collaborators

7 papers

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.CV2026

Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry

Michał Zakrzewski, Mariia Shpir, Taras Rumezhak

Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al., 2017), matching the query to…

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…

cs.CR2022

Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy

Lucas Rosenblatt, Bernease Herman, Anastasia Holovenko +7

Differential privacy (DP) data synthesizers support public release of sensitive information, offering theoretical guarantees for privacy but limited evidence of utility in practica…

cs.CV2022

Towards realistic symmetry-based completion of previously unseen point clouds

Taras Rumezhak, Oles Dobosevych, Rostyslav Hryniv +3

3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, sp…