arXiv Machine Learning June 2, 2026 By Yujun Li, Hongyuan Zhang, Yuan Yuan

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

Read the original on arXiv Machine Learning →

arXiv:2605. 03403v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 31

S-GRPO: Unified Post-Training for Large Vision-Language Models

arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).

By Yuming Yan, Kai Tang, Sihong Chen, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu

llms reinforcement-learning fine-tuning multimodal

arXiv Machine Learning

Sep 10

To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models

The paper introduces selective adaptation for vision‑language models, questioning whether test‑time adaptation (TTA) should always be applied. By analyzing per‑sample predictions before and after adaptation, the authors find that many adaptations are negligible or even harmful, flipping correct predictions. They propose Cross‑Augmentation Similarity (CAS), which skips adaptation when predictions across augmented views are highly similar, achieving comparable or better accuracy while reducing adaptation by up to 85%.

By Siru Jiang, Yuwei Liang, Jian Liang, Ran He, Tieniu Tan

llms multimodal

arXiv Computer Vision

Sep 1

GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models

arXiv:2608.29395v1 Announce Type: new Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data tha...

By Pedram MohajerAnsari, Amir Salarpour, Run Wang, Mert D. Pes\'e

llms multimodal benchmarks

arXiv Machine Learning

Jun 5

Test-Time Training for Visual Foresight Vision-Language-Action Models

arXiv:2605. 08215v2 Announce Type: replace-cross Abstract: Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance.

By Sangwu Park, Wonjoong Kim, Yeonjun In, Sein Kim, Hongseok Kang, Chanyoung Park

multimodal

arXiv AI

Jul 7

Verifier-free Test-Time Sampling for Vision-Language-Action Models

arXiv:2510. 05681v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control.

By Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin

robotics multimodal benchmarks

arXiv Machine Learning

Jul 7

USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning

arXiv:2607. 03900v1 Announce Type: cross Abstract: Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision-language models (e.

By Siru Jiang, Jian Liang, Ran He, Tieniu Tan

llms multimodal

One email a morning, machine-written

Related stories

S-GRPO: Unified Post-Training for Large Vision-Language Models

To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models

GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models

Test-Time Training for Visual Foresight Vision-Language-Action Models

Verifier-free Test-Time Sampling for Vision-Language-Action Models

USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning