HSE Computer Science Researchers Win Gold Medal at International Machine Learning Competition
A team comprising HSE International Laboratory of Statistical and Computational Genomics researchers Aleksei Shmelev and Nikita Chervov, 2025 graduate of the HSE Faculty of Computer Science’s Master’s programme in Data Analysis in Biology and Medicine Ivan Gevorkov, and two students from the United States achieved an outstanding result at the 2026 NeuroGolf international machine learning championship. The team won a gold medal and placed seventh overall.
The competition was held on the Kaggle platform and was based on tasks from the ARC-AGI benchmark, designed to assess the ability of artificial intelligence systems to perform abstract reasoning. Participants had to solve a total of 400 tasks. Each task contained several pairs of ‘before’ and ‘after’ images linked by a single hidden transformation rule. Participants had to identify the underlying pattern from these examples and then propose a minimal neural network architecture capable of performing the same transformation on new images. Since each of the 400 tasks required a different solution, working through the entire set manually was practically impossible. This was one of the reasons why the team decided to automate the research process.
The researchers created a factory of 330 ChatGPT-based agents that could work on a large number of tasks in parallel. To manage the system, the team also developed a Telegram bot that made it easy to monitor and control the agents’ work.
One of the main challenges was determining which tasks should be prioritised for further optimisation. Testing new solutions on Kaggle was subject to daily limits, so each attempt had to be used as efficiently as possible.
To address this, the team plotted the distribution of scores across tasks and tracked how they changed over time. This made it possible to identify the tasks that produced the greatest increases in the overall score and were therefore the most promising areas for further work. The agents’ efforts could then be directed towards those tasks.
The competition provided an opportunity to fine-tune a pipeline for automated AI-agent-based research. This approach makes it possible to scale up work with research hypotheses and test them experimentally more quickly. This is particularly relevant given the rapid growth in the number of new methods and research papers in the field of artificial intelligence.
The team plans to use the approach developed during the competition in their future work to accelerate their research.
A detailed description of the solution has been published in a Kaggle write-up. It provides information about the architecture of the agent system, implementation details, and the open-source code.
Aleksei Shmelev
‘During the competition, we tried different AI models, but mainly worked with ChatGPT and Claude. I found it very interesting to observe how these agents behaved during long periods of autonomous work. It is no longer a secret that modern models are extremely powerful and can perform complex tasks almost flawlessly if the task is formulated clearly. But it turned out that they often behave just like people who are tired after a long working day,’ said Aleksei Shmelev. ‘For example, ChatGPT could simply give up and say that it could not make any further progress. At the same time, sometimes a short prompt such as “Don't give up. I believe in you. You will definitely find a better solution. Think outside the box, explore new branches, and keep trying” was enough to get the model out of a dead end and eventually find a solution. Interestingly, the same approach also worked with both ChatGPT and Claude. You could say something like, “Come on, I know someone who got a higher score on this task. So don't tell me it's impossible. You can do better. Rethink your approach and find a stronger solution.” After that, the model would quite often immediately find a more optimal solution.’
Nikita Chervov
Summing up the results of the competition, Nikita Chervov highlights: ‘We have improved our skills in automating work with agents, which we plan to use in the future to speed up the testing of ideas related to our research.’
The HSE News Service congratulates Aleksei, Nikita, and their team on this outstanding result and wishes them many more scientific achievements!
See also:
HSE University Expands Cooperation with Malaysia in Technology Foresight
HSE University researchers will take part in a study of the future of engineering education in Malaysia, while the Malaysian Industry-Government Group for High Technology (MIGHT) will use the iFORA big-data analysis system to validate the findings of its foresight research. These are the outcomes of a visit by HSE representatives to Kuala Lumpur.
Scientists Train Neural Network to Generate Process Plans from 3D Models
Researchers at the HSE FCS AI and Digital Science Institute have developed CAD2TechSpec, a framework that converts 3D models of mechanical parts into machining process plans—step-by-step instructions for machine tools. The solution aims to reduce the time required for the design and preparation of technical process documentation in mechanical engineering, aircraft manufacturing, and other high-tech industries. The study findings have been published in PeerJ Computer Science.
