arXiv AI By Xinyu Qiu, Yunzhu Zhang, Heng Jia, Shuheng Shen, Changhua Meng, Linchao Zhu

VISTA: View-Consistent Self-Verified Training for GUI Grounding

Read the original on arXiv AI →

arXiv:2606. 14579v1 Announce Type: new Abstract: When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult instances or all successes on easy ones, yielding no useful relative advantage.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 2

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

arXiv:2601. 14232v2 Announce Type: replace-cross Abstract: Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis.

By Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov