1 citations · 1 across the 6 of their papers we have counts for
9 papers
Improving social media for democratic discourse
Fan Cheng, Amirhossein Farzmahdi, Pinyuan Feng +8
Social media have expanded opportunities for communication and political participation, but today's dominant platforms are optimized primarily for engagement and advertising revenu…
Training Object Permanence in World Models
Haotian Zhang, Fengyuan Yu, Dezhi Luo +28
Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun t…
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Junxiang Xu, Ruisi Wang, Fanyi Pu +49
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be r…
Vision Language Models Cannot Reason About Physical Transformation
Dezhi Luo, Yijiang Li, Maijunxian Wang +7
Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in embodied applications, whether they…
Towards Interpretable Visual Decoding with Attention to Brain Representations
Pinyuan Feng, Hossein Adeli, Wenxuan Guo +3
Recent work has demonstrated that complex visual stimuli can be decoded from human brain activity using deep generative models, offering new ways to probe how the brain represents…
Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues
Zory Zhang, Pinyuan Feng, Bingyang Wang +7
Where someone looks is a nonverbal communication cue that children and adults readily use. How well can Vision-Language Models (VLMs) infer gaze targets? To construct evaluation st…
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration
Yanshu Li, Jianjiang Yang, Tian Yun +3
Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains high…
Better artificial intelligence does not mean better models of biology
Drew Linsley, Pinyuan Feng, Thomas Serre
Deep neural networks (DNNs) once showed increasing alignment with primate perception and neural responses as they improved on vision benchmarks, raising hopes that advances in AI w…
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…