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.
Paper establishes baselines for offline RL from visual observations.
Proposes Population Difference Criterion for visually observed subpopulation differences.
DPFRL uses particle filters for decision making with complex visual observations.
Neural model predicts object states and physical parameters from visual observations.
CVRL tackles complex visual observations in reinforcement learning.
Proposes MR-SNE for multimodal data visualization.
A framework disentangles controllable objects from visual signals for improved RL.
Helps visually impaired users make better decisions by adjusting their observations.
Algorithm improves imitation learning from visual data in partially observable environments.
In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …
The paper addresses bias in visual recognition models by reweighting observations.
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…
This research reverses feature visualization in neural networks to optimize for specific feature objectives.
This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying the document, thereby explaining the model's prediction. We successfully applied HAN to a sequential analysis task in the form of real-time m…
3D RadViz improves 3D data visualization of multidimensional datasets.
We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of causal learning to settings in which the causal variables need to be constructed …
MuZero visualizes its internal representations to stabilize planning.
A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened decision map and input samples is possible. We first provide a means of visually co…
New method helps interpret complex models by visualizing feature shifts.
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many triplet selection strategies for Metric Learning, we find that the best performance …
New RL environments help AI learn causal relationships from visual data.
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not always reflecting the underlying true ambiguity and hardness. In this paper, we propose angular visual hardness (AVH), a score given by the …
Few-shot visual reasoning model learns analogical relationships from small data.
Causal reasoning has been an indispensable capability for humans and other intelligent animals to interact with the physical world. In this work, we propose to endow an artificial agent with the capability of causal reasoning for completing goal-directed tasks. We develop learning-based approaches to inducing causal kn…
Paper develops a framework for generating coherent image captions using visual features and hierarchical topics.
Study evaluates interpretability of time series foundation models' latent spaces.
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…
Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex action sequences. In this work, we address the problem of learning an agent's action…
The paper corrects biases in estimating intrinsic dimension and differential entropy.
Clouds frequently cover the Earth's surface and pose an omnipresent challenge to optical Earth observation methods. The vast majority of remote sensing approaches either selectively choose single cloud-free observations or employ a pre-classification strategy to identify and mask cloudy pixels. We follow a different st…
A model predicts visual motion by learning from natural videos.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions. Visual observations of the effects of wind---the swaying of trees and flapping of flags, for example---encode information regarding local wind conditions that can pote…
This work proves the continuum limit of t-SNE for data visualization.
In a wide variety of situations, anomalies in the behaviour of a complex system, whose health is monitored through the observation of a random vector X = (X1,. .. , X d) valued in R d , correspond to the simultaneous occurrence of extreme values for certain subgroups {1,. .. , d} of variables Xj. Under th…
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …
Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversarial regularization (AdvReg) aims to address this issue via an adversary sub-network that encourages the main model to learn a bias-free repr…
Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by …
The paper offers a checklist for comparing human and machine visual perception.
Develops a two-stage approach for robust tensor completion of visual data.
Clinical researchers use disease progression models to understand patient status and characterize progression patterns from longitudinal health records. One approach for disease progression modeling is to describe patient status using a small number of states that represent distinctive distributions over a set of obser…
Study finds physical priors don't significantly improve ML models for learning latent dynamics.
In this paper we address the problem of tracking multiple speakers via the fusion of visual and auditory information. We propose to exploit the complementary nature of these two modalities in order to accurately estimate smooth trajectories of the tracked persons, to deal with the partial or total absence of one of the…
Yarbus' claim to decode the observer's task from eye movements has received mixed reactions. In this paper, we have supported the hypothesis that it is possible to decode the task. We conducted an exploratory analysis on the dataset by projecting features and data points into a scatter plot to visualize the nuance prop…
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.