English
Related papers

Related papers: Internal Guidance for Satallax

200 papers

When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD)…

Artificial Intelligence · Computer Science 2021-07-08 Ankit Shah , Pritish Kamath , Shen Li , Patrick Craven , Kevin Landers , Kevin Oden , Julie Shah

Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we…

Machine Learning · Computer Science 2026-04-07 Maria Chzhen , Priya L. Donti

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

Artificial Intelligence · Computer Science 2020-07-21 Teodora Popordanoska , Mohit Kumar , Stefano Teso

We introduce a theorem proving approach to the specification and generation of temporal logical constraints for training neural networks. We formalise a deep embedding of linear temporal logic over finite traces (LTL$_f$) and an associated…

Artificial Intelligence · Computer Science 2022-07-11 Mark Chevallier , Matthew Whyte , Jacques D. Fleuriot

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

Machine Learning · Computer Science 2026-04-22 Thomas Zollo , Jimmy Wang , Richard Zemel

We re-examine the topic of machine-learned clause selection guidance in saturation-based theorem provers. The central idea, recently popularized by the ENIGMA system, is to learn a classifier for recognizing clauses that appeared in…

Artificial Intelligence · Computer Science 2021-04-15 Martin Suda

In this work, we introduce NoiseQuery as a novel method for enhanced noise initialization in versatile goal-driven text-to-image (T2I) generation. Specifically, we propose to leverage an aligned Gaussian noise as implicit guidance to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Ruoyu Wang , Huayang Huang , Ye Zhu , Olga Russakovsky , Yu Wu

We are developing a general framework for using learned Bayesian models for decision-theoretic control of search and reasoningalgorithms. We illustrate the approach on the specific task of controlling both general and domain-specific…

Artificial Intelligence · Computer Science 2013-01-14 Eric J. Horvitz , Yongshao Ruan , Carla P. Gomes , Henry Kautz , Bart Selman , David Maxwell Chickering

We target the problem of accuracy and robustness in causal inference from finite data sets. Some state-of-the-art algorithms produce clear output complete with solid theoretical guarantees but are susceptible to propagating erroneous…

Artificial Intelligence · Computer Science 2012-10-19 Tom Claassen , Tom Heskes

We propose a general framework for reduced-rank modeling of matrix-valued data. By applying a generalized nuclear norm penalty we can directly model low-dimensional latent variables associated with rows and columns. Our framework flexibly…

Machine Learning · Statistics 2017-08-23 William Fithian , Rahul Mazumder

Estimating the distribution over failures is a key step in validating autonomous systems. Existing approaches focus on finding failures for a small range of initial conditions or make restrictive assumptions about the properties of the…

Robotics · Computer Science 2023-05-18 Harrison Delecki , Anthony Corso , Mykel J. Kochenderfer

This paper contributes to the area of inductive logic programming by presenting a new learning framework that allows the learning of weak constraints in Answer Set Programming (ASP). The framework, called Learning from Ordered Answer Sets,…

Artificial Intelligence · Computer Science 2020-02-19 Mark Law , Alessandra Russo , Krysia Broda

The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples…

Computation and Language · Computer Science 2023-05-19 Wangchunshu Zhou , Yuchen Eleanor Jiang , Ryan Cotterell , Mrinmaya Sachan

Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we…

We investigate the generalization properties of a self-training algorithm with halfspaces. The approach learns a list of halfspaces iteratively from labeled and unlabeled training data, in which each iteration consists of two steps:…

Machine Learning · Computer Science 2022-02-16 Lies Hadjadj , Massih-Reza Amini , Sana Louhichi , Alexis Deschamps

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We…

Machine Learning · Computer Science 2020-06-17 Aishwarya Sivaraman , Golnoosh Farnadi , Todd Millstein , Guy Van den Broeck

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Artificial Intelligence · Computer Science 2025-07-22 Nicolas Wischermann , Claudio Mayrink Verdun , Gabriel Poesia , Francesco Noseda

Classification aids software development activities by organizing requirements in classes for easier access and retrieval. The majority of requirements classification research has, so far, focused on binary or multi-class classification.…

Software Engineering · Computer Science 2025-04-24 Waleed Abdeen , Michael Unterkalmsteiner , Krzysztof Wnuk , Alexandros Chirtoglou , Christoph Schimanski , Heja Goli

We have designed a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates. Based on principles of…

Semi-supervised learning is a model training method that uses both labeled and unlabeled data. This paper proposes a fully Bayes semi-supervised learning algorithm that can be applied to any multi-category classification problem. We assume…

Machine Learning · Statistics 2024-07-22 Rui Zhu , Shuvrarghya Ghosh , Subhashis Ghosal
‹ Prev 1 4 5 6 7 8 10 Next ›