paper-with-me

홈 › Papers

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better

2026-03-27 · Mriganka Nath, Anurag Das, Jiahao Xie, Bernt Schiele arxiv

Large vision-language models (LVLMs) tend to hallucinate, especially when visual inputs are corrupted at test time. We show that such corruptions act as additional distribution shifts, significantly amplifying hallucination rates in real-world applications. To address this, we propose CLIP-guided Test-Time Training (ClipTTT), a method to adapt LVLMs under degraded conditions on the fly with a single test sample. Specifically, we leverage the image-text alignment strength of a pre-trained CLIP model as a stable guidance signal to identify reliable self-supervision targets, enabling rapid adaptation without altering the base LVLMs. Extensive experiments on standard hallucination benchmarks, with 15 common corruptions, demonstrate that ClipTTT effectively mitigates hallucinations and improves descriptive faithfulness under visual corruptions.

📄 PDF Abstract BibTeX arXiv:2603.26486

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation

2025-07-01 · Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He 외 arxiv

Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods operate strictly within CLIP's original …

Test-time Adaptation

CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition

2026-03-30 · Muhammad Osama Zeeshan, Masoumeh Sharafi, Benoit Savary, Alessandro Lameiras Koerich 외 arxiv

Personalization in emotion recognition (ER) is essential for accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs), such as CLIP, demonstrate strong …

Facial Expression RecognitionVideo Emotion Recognition

Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

2022-09-08 · Xiaodan Du, Raymond A. Yeh, Nicholas Kolkin, Eli Shechtman 외

We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Leveraging the recent advances in Contrastive Language-Image Pre-training (CLIP), no text dat…

DiversityFace Generation

A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models

2026-03-27 · Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed, Iacopo Masi arxiv

Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. Wh…

Visual Question AnsweringAdversarial RobustnessImage Captioning

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation

2025-11-01 · Fangyu Wu, Yujun Cai arxiv

Vision language models such as CLIP have shown remarkable performance in zero shot classification, but remain susceptible to spurious correlations, where irrelevant visual features influence predictions. Existing debiasi…