mlsanityData to 7 Oct 2026

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning

arXiv 2605.03403 ↗First posted 5 May 2026cs.CV cs.LGcited by 0

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether the GRPO also significantly promotes the test-time adaptation (TTA) of vision language models. In this paper, we propose Group Relative Policy Optimization for Test-Time Adaptation (GRPO-TTA), which adapts GRPO to the TTA setting by reformulating class-specific prompt prediction as a group-wise policy optimization problem. Specifically, we construct output groups by sampling top-K class candidates from CLIP similarity distributions, enabling probability-driven optimization without access to ground-truth labels. Moreover, we design reward functions tailored to test-time adaptation, including alignment rewards and dispersion rewards, to guide effective visual encoder tuning. Extensive experiments across diverse benchmarks demonstrate that GRPO-TTA consistently outperforms existing test-time adaptation methods, with notably larger performance gains under natural distribution shifts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 42 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

11 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning19 Nov
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale18 Mar
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan
  4. 2017Proximal Policy Optimization Algorithms20 Jul

Other references · 7

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  3. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 515
  4. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 81
  5. 2024DOTA: Distributional Test-Time Adaptation of Vision-Language Modelscited by 22
  6. 2025On the Robustness of Reward Models for Language Model Alignmentcited by 13
  7. 2025CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptationcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026S-GRPO: Unified Post-Training for Large Vision-Language Models
  2. 2025TTRV: Test-Time Reinforcement Learning for Vision Language Models
  3. 2026Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
  4. 2026All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
  5. 2026Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups
  6. 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
  7. 2026Perturb the Thought, Not the Pixels: Latent-Space Rollout Diversification for Reinforcement Learning of Vision-Language Models
  8. 2025DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models