Alexey Dontsov
6 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Cross-Pollinator (15) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13)
π§
Keyword Pioneer
Conferences
ACL (2)
EACL (2)
AAAI (1)
NAACL (1)
Top co-authors
Research topics
Keywords
sparse autoencoder
(3)
question answering
(1)
multimodal learning
(1)
privacy preservation
(1)
machine unlearning
(1)
model forgetting
(1)
feature representation
(1)
deep learning model
(1)
language model
(1)
mechanistic interpretability
(1)
electronic health record
(1)
reasoning model
(1)
causal intervention
(1)
gradient ascent
(1)
reward estimation
(1)
process reward model
(1)
text-to-sql generation
(1)
data removal
(1)
feature steering
(1)
large language model
(1)
Papers
Out of Distribution, Out of Luck: Process Rewards Misguide Reasoning Models
EACL 2026
Feature Drift: How Fine-Tuning Repurposes Representations in LLMs
EACL 2026
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
AAAI 2026
Motivating Next-Gen Accelerators with Flexible N:M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
ACL 2026
CLEAR: Character Unlearning in Textual and Visual Modalities
ACL 2025
AIRI NLP Team at EHRSQL 2024 Shared Task: T5 and Logistic Regression to the Rescue
NAACL 2024