13 papers
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong +3
Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their wides…
UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations
Tingyu Yuan, Biaoliang Guan, Wen Ye +8
In embodied intelligence, the embodiment gap between robotic and human hands brings significant challenges for learning from human demonstrations. Although some studies have attemp…
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
Wenqian Ye, Bohan Liu, Guangtao Zheng +6
Spurious bias, a tendency to exploit spurious correlations between superficial input attributes and prediction targets, has revealed a severe robustness pitfall in classical machin…
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye, Luyang Jiang, Eric Xie +16
Back in the early 20th century, a horse named Hans appeared to perform arithmetic and other intellectual tasks during exhibitions in Germany, while it actually relied solely on inv…
What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Xu Cao, Yifan Shen, Bolin Lai +8
Recently, Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation,…
Recent Advances, Applications and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2024 Symposium
Amin Adibi, Xu Cao, Zongliang Ji +39
The fourth Machine Learning for Health (ML4H) symposium was held in person on December 15th and 16th, 2024, in the traditional, ancestral, and unceded territories of the Musqueam,…