Institution profile

Skolkovo Institute of Science and Technology

Academic institutioneurope · ru
Official website
Research library298linked papers
Opportunities0open roles
Selected work

Representative Papers

Vision-Language Models Unlock Task-Centric Latent Actions

Jan 30, 2026

This work addresses the vulnerability of existing latent action models to task-irrelevant distractors, which often leads to the erroneous encoding of noise as action signals. To mitigate this, the authors propose a novel approach that leverages the commonsense reasoning capabilities of vision-language models (VLMs) to generate task-aware representations distinguishing controllable dynamics from noise. Specifically, task-oriented natural language prompts—such as “ignore distractors”—are used to guide VLMs in producing supervision signals that, in an unsupervised setting, steer latent action models toward learning task-centric action representations. Evaluated on the Distracting MetaWorld benchmark, the method improves downstream task success rates by up to sixfold, significantly enhances action semantic consistency, and effectively suppresses interference. The study also reveals notable differences in prompt sensitivity and performance across various VLMs in the context of action representation learning.

1 citationsRead paper

RaceVLA: VLA-based Racing Drone Navigation with Human-like Behaviour

Mar 04, 2025

To address the challenges of imitating human piloting behavior and adapting to dynamic environments in high-speed racing drone autonomous navigation, this work introduces the Vision-Language-Action (VLA) paradigm to racing scenarios for the first time. We propose a lightweight VLA architecture tailored for dynamic race tracks, along with a dedicated fine-tuning strategy that accommodates onboard dynamic visual input and simplified motion primitives. Trained on a novel multimodal racing drone dataset, our system enables language-guided action generation and real-time closed-loop control. Experiments demonstrate superior semantic generalization (45.5) and motion generalization (75.0) over OpenVLA and RT-2. In physical flight tests, the drone achieves an average speed of 1.04 m/s and a peak speed of 2.02 m/s, exhibiting robust high-speed maneuverability under complex, time-varying track conditions.

1 citationsRead paper

Online algorithm for aggregating experts’ predictions with unbounded quadratic loss

Oct 01, 2020Russian Mathematical Surveys

This paper studies online expert aggregation under unbounded quadratic loss—a setting where conventional methods require prior knowledge of the loss upper bound, while our work proposes the first adaptive algorithm that operates without such a bound. Methodologically, we design an exponential-weighting-based dynamic weight update scheme, integrating online learning with adaptive truncation to ensure robustness against highly volatile losses. We theoretically establish that the algorithm achieves the optimal sublinear regret bound $O(sqrt{T log N})$. Empirically, it significantly outperforms classical weighted averaging and existing adaptive approaches on benchmark tasks featuring unbounded and rapidly varying losses. The key contribution is the elimination of dependence on a known loss bound, thereby enabling a more general and robust aggregation framework for online prediction in real-world dynamic environments.

1 citationsRead paper
Recent publications

Latest Papers