PPaperPicks

Alexey Dontsov

5 papers at tracked venues · 3 at CORE A* · active 20252026

Venues

Frequent coauthors

Papers

  1. Feature Drift: How Fine-Tuning Repurposes Representations in LLMs
  2. I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
  3. Motivating Next-Gen Accelerators with Flexible N: M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
  4. Out of Distribution, Out of Luck: Process Rewards Misguide Reasoning Models
    EACL 2026 · Alexey Dontsov
  5. CLEAR: Character Unlearning in Textual and Visual Modalities
    ACL 2025 · Alexey Dontsov