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.
Program synthesis struggles with complex spatial relationships in image classification.
Few-shot visual reasoning model learns analogical relationships from small data.
ARNe model excels in abstract visual reasoning tasks.
MXGNet tackles visual reasoning tasks using graph neural networks.
A new method learns object hierarchies from images to reason about physical interactions.
We focus on two supervised visual reasoning tasks whose labels encode a semantic relational rule between two or more objects in an image: the MNIST Parity task and the colorized Pentomino task. The objects in the images undergo random translation, scaling, rotation and coloring transformations. Thus these tasks involve…
A framework isolates VQA reasoning from perception for better model evaluation.
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing t…
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated w…
VCML learns concepts and metaconcepts from images and questions.
Improved few-shot visual reasoning with image preprocessing.
Constellation learns group-level visual relationships for abstract reasoning.
Enhances statistical inference using synthetic data.
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - an…
Neural model predicts object states and physical parameters from visual observations.
DP synthetic data may inflate statistical test results, caution advised.
We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions …
More than 50 years ago Bongard introduced 100 visual concept learning problems as a testbed for intelligent vision systems. These problems are now known as Bongard problems. Although they are well known in the cognitive science and AI communities only moderate progress has been made towards building systems that can so…
Agent learns causal relationships from visual data to perform tasks.
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
Proposes a fuzzy rule-based method for data visualization.
Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications. First, GANs may generate more labeled training data, which may help improve classification accuracy. Second, in scenarios where real data cannot be release…
This paper proposes a web-based visual graph analytics platform for interactive graph mining, visualization, and real-time exploration of networks. GraphVis is fast, intuitive, and flexible, combining interactive visualizations with analytic techniques to reveal important patterns and insights for sense making, reasoni…
With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images. To gain a better understanding of how a disease impacts the brain, the studies visualize the salience maps of the ConvNet highlighting voxels within the brain major…
One aim of data mining is the identification of interesting structures in data. For better analytical results, the basic properties of an empirical distribution, such as skewness and eventual clipping, i.e. hard limits in value ranges, need to be assessed. Of particular interest is the question of whether the data orig…
Optimizes cover parameter in Mapper algorithm for better visualization.
Agent Trading Arena trains LLMs in real-time financial markets to improve numerical reasoning.
Visual analytics systems combine machine learning or other analytic techniques with interactive data visualization to promote sensemaking and analytical reasoning. It is through such techniques that people can make sense of large, complex data. While progress has been made, the tactful combination of machine learning a…
Synthetic construction of Hopf fibration in 4D space.
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-d…
A novel method for visual question answering using scene graphs and reinforcement learning.
Visualizes deep neural networks for speech recognition using learned topographic filter maps.
SHAP Distance assesses semantic fidelity of synthetic tabular data.
Generates realistic time-series data from causal models.
DPFRL uses particle filters for decision making with complex visual observations.
It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing pr…
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
DAISYnt evaluates synthetic data quality and privacy in regulated domains.
SATNet solves the Symbol Grounding Problem, enabling self-supervised learning.
In many contexts, it can be useful for domain experts to understand to what extent predictions made by a machine learning model can be trusted. In particular, estimates of trustworthiness can be useful for fraud analysts who process machine learning-generated alerts of fraudulent transactions. In this work, we present …
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
Explains curves and surfaces in differential geometry.
The paper offers a checklist for comparing human and machine visual perception.
Proposes QQE for transforming and embedding data distributions.
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based reasoning by modelling it as a continuous dynamical system using neural ordinary…
The paper proposes a framework to reason about object dynamics for faster reinforcement learning.