English
Related papers

Related papers: Equivalence of eval-readback and eval-apply big-st…

200 papers

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to…

Machine Learning · Computer Science 2023-05-01 Mastane Achab , Reda Alami , Yasser Abdelaziz Dahou Djilali , Kirill Fedyanin , Eric Moulines

Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pipeline requires resolving incompatible dependencies, matching underspecified evaluation…

Artificial Intelligence · Computer Science 2026-04-20 Suhwan Choi , Yunsung Lee , Yubeen Park , Chris Dongjoo Kim , Ranjay Krishna , Dieter Fox , Youngjae Yu

Semiconductor companies have increasingly adopted a methodology that starts with a system-level design specification in C/C++/SystemC. This model is extensively simulated to ensure correct functionality and performance. Later, a Register…

Software Engineering · Computer Science 2016-09-02 Rajdeep Mukherjee , Saurabh Joshi , Andreas Griesmayer , Daniel Kroening , Tom Melham

Push/enter and eval/apply are two calling conventions used in implementations of functional languages. In this paper, we explore the following observation: when considering functions with multiple arguments, the stack under the push/enter…

Programming Languages · Computer Science 2016-06-22 Maciej Piróg , Jeremy Gibbons

Recently, the scientific community has questioned the statistical reproducibility of many empirical results, especially in the field of machine learning. To contribute to the resolution of this reproducibility crisis, we propose a…

Calculi with control operators have been studied to reason about control in programming languages and to interpret the computational content of classical proofs. To make these calculi into a real programming language, one should also…

Logic in Computer Science · Computer Science 2012-10-12 Robbert Krebbers

Even though deep neural networks succeed on many different tasks including semantic segmentation, they lack on robustness against adversarial examples. To counteract this exploit, often adversarial training is used. However, it is known…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Daniel Wiens , Barbara Hammer

Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast…

Computation and Language · Computer Science 2025-10-14 Jens Van Nooten , Andriy Kosar , Guy De Pauw , Walter Daelemans

The functional correspondence is a manual derivation technique transforming higher-order evaluators into the semantically equivalent abstract machines. The transformation consists of two well-known program transformations: translation to…

Programming Languages · Computer Science 2021-08-17 Maciej Buszka , Dariusz Biernacki

The heterogeneous nature of the logical foundations used in different interactive proof assistant libraries has rendered discovery of similar mathematical concepts among them difficult. In this paper, we compare a previously proposed…

Logic in Computer Science · Computer Science 2021-07-22 Qingxiang Wang , Cezary Kaliszyk

A decidability proof for bisimulation equivalence of first-order grammars (finite sets of labelled rules for rewriting roots of first-order terms) is presented. The equivalence generalizes the DPDA (deterministic pushdown automata)…

Logic in Computer Science · Computer Science 2014-06-02 Petr Jancar

We investigate a simply typed modal $\lambda$-calculus, $\lambda^{\to\square}$, due to Pfenning, Wong and Davies, where we define a well-typed term with respect to a context stack that captures the possible world semantics in a syntactic…

Programming Languages · Computer Science 2023-06-22 Jason Z. S. Hu , Brigitte Pientka

This study uses stacked generalization, which is a two-step process of combining machine learning methods, called meta or super learners, for improving the performance of algorithms in step one (by minimizing the error rate of each…

Machine Learning · Computer Science 2020-04-07 Kathleen Kerwin , Nathaniel D. Bastian

For many tasks, the reward function is inaccessible to introspection or too complex to be specified procedurally, and must instead be learned from user data. Prior work has evaluated learned reward functions by evaluating policies optimized…

Machine Learning · Computer Science 2021-03-19 Adam Gleave , Michael Dennis , Shane Legg , Stuart Russell , Jan Leike

Multistep returns, such as $n$-step returns and $\lambda$-returns, are commonly used to improve the sample efficiency of reinforcement learning (RL) methods. The variance of the multistep returns becomes the limiting factor in their length;…

Machine Learning · Computer Science 2025-12-23 Brett Daley , Martha White , Marlos C. Machado

Entity matching is a fundamental task in data cleaning and data integration. With the rapid adoption of large language models (LLMs), recent studies have explored zero-shot and few-shot prompting to improve entity matching accuracy.…

Databases · Computer Science 2025-12-01 Rohan Bopardikar , Jin Wang , Jia Zou

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…

Machine Learning · Computer Science 2024-02-01 Thomas Degris , Khurram Javed , Arsalan Sharifnassab , Yuxin Liu , Richard Sutton

Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems. As Large Language Models (LLMs) improve their reasoning…

Computation and Language · Computer Science 2026-05-20 Husnain Amjad , Raja Khurram Shahzad , Aamir Shahzad , Mehwish Fatima

Class-incremental learning (CIL) aims to acquire new classes over time while retaining prior knowledge, yet most setups and methods assume balanced task streams. In practice, the number of classes per task often varies significantly. We…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Xiaoyan Zhang , Jiangpeng He

State-space reduction techniques, used primarily in model-checkers, all rely on the idea that some actions are independent, hence could be taken in any (respective) order while put in parallel, without changing the semantics. It is thus not…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-04-03 Lisbeth Fajstrup , Eric Goubault , Emmanuel Haucourt , Samuel Mimram , Martin Raussen