arxiv:2605.31159
Daniil Gavrilov
kefirski
AI & ML interests
hustle
Recent Activity
authored a paper 4 days ago
ESSA: Evolutionary Strategies for Scalable Alignment authored a paper 4 days ago
Train One Sparse Autoencoder Across Multiple Sparsity Budgets to
Preserve Interpretability and Accuracy authored a paper 4 days ago
Steering LLM Reasoning Through Bias-Only AdaptationOrganizations
arxiv:2603.02765
arxiv:2602.06717
arxiv:2509.06608
arxiv:2508.04280
arxiv:2507.12990
arxiv:2507.04453
arxiv:2505.24473
arxiv:2505.22255
arxiv:2505.18706
arxiv:2502.09245
arxiv:2502.03032
arxiv:2502.01237
arxiv:2410.07656
arxiv:2404.09656
arxiv:2402.10644
arxiv:2205.07276
arxiv:2204.03276
arxiv:2101.04229
arxiv:1901.07786
