◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Daniil Laptev

4 papers here

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author3

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG4

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.LG2025

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors

Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov +6

The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream…

cs.LG2025

Teach Old SAEs New Domain Tricks with Boosting

Nikita Koriagin, Yaroslav Aksenov, Daniil Laptev +3

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features n…

cs.LG2025

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Nikita Balagansky, Yaroslav Aksenov, Daniil Laptev +4

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via spa…

cs.LG2025

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov +1

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.