11 papers
EvoMem: Memory-Augmented Evolution for Code Optimization
Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin +8
Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks an…
TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics
QuocViet Pham, Elvir Karimov, Andrey Galichin +1
LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to c…
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7
Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practi…
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Rece…
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Valentin Khrulkov, Andrey Galichin, Denis Bashkirov +5
Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering…
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absor…
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is of…
Listener-Rewarded Thinking in VLMs for Image Preferences
Alexander Gambashidze, Li Pengyi, Matvey Skripkin +5
Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However,…
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Andrey Galichin, Alexey Dontsov, Polina Druzhinina +4
Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms b…
Spread them Apart: Towards Robust Watermarking of Generated Content
Mikhail Pautov, Danil Ivanov, Andrey V. Galichin +2
Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is…
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin +2
While Deep Neural Networks (DNNs) have demonstrated remarkable performance in tasks related to perception and control, there are still several unresolved concerns regarding the pri…