3 papers
cs.LG2026
Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments
Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel +22
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
Zahar Kohut, Zakhar Kohut, Severyn Shykula +8
Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final…