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.
Survey of software developers' experience with Github Copilot tool.
LATM framework uses LLMs to create and reuse tools for efficient problem-solving.
We propose a tool-use model that can detect the features of tools, target objects, and actions from the provided effects of object manipulation. We construct a model that enables robots to manipulate objects with tools, using infant learning as a concept. To realize this, we train sensory-motor data recorded during a t…
New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.
Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and thus properly grasping and manipulating the tool to achieve the task. Task-agnostic grasping optimizes for grasp robustness while ignoring crucial task-specific constrain…
In this paper we explore the richness of information captured by the latent space of a vision-based generative model. The model combines unsupervised generative learning with a task-based performance predictor to learn and to exploit task-relevant object affordances given visual observations from a reaching task, invol…
Homological stability aids in computing group homology.
Generative tools mimic stock market traders using synthetic data.
We examined the use of three conventional anomaly detection methods and assess their potential for on-line tool wear monitoring. Through efficient data processing and transformation of the algorithm proposed here, in a real-time environment, these methods were tested for fast evaluation of cutting tools on CNC machines…
We derive generalization error bounds for traditional time-series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space models. These non-asymptotic bounds need only weak assumptions on the data-generating…
Machine learning-based lithography hotspot detection has been deeply studied recently, from varies feature extraction techniques to efficient learning models. It has been observed that such machine learning-based frameworks are providing satisfactory metal layer hotspot prediction results on known public metal layer be…
Exact Bayesian inference for discrete models using probability generating functions.
Recent work has shown that Field-Programmable Gate Arrays (FPGAs) play an important role in the acceleration of Machine Learning applications. Initial specification of machine learning applications are often done using a high-level Python-oriented framework such as Tensorflow, followed by a manual translation to either…
One of the open challenges in designing robots that operate successfully in the unpredictable human environment is how to make them able to predict what actions they can perform on objects, and what their effects will be, i.e., the ability to perceive object affordances. Since modeling all the possible world interactio…
UniFeat is an open-source Java tool for feature selection.
A study ranks critical Lean Six Sigma tools for implementation in Portuguese companies.
Deep generative models are universal tools for learning data distributions on high dimensional data spaces via a mapping to lower dimensional latent spaces. We provide a study of latent space geometries and extend and build upon previous results on Riemannian metrics. We show how a class of heuristic measures gives mor…
AD-HOC simplifies high-order derivative calculations in C++.
Develops a tool to identify abnormal blood smear results based on CBC tests.
Interactive tool helps RL researchers debug and understand their models.
Deep learning generalizes well despite being overparameterized.
Tool for contracting subcurves of hyperelliptic curves, proving differential implications.
Survey of tools for studying hierarchical hyperbolic spaces.
This master's thesis discusses an important issue regarding how algorithmic decision making (ADM) is used in crime forecasting. In America forecasting tools are widely used by judiciary systems for making decisions about risk offenders based on criminal justice for risk offenders. By making use of such tools, the judic…
New tool: relative Hopf invariant for Poincaré surgery.
We study the geometry of complete generic Ricci solitons with the aid of some geometric-analytical tools extending techniques of the usual Riemannian setting.
ToolChain-CRC addresses the risk-control problem for retrieval-augmented and tool-using agents under drift.
New methods improve tool-to-tool matching in semiconductor manufacturing.
Algorithm performance in supervised learning is a combination of memorization, generalization, and luck. By estimating how much information an algorithm can memorize from a dataset, we can set a lower bound on the amount of performance due to other factors such as generalization and luck. With this goal in mind, we int…
Paper introduces ML tools for guided wave behaviour in composite materials.
State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes. In addition to performing straightforward dictionary attacks, these tools can expand password dictionaries using password generation rules, such as concatenation…
We offer a graphical interpretation of unfairness in a dataset as the presence of an unfair causal path in the causal Bayesian network representing the data-generation mechanism. We use this viewpoint to revisit the recent debate surrounding the COMPAS pretrial risk assessment tool and, more generally, to point out tha…
Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In thi…
In this paper, we present the principal components of an economic scenario generator (ESG), both for the theoretical design and for practical implementation. The choice of these components should be linked to the ultimate vocation of the economic scenario generator, which can be either a tool for pricing financial prod…
Generalizes tools for studying collapsed manifolds to new geometry.
The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as images or sounds. In this work we investigate the possibility of learning the prior distribution over neural network parameters using such tools. Our resulting variational Bayes algorithm …
In manufacture, steel and other metals are mainly cut and shaped during the fabrication process by computer numerical control (CNC) machines. To keep high productivity and efficiency of the fabrication process, engineers need to monitor the real-time process of CNC machines, and the lifetime management of machine tools…
TIR expands LLM capabilities by enabling problem-solving strategies.
We consider the future causal boundary as a tool to find obstructions to conformal extensions, the latter being a slight generalization to conformal compactifications.
Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called "privacy amplification by subsampling" principle, which ensures that a differentially private mechanism run on a random subsample of a population provides higher privacy guaran…
New L0 norm added to TDA for market analysis.
Interview study reveals considerations for designing semi-automated bias detection tools.
We study vector fields generating a local flow by automorphisms of a parabolic geometry with higher order fixed points. We develop general tools extending the techniques of [1], [2], and [3]. We apply these tools to almost Grassmannian, almost quaternionic, and contact parabolic geometries, including CR structures, to …
This work proves generalization bounds for neural networks without Lipschitz assumptions.
Visualizes deep generative models for drug design.
Scalable tools for nested optimization in deep learning.
We introduce a notion of probabilistic convexity and generalize some classical globalization theorems in Alexandrov geometry. A weighted Alexandrov's lemma is developed as a basic tool.
New tools quantify deep generative models' performance.