3 papers
cs.LG2026
VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
Egor Cherepanov, Nikita Kachaev, Daniil Zelezetsky +6
Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on i…
cs.CL2026
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
Alla Chepurova, Aydar Bulatov, Mikhail Burtsev +1
Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text re…
cond-mat.mtrl-sci2025
Enhancing composition-based materials property prediction by cross-modal knowledge transfer
Ivan Rubtsov, Ivan Dudakov, Yuri Kuratov +1
Crystal graph neural networks are widely applicable in modeling experimentally synthesized compounds and hypothetical materials with unknown synthesizability. In contrast, structur…