Papers by Aleksandr Medvedev

2 papers
ATGen: A Framework for Active Text Generation (2025.acl-demo)

Copied to clipboard

Challenge: Despite the surging popularity of natural language generation tasks, the application of active learning (AL) to NLG has been limited.
Approach: They propose a framework that bridges AL with text generation tasks and provides a unified platform for smooth implementation and benchmarking of novel AL strategies tailored to NLG tasks.
Outcome: The proposed framework simplifies AL-empowered annotation in NLG tasks using both human annotators and automatic annotation agents based on large language models (LLMs).
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground (2026.eacl-demo)

Copied to clipboard

Challenge: Recent foundation models show that reasoningoriented training and improved decoding methods can substantially boost both accuracy and speed.
Approach: They propose an open-weight Russian LLM for hybrid reasoning and efficient inference.
Outcome: The proposed model supports direct answering and reasoning-trace generation . the model and inference pipeline can be extended or modified to suit Russian-language reasoning .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations