← Search

Valentin Malykh

5 accepted papers

2025

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

NeurIPS 2025poster

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning…

Cited by 0SourcecodeScholar
2024

Searching by Code: A New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets

COLING 2024main

Code search is an important and well-studied task, but it usually means searching for code by a text query. We argue that using a code snippet (and possibly an error traceback) as a query while looking for bugfixing instructions and code samples is a natural use case not covered by prior art. Moreov…

Cited by 1SourcePDFScholar
2022

DetIE: Multilingual Open Information Extraction Inspired by Object Detection

AAAI 2022technical

State of the art neural methods for open information extraction (OpenIE) usually extract triplets (or tuples) iteratively in an autoregressive or predicate-based manner in order not to produce duplicates. In this work, we propose a different approach to the problem that can be equally or more succes…

2020

SumTitles: a Summarization Dataset with Low Extractiveness

COLING 2020main

The existing dialogue summarization corpora are significantly extractive. We introduce a methodology for dataset extractiveness evaluation and present a new low-extractive corpus of movie dialogues for abstractive text summarization along with baseline evaluation. The corpus contains 153k dialogues…