◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Taras Rumezhak

7 papers hereh-index 327 citations10 works total

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

author position
  • first author1
  • middle author3
  • last author1

Across the 5 of 7 papers where every author was matched, so the position is known.

fields
  • cs.LG4
  • cs.CV2
  • cs.CR1

identity via Semantic Scholar / OpenAlex

collaborators
Showing cs.LGShow all

4 papers · 1 filter

cs.LG2026

Agreement versus Softmax under Spatial Disambiguation

Michał Zakrzewski, Mariia Shpir, Taras Rumezhak +1

ScanRefer Multiple queries require spatial disambiguation: several instances of the target class are present, and the referencer must pick one. When per-query logits were never log…

cs.LG2026

Running the Gauntlet: Hard Agentic Tasks

Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel +21

As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchma…

cs.LG2026

Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion

Mykola Vysotskyi, Zahar Kohut, Mariia Shpir +2

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervi…

cs.LG2026

Just on Time: Token-Level Early Stopping for Diffusion Language Models

Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi +7

Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final…

◍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.