of the target distribution.

GeNet classifies metagenomic sequences with less memory and comparable recall to state-of-the-art methods.

problem Classifying metagenomic sequences from raw DNA sequences.
method Exploits hierarchical structure between labels for training, using deep representations.
result GeNet achieves competitive precision and good recall with less memory requirements.

LLMs can be tricked into recalling facts based on context clues.

problem Manipulation of LLMs' factual recall through context changes.
method Mathematical exploration of transformers' associative memory properties.
result Transformers use self-attention and value matrix for associative memory.

Unified framework for sequence models using test-time regression.

problem Designing efficient sequence models with associative memory.
method Formalizing associative recall as regression over input tokens, deriving various sequence models.
result Clarifies the effectiveness of query-key normalization in softmax attention and offers new generalizations.

KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.

problem Linear attention's poor performance on associative recall tasks.
method Formulates attention recall as a spherical-packing problem and introduces Kernelized Linear Attention Activations (KATA).
result KATA features offer a favorable capacity-interference tradeoff, enabling efficient associative recall.

Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.

problem Impersonation attacks using master faces for face-based identity authentication.
method Evolutionary algorithm in latent space of StyleGAN, neural network to direct search, 2D and 3D face reconstruction.
result Obtains high impersonation rates with fewer master faces for 2D and 3D face verification.

Face recognition systems are vulnerable to composite face reconstruction attacks.

problem Vulnerability of face recognition systems to composite face reconstruction attacks.
method Assumed attacker uses composite face parts to reconstruct faces faster and more efficiently.
result Current face recognition systems are extremely vulnerable to random search attacks.

We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents' beliefs are formed. They do so by making rational inferences about their observations which include a sequence of independ…

2015-09-30abs ↗pdf ↗

Study improves detection of cryptocurrency pump-and-dump schemes.

problem Class imbalance in P&D detection due to rare events.
method Synthetic Minority Oversampling Technique (SMOTE) and ensemble learning models.
result XGBoost and LightGBM achieved high recall rates (94.87% and 93.59%) with strong F1-scores.