conftrace_
← Authors

Yaroslav Aksenov

4 papers · 2024–2025 · 4 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15)

Conferences

ACL (1) EMNLP (1) ICLR (1) ICML (1)

Top co-authors

Daniil Gavrilov (4) Nikita Balagansky (4) Boris Shaposhnikov (2) Alexey Gorbatovski (2) Daniil Laptev (2) Nikita Koriagin (1) Alexey Malakhov (1) Vadim Kurochkin (1) Ian Maksimov (1) Nikita Surnachev (1)

Keywords

in-context learning (1) language modeling (1) state space model (1) language model (1) sparse autoencoder (1) sparsity constraint (1) linear transformer (1) kernel function (1) hierarchical training (1) interpretable feature (1) learnable kernel (1) explained variance (1)

Papers

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy EMNLP 2025 Learn Your Reference Model for Real Good Alignment ICLR 2025 Analyze Feature Flow to Enhance Interpretation and Steering in Language Models ICML 2025 Linear Transformers with Learnable Kernel Functions are Better In-Context Models ACL 2024