Skip to main content

Showing 1–8 of 8 results for author: McCallum, S

Searching in archive cs. Search in all archives.
.
  1. arXiv:2510.11307  [pdf, ps, other

    cs.CL cs.AI

    FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks

    Authors: Sabrina McCallum, Amit Parekh, Alessandro Suglia

    Abstract: Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. Th… ▽ More

    Submitted 13 October, 2025; originally announced October 2025.

    Comments: EMNLP 2025 Findings

  2. arXiv:2510.00043  [pdf, ps, other

    cs.LG cs.CL math.NT

    Linear Regression in p-adic metric spaces

    Authors: Gregory D. Baker, Scott McCallum, Dirk Pattinson

    Abstract: Many real-world machine learning problems involve inherently hierarchical data, yet traditional approaches rely on Euclidean metrics that fail to capture the discrete, branching nature of hierarchical relationships. We present a theoretical foundation for machine learning in p-adic metric spaces, which naturally respect hierarchical structure. Our main result proves that an n-dimensional plane min… ▽ More

    Submitted 27 September, 2025; originally announced October 2025.

    MSC Class: 11D88; 62J99; 68T50 ACM Class: G.3; I.2.6; I.2.7; I.5.1; I.5.4

    Journal ref: p-Adic Numbers, Ultrametric Analysis and Applications, volume 17(4), 2025

  3. arXiv:2509.12917  [pdf, ps, other

    cs.LG stat.ML

    Reversible Deep Equilibrium Models

    Authors: Sam McCallum, Kamran Arora, James Foster

    Abstract: Deep Equilibrium Models (DEQs) are an interesting class of implicit model where the model output is implicitly defined as the fixed point of a learned function. These models have been shown to outperform explicit (fixed-depth) models in large-scale tasks by trading many deep layers for a single layer that is iterated many times. However, gradient calculation through DEQs is approximate. This often… ▽ More

    Submitted 3 December, 2025; v1 submitted 16 September, 2025; originally announced September 2025.

  4. arXiv:2410.11648  [pdf, other

    cs.LG stat.ML

    Efficient, Accurate and Stable Gradients for Neural ODEs

    Authors: Sam McCallum, James Foster

    Abstract: Training Neural ODEs requires backpropagating through an ODE solve. The state-of-the-art backpropagation method is recursive checkpointing that balances recomputation with memory cost. Here, we introduce a class of algebraically reversible ODE solvers that significantly improve upon both the time and memory cost of recursive checkpointing. The reversible solvers presented calculate exact gradients… ▽ More

    Submitted 29 January, 2025; v1 submitted 15 October, 2024; originally announced October 2024.

    Comments: Preprint

  5. Iterated Resultants and Rational Functions in Real Quantifier Elimination

    Authors: James H. Davenport, Matthew England, Scott McCallum, Ali K. Uncu

    Abstract: This paper builds and extends on the authors' previous work related to the algorithmic tool, Cylindrical Algebraic Decomposition (CAD), and one of its core applications, Real Quantifier Elimination (QE). These topics are at the heart of symbolic computation and were first implemented in computer algebra systems decades ago, but have recently received renewed interest as part of the ongoing develop… ▽ More

    Submitted 26 December, 2024; v1 submitted 23 December, 2023; originally announced December 2023.

    Comments: Submitted to Mathematics in Computer Science

    MSC Class: 14W30 (primary) 68W30 (secondary) ACM Class: I.1.2

    Journal ref: Mathematics in Computer Science, volume 19, article number 12, Springer, 2025

  6. arXiv:2312.04736  [pdf, other

    cs.CL cs.AI

    Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning

    Authors: Sabrina McCallum, Max Taylor-Davies, Stefano V. Albrecht, Alessandro Suglia

    Abstract: Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the envi… ▽ More

    Submitted 7 December, 2023; originally announced December 2023.

    Comments: Accepted at Workshop on Goal-conditioned Reinforcement Learning, NeurIPS 2023

  7. Truth Table Invariant Cylindrical Algebraic Decomposition

    Authors: Russell Bradford, James H. Davenport, Matthew England, Scott McCallum, David Wilson

    Abstract: When using cylindrical algebraic decomposition (CAD) to solve a problem with respect to a set of polynomials, it is likely not the signs of those polynomials that are of paramount importance but rather the truth values of certain quantifier free formulae involving them. This observation motivates our article and definition of a Truth Table Invariant CAD (TTICAD). In ISSAC 2013 the current author… ▽ More

    Submitted 13 November, 2015; v1 submitted 3 January, 2014; originally announced January 2014.

    Comments: 40 pages

    MSC Class: 68W30; 03C10 ACM Class: I.1.2

    Journal ref: Journal of Symbolic Computation 76, pp. 1-35, 2016

  8. Cylindrical Algebraic Decompositions for Boolean Combinations

    Authors: Russell Bradford, James H. Davenport, Matthew England, Scott McCallum, David Wilson

    Abstract: This article makes the key observation that when using cylindrical algebraic decomposition (CAD) to solve a problem with respect to a set of polynomials, it is not always the signs of those polynomials that are of paramount importance but rather the truth values of certain quantifier free formulae involving them. This motivates our definition of a Truth Table Invariant CAD (TTICAD). We generalise… ▽ More

    Submitted 29 April, 2013; originally announced April 2013.

    Comments: To appear in the proceedings of the 38th International Symposium on Symbolic and Algebraic Computation (ISSAC '13)

    MSC Class: 68W30; 03C10 ACM Class: I.1.2

    Journal ref: In: Proceedings of the 38th International Symposium on Symbolic and Algebraic Computation, (ISSAC '13), pp 125-132, 2013