Hugging Face Trending Papers August 10, 2026

SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks

Read the original on Hugging Face Trending Papers →

Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios. This necessitates the need to evaluate the semantic robustness of perception models; conformance of behavior to high-level requirements over real-world perceptual variability.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Aug 12

SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks

arXiv:2608. 10289v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios.

By Nusrat Jahan Mozumder, Divya Gopinath, Corina Pasareanu, Matthew Dwyer

llms diffusion multimodal benchmarks safety

arXiv Machine Learning

Jun 18

Semantic Robustness Certification for Vision-Language Models

arXiv:2606. 18839v1 Announce Type: new Abstract: Vision-language models (VLMs) are now widely used in downstream tasks.

By Peiyu Yang, Paul Montague, Feng Liu, Andrew C. Cullen, Amardeep Kaur, Christopher Leckie, Sarah M. Erfani

llms multimodal

arXiv Machine Learning

Aug 11

Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning

arXiv:2608. 09011v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical scenarios.

By Ao Zhou, Zhiwei Jiang, Zifeng Cheng, Cong Wang, Shufan Yang, Haoru Chen, Qing Gu

llms rag nlp multimodal benchmarks safety

Hugging Face Trending Papers

Jul 13

DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs

While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities.

llms agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 29

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.

By Shikai Qiu, Xiaowen Xu, Benlei Cui, Ting Ma, Xiufeng Huang, Wenjing Jiang, Shaoxuan He, Haolei Xu, Chunyang Chai, Yujian Li, Yiliang Zhang, Guanghui Wang, Ziheng Wang, Ziwen Xu, Zhaoyu Fan, Jinhao Chen, Ruijie Jian, Hongxing Li, Chuxi Xiao, Xinyue Chen, Wenxuan Liu, Libin Dong, Yupeng Cao, Xiaoqian Xia, Jing Wang, Zhe Jiang, Zhenan Ye, Guang Yang, Bin Liu, Wei Peng, Ziqiang Zhu, Meihui Lian, Kaiwen Lv Kacuila, Haidong Ding, Dongjie Zhang, Yangfan Zhou, Bingyu Zhu, Yan Wang, Hai Zhao, Xuan Jin, Wei Zhao, Pengfei Sun, Huiming Zhang, Wei Wang, Xipeng Cao, Jialun Chen, Xiao Chen, Shaola Ren, Yunqing Hu, Bin Li, Chengwen Yao, Meng Huang, Xianfeng Li, Bin Tang, Chao Liu, Hui Xue, Longtao Huang, Haiwen Hong

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 30

On the Faithfulness of Post-Hoc Concept Bottleneck Models

arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.

By Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler

llms multimodal benchmarks

Related stories

SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks

Semantic Robustness Certification for Vision-Language Models

Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning

DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

On the Faithfulness of Post-Hoc Concept Bottleneck Models