ASdb: a system for classifying owners of autonomous systems

M Ziv, L Izhikevich, K Ruth, K Izhikevich… - Proceedings of the 21st …, 2021 - dl.acm.org
While Autonomous Systems (ASes) are crucial for routing Internet traffic, organizations that
own them are little understood. Regional Internet Registries (RIRs) inconsistently collect …

Instructdet: Diversifying referring object detection with generalized instructions

R Dang, J Feng, H Zhang, C Ge, L Song… - arXiv preprint arXiv …, 2023 - arxiv.org
We propose InstructDET, a data-centric method for referring object detection (ROD) that
localizes target objects based on user instructions. While deriving from referring expressions …

Revisiting few-shot object detection with vision-language models

A Madan, N Peri, S Kong, D Ramanan - arXiv preprint arXiv:2312.14494, 2023 - arxiv.org
Few-shot object detection (FSOD) benchmarks have advanced techniques for detecting new
categories with limited annotations. Existing benchmarks repurpose well-established …

Human–robot dialogue annotation for multi-modal common ground

C Bonial, SM Lukin, M Abrams, A Baker… - Language Resources …, 2024 - Springer
In this paper, we describe the development of symbolic representations annotated on
human–robot dialogue data to make dimensions of meaning accessible to autonomous …

What you say is what you show: Visual narration detection in instructional videos

K Ashutosh, R Girdhar, L Torresani… - arXiv preprint arXiv …, 2023 - arxiv.org
Narrated''how-to''videos have emerged as a promising data source for a wide range of
learning problems, from learning visual representations to training robot policies. However …

Bridging the gap: Using deep acoustic representations to learn grounded language from percepts and raw speech

GY Kebe, LE Richards, E Raff, F Ferraro… - Proceedings of the …, 2022 - ojs.aaai.org
Learning to understand grounded language, which connects natural language to percepts,
is a critical research area. Prior work in grounded language acquisition has focused …

Augmenting simulation data with sensor effects for improved domain transfer

AJ Berlier, A Bhatt, C Matuszek - European Conference on Computer …, 2022 - Springer
Simulation provides vast benefits for the field of robotics and Human-Robot Interaction (HRI).
This study investigates how sensor effects seen in the real domain can be modeled in …

Artificial Dreams: Surreal Visual Storytelling as Inquiry Into AI'Hallucination'

BA Halperin, SM Lukin - Proceedings of the 2024 ACM Designing …, 2024 - dl.acm.org
What does it mean for stochastic artificial intelligence (AI) to “hallucinate” when performing a
literary task as open-ended as creative visual storytelling? In this paper, we investigate AI …

What Do Machine Learning Researchers Mean by" Reproducible"?

E Raff, M Benaroch, S Samtani, AL Farris - arXiv preprint arXiv …, 2024 - arxiv.org
The concern that Artificial Intelligence (AI) and Machine Learning (ML) are entering a"
reproducibility crisis" has spurred significant research in the past few years. Yet with each …

The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track

E Bhardwaj, H Gujral, S Wu, C Zogheib… - arXiv preprint arXiv …, 2024 - arxiv.org
Data curation is a field with origins in librarianship and archives, whose scholarship and
thinking on data issues go back centuries, if not millennia. The field of machine learning is …