Biologists Discover 'Molecular Fingerprint' of Preeclampsia
Researchers at HSE University employed a new method to model hypoxia in placental cells during pregnancies complicated by preeclampsia and identified molecular markers of tissue hypoxia. Since hypoxia is one of the key mechanisms underlying preeclampsia, these findings are important for a more accurate and timely diagnosis of the disease and for the development of effective treatment methods. The paper has been published in Placenta.
Laboratory of Future Networks: HSE Telecommunications Research Institute Develops 5G/6G Research Testbed
The 5G/6G testbed at the HSE Telecommunications Research Institute is becoming a research platform, an educational laboratory, and a foundation for developing new software components for future networks. It makes it possible not only to observe how a mobile network operates, but also to change its operating conditions and measure the results: data-transmission speed, latency, errors, radio-resource utilisation, and other parameters. Based on the testbed, researchers plan to develop MIMO, O-RAN, xApp, and IAB technologies, as well as experiment with artificial intelligence.
‘Hedgehog’ Versus ‘Relatives’: Researchers Measure How the Brain Responds to Unexpected Words During Natural Speech
Russian neurophysiologists, including researchers from HSE University, have demonstrated the feasibility of using event-related fields (ERFs) to study brain activity during natural speech perception. The researchers showed that this approach can be applied not only to individual words but also to continuous speech. Their findings indicate that words whose meanings differ significantly from the preceding context require longer processing times. The study also reveals that the brain processes function words in two stages: first, it identifies their grammatical role and then uses this information to predict the next word. The study has been published in Frontiers in Human Neuroscience.
Hybrid Intelligence: Competencies in the Age of AI Discussed at Technoprom-2026
Artificial intelligence is not creating new professions, but rather transforming the nature of existing ones. This was the conclusion reached by participants in the panel session ‘Hybrid Intelligence: Digital and Human Drivers of Development,’ organised by the Institute for Statistical Studies and Economics of Knowledge (ISSEK) at HSE University as part of the 13th International Forum of Technological Development (Technoprom-2026). The experts discussed how the nature of work is changing, which skills are becoming increasingly sought after, and what prevents companies from fully capitalising on new technologies.
Scientists Develop New Solution for 6G Communication Systems
A terahertz neuromorphic circuit developed by scientists at HSE University could make 6G communication systems both more accurate and energy-efficient. The circuit enables indoor tracking of mobile devices with an accuracy of up to 99%. The results were presented at PIERS 2026, an international symposium on Photonics and Electromagnetism held in China.
Scientists Develop Algorithm for More Reliable Processors in Data Centres
Researchers from HSE MIEM and Samara University have developed the LRF-3D algorithm to automatically bypass idle nodes in three-dimensional networks-on-chip. Thanks to its hierarchical architecture, the algorithm outperforms existing solutions in both speed and path accuracy, improving processor reliability for use in data centres, supercomputers, and AI computing. The source code and test results are publicly available.
Researchers Rank Recommendation Algorithms Using Sports Tournament Model
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed an approach for selecting recommendation algorithms more effectively. Their approach uses pairwise comparisons of algorithms to create a tournament table, with the overall ranking based on their performance across all datasets in the tournament. This can reduce the number of algorithms that need to be tested when developing new services, saving both time and money. The study was presented at the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026).
Researchers Develop Method for Direct Generation of Regulatory DNA
Researchers at HSE University have developed a model for generating promoters and enhancers—DNA sequences that regulate gene activity. The model works directly with DNA nucleotides, without first transforming them into a continuous numerical representation. This solution could be useful for applications in synthetic biology and gene therapy. The study results were presented at the ICLR 2026 Workshop ‘Generative AI in Genomics (Gen^2): Barriers and Frontiers.’