Daniil Gavrilov
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
8
Venues
6
Active years
2019–2025
Best venue rank
A*
Where they publish
Papers
8 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2025 | EMNLP | Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy. | Nikita Balagansky, Yaroslav Aksenov, Daniil Laptev, Vadim Kurochkin, Gleb Gerasimov, Nikita Koriagin, Daniil Gavrilov |
| 2025 | EMNLP | Steering LLM Reasoning Through Bias-Only Adaptation. | Viacheslav Sinii, Alexey Gorbatovski, Artem Cherepanov, Boris Shaposhnikov, Nikita Balagansky, Daniil Gavrilov |
| 2025 | ICLR | Mechanistic Permutability: Match Features Across Layers. | Nikita Balagansky, Ian Maksimov, Daniil Gavrilov |
| 2025 | ICLR | Learn Your Reference Model for Real Good Alignment. | Alexey Gorbatovski, Boris Shaposhnikov, Alexey Malakhov, Nikita Surnachev, Yaroslav Aksenov, Ian Maksimov, Nikita Balagansky, Daniil Gavrilov |
| 2025 | ICML | Analyze Feature Flow to Enhance Interpretation and Steering in Language Models. | Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov |
| 2024 | ACL | Linear Transformers with Learnable Kernel Functions are Better In-Context Models. | Yaroslav Aksenov, Nikita Balagansky, Sofia Maria Lo Cicero Vaina, Boris Shaposhnikov, Alexey Gorbatovski, Daniil Gavrilov |
| 2021 | EACL | Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning. | Evgeny Lagutin, Daniil Gavrilov, Pavel Kalaidin |
| 2019 | ECIR | Self-attentive Model for Headline Generation. | Daniil Gavrilov, Pavel Kalaidin, Valentin Malykh |