Igor Kiselev — accepted AI-conference papers

2026

Object-Centric Latent Action Learning

Albina Klepach, Alexander Nikulin, Ilya Zisman, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov +3

AAAI 2026technical

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization (LAPO) has shown promise in inferring proxy action labels from v

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun, Ivan Tsvigun, Zhuohan Xie, Igor Kiselev +6

EMNLP 2025

LLMs have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information, and users generally lack the tools to detect when this happens. Uncertainty quantification (UQ) provides a framework for assessing the reliability of model outputs, aiding in the identification of

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Latent Action Learning Requires Supervision in the Presence of Distractors

Alexander Nikulin, Ilya Zisman, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev +1

ICML 2025poster

Recently, latent action learning, pioneered by Latent Action Policies (LAPO), have shown remarkable pre-training efficiency on observation-only data, offering potential for leveraging vast amounts of video available on the web for embodied AI. However, prior work has focused on distractor-free data,…

Cited by 0 Source ↗PDF ↗Scholar ↗