Cover Image

Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Kaihua, Qi, Jiaxin, Ou, Jinli, Zheng, Yuhua, Huang, Jianqiang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Spatial Transcriptomics as Images for Large-Scale Pretraining
by: Zhu, Yishun, et al.
Published: (2026)

Unbiased Scene Graph Generation from Biased Training
by: Tang, Kaihua, et al.
Published: (2020)

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
by: Tang, Kaihua, et al.
Published: (2020)

Test-Time Hinting for Black-Box Vision-Language Models
by: Hou, Kaihua, et al.
Published: (2026)

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
by: Wang, Xin, et al.
Published: (2024)

Invariant Feature Learning for Generalized Long-Tailed Classification
by: Tang, Kaihua, et al.
Published: (2022)

Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
by: Tang, Zhijiang, et al.
Published: (2026)

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
by: Qi, Jiaxin, et al.
Published: (2022)

ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models
by: Luo, Wei, et al.
Published: (2026)

TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models
by: Li, Zhiwei, et al.
Published: (2025)

Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models
by: Mishra, Shambhavi, et al.
Published: (2024)

Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
by: Chen, Kaihua, et al.
Published: (2025)

AME: Aligned Manifold Entropy for Robust Vision-Language Distillation
by: Cao, Guiming, et al.
Published: (2025)

CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation
by: Lafon, Marc, et al.
Published: (2025)

TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models
by: Zhang, Haokui, et al.
Published: (2026)

Efficient Test-Time Scaling for Small Vision-Language Models
by: Kaya, Mehmet Onurcan, et al.
Published: (2025)

Prototype-Based Test-Time Adaptation of Vision-Language Models
by: Huang, Zhaohong, et al.
Published: (2026)

Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models
by: Li, Jiayu, et al.
Published: (2026)

Test-Time Consistency in Vision Language Models
by: Chou, Shih-Han, et al.
Published: (2025)

Two Causal Principles for Improving Visual Dialog
by: Qi, Jiaxin, et al.
Published: (2019)

Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models
by: Qiao, Xiaozhen, et al.
Published: (2025)

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
by: Sheng, Lijun, et al.
Published: (2025)

Realistic Test-Time Adaptation of Vision-Language Models
by: Zanella, Maxime, et al.
Published: (2025)

Bayesian Test-Time Adaptation for Vision-Language Models
by: Zhou, Lihua, et al.
Published: (2025)

Efficient Test-Time Adaptation of Vision-Language Models
by: Karmanov, Adilbek, et al.
Published: (2024)

DataViz3D: An Novel Method Leveraging Online Holographic Modeling for Extensive Dataset Preprocessing and Visualization
by: Duan, Jinli
Published: (2024)

BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis
by: Cui, Shuang, et al.
Published: (2025)

Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
by: Hai, Jia-Wei, et al.
Published: (2026)

Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning
by: Gao, Zhengqing, et al.
Published: (2024)

dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
by: Xin, Yi, et al.
Published: (2025)

ReasonEdit: Editing Vision-Language Models using Human Reasoning
by: Qiu, Jiaxing, et al.
Published: (2026)

Ultra-Light Test-Time Adaptation for Vision--Language Models
by: Kim, Byunghyun
Published: (2025)

Efficient Test-Time Prompt Tuning for Vision-Language Models
by: Zhu, Yuhan, et al.
Published: (2024)

Online Gaussian Test-Time Adaptation of Vision-Language Models
by: Fuchs, Clément, et al.
Published: (2025)

Negation-Aware Test-Time Adaptation for Vision-Language Models
by: Han, Haochen, et al.
Published: (2025)

TTRV: Test-Time Reinforcement Learning for Vision Language Models
by: Singh, Akshit, et al.
Published: (2025)

Flatness Guided Test-Time Adaptation for Vision-Language Models
by: Li, Aodi, et al.
Published: (2025)

Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving
by: Yang, Lijin, et al.
Published: (2026)

ScenePilot-4K: A Large-Scale First-Person Dataset and Benchmark for Vision-Language Models in Autonomous Driving
by: Wang, Yujin, et al.
Published: (2026)

A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
by: Mirza, Mujtaba Hussain, et al.
Published: (2026)