Artyom Gadetsky — accepted AI-conference papers

2026

PACER: Acyclic Causal Discovery from Large-scale Interventional Data

Ramon Viñas Torné, Sílvia Fàbregas Salazar, Soyon Park, Ivo Alexander Ban, Artyom Gadetsky, Nikita Doikov +1

ICML 2026poster

Inferring the structure of directed acyclic graphs (DAGs) from data is a central challenge in causal discovery, particularly in modern high-dimensional settings where large-scale interventional data are increasingly available. While interventional data can substantially improve identifiability, exis…

Cited by 0 Source ↗Scholar ↗

2025

Large (Vision) Language Models are Unsupervised In-Context Learners

Artyom Gadetsky, Andrei Atanov, Yulun Jiang, Zhitong Gao, Ghazal Hosseini Mighan, Amir Zamir +1

ICLR 2025poster

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning (ICL), and supervised fine-tuning can further enhance the mo…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Fine-grained Classes and How to Find Them

Matej Grcic, Artyom Gadetsky, Maria Brbic

ICML 2024poster

In many practical applications, coarse-grained labels are readily available compared to fine-grained labels that reflect subtle differences between classes. However, existing methods cannot leverage coarse labels to infer fine-grained labels in an unsupervised manner. To bridge this gap, we propose…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

Let Go of Your Labels with Unsupervised Transfer

Artyom Gadetsky, Yulun Jiang, Maria Brbic

ICML 2024poster

Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance to define visual categories that appear in the data. Here, we…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning

Artyom Gadetsky, Maria Brbic

NeurIPS 2023spotlight

We present HUME, a simple model-agnostic framework for inferring human labeling of a given dataset without any external supervision. The key insight behind our approach is that classes defined by many human labelings are linearly separable regardless of the representation space used to represent a d…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2021

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces

Kirill Struminsky, Artyom Gadetsky, Denis Rakitin, Danil Karpushkin, Dmitry P. Vetrov

NeurIPS 2021poster

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to define a latent variable as a perturbed algorithm output an…

Cited by 12 Source ↗PDF ↗code ↗Scholar ↗