20 papers · ranked by Valyu relevance
Noah Patton, Kia Rahmani, Meghana Missula, Joydeep Biswas + 1 more
'Işıl Dillig'] Abstract. The goal of programmatic Learning from Demonstration (LfD) is to learn a policy in a programming language that can be used to control a robot's behavior from a set of user demonstrations. This paper presents a new programmatic LfD algorithm that targets long-horizon robot tasks which require…
Jiang, Shan, Zhu, Chenguang + 2 more
JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure resistance to deobfuscation, leaving the critical question of whether obfuscators…
Yuezhi Yang, Hao Pan
Sketch design concepts are recurring patterns found in parametric CAD sketches. Though rarely explicitly formalized by the CAD designers, these concepts are implicitly used in design for modularity and regularity. In this paper, we propose a learning based approach that discovers the modular concepts by induction over…
Masaomi Yamaguchi, Kazutaka Matsuda, Cristina David, Meng Wang
We propose a technique for synthesizing bidirectional programs from the corresponding unidirectional code plus a few input/output examples. The core ideas are: (1) constructing a sketch using the given unidirectional program as a specification, and (2) filling the sketch in a modular fashion by exploiting the…
Ryan Yen, Jian Zhao, Daniel Vogel
Sketching Authors: Ryan Yen, Jian Zhao, Daniel Vogel Title: Code Shaping: Iterative Code Editing with Free-form AI-Interpreted Sketching Authors: Ryan Yen, Jian Zhao, Daniel Vogel Content: ### 8.3 Shaping AI Output with Sketches While we did not compare sketches to textual prompts directly, some participants (5/18)…
Daniel N. Baker, Ben Langmead
A genomic sketch is a small, probabilistic representation of the set of k-mers in a sequencing dataset. Sketches are building blocks for large-scale analyses that consider similarities between many pairs of sequences or sequence collections. While existing tools can easily compare 10,000s of genomes, relevant datasets…
Greg Wilson, Francis Ouellette
The insight on which all modern computing is based is that code is just another kind of data. Programs are just text files, which means we can process it like any other piece of text. Examples of this include: 1. style-checking tools that check that the layout, variable names, and other properties conform to coding…
Daniel N. Baker, Ben Langmead
A genomic sketch is a small, probabilistic representation of the set of $k$-mers in a sequencing data set. Sketches are building blocks for large-scale analyses that consider similarities between many pairs of sequences or sequence collections. Although existing tools can easily compare tens of thousands of genomes…
Jiaxing Bai, Feng Zhou, Chongyang Tan, Yichun Gao + 4 more
The rapid expansion of single-cell RNA sequencing (scRNA-seq) datasets poses analytical challenges, including computational burden raised by increasing data scale, and imbalances in cell population sizes. Dataset sketching mitigates these issues by selecting representative subsets that preserve biological signals.…
Seewon Choi, Alaia Solko-Breslin, Rajeev Alur, Eric Wong
Many computational tasks benefit from being formulated as the composition of neural networks followed by a discrete symbolic program. The goal of neurosymbolic learning is to train the neural networks using only end-to-end input-output labels of the composite. We introduce CTSketch, a novel, scalable neurosymbolic…
Isaac Joffe, Yuchen Qian, Mohammad Talebi-Kalaleh, Qipei Mei + 2 more
Structural engineers are often required to draw two-dimensional engineering sketches for quick structural analysis, either by hand calculation or using analysis software. However, calculation by hand is slow and error-prone, and the manual conversion of a hand-drawn sketch into a virtual model is tedious and…
Mahmudur Rahman Hera, David Koslicki
The increasing number and volume of genomic and metagenomic data necessitates scalable and robust computational models for precise analysis. Sketching techniques utilizing k-mers from a biological sample have proven to be useful for large-scale analyses. In recent years, FracMinHash has emerged as a popular sketching…
Sebastijan Veselic, Nour Mohsen, Lennart Luettgau, Elena Gutierrez + 5 more
Reasoning flexibly composes known elements to solve novel problems. Recent theories suggest the brain uses the axis of time to compose elements for reasoning. In this view, elements are packaged into fast neural sequences, with each sequence exploring the implications of a different composition. Using…
Honggang Zhao, Mingyue Liu, Mingyong Li, Andrea Prati + 2 more
'Luis Javier García Villalba' 'Vincent A. Cicirello'] Zero-shot sketch-based image retrieval (ZS-SBIR) is an important computer vision problem. The image category in the test phase is a new category that was not visible in the training stage. Because sketches are extremely abstract, the commonly used backbone networks…
Oliver Lee, Malte Gather, Eli Zysman-Colman
We describe a new tool for the efficient management of computational chemistry. Digichem is a program that automates and simplifies nearly the entire computational pipeline, including large-scale batch submission of calculations, analysis and results parsing, the generation of 3D density plots and 2D graphs of…
Joshua S. Rule, Steven T. Piantadosi, Andrew Cropper, Kevin Ellis + 2 more
Throughout their lives, humans seem to learn a variety of rules for things like applying category labels, following procedures, and explaining causal relationships. These rules are often algorithmically rich but are nonetheless acquired with minimal data and computation. Symbolic models based on program learning…
Authors not listed
Step-by-step thinking is essential in all domains of chemical sciences and engineering. While machine learning tools are broadly used, algorithms that automate reasoning are far less common. We elaborate on seven categories of human reasoning activities and connect each to applications in chemical science and…
Babu Bassa
In this communication the author describes a software tool named "ChameleonSort". The software program, developed by the present author is useful in the sorting of biological sequence variants like those accumulating mutations while diverging from the common ancestors. Examples include viral protein variants, protein…
Authors not listed
We present an open source collection of scripts and programs for the setup, management and evaluation of calculations with the Vienna ab-initio simulation package (VASP), called utils4VASP. It contains 20 independent Python scripts and Fortran programs, all with a unified and intuitive handling concept based on command…
Yun-Fei Liu, Marina Bedny
Programming is a cornerstone of modern society, yet its cognitive and neural basis remains poorly understood. In this study, we test the hypothesis that programming “recycles” pre-existing neural mechanisms and representations in fronto-parietal reasoning networks. Using fMRI, we scanned programming-naïve…