Author

Mehmet Yardimci

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jun 2026

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

It is argued that critic architecture deserves explicit treatment as a design variable in multi-objective humanoid RL, and specify the single-variable ablation needed to establish its causal contribution.

Mehmet Yardimci · arXiv.org · 0 citations

#machine learning Preprint Sep 2026

Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy

Online reinforcement learning fine-tuning of pretrained flow-matching vision-language-action (VLA) policies promises robots that keep learning after deployment, but continued updates often destroy competence on individual tasks while the aggregate still looks healthy. We study this failure mode, which we call task coll...

Mehmet Yardimci, Y. Cogurcu · 0 citations