6 papers
Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Hao Dong, Lijun Sheng, Jian Liang +3
Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when direct…
To Trust Or Not To Trust Your Vision-Language Model's Prediction
Hao Dong, Moru Liu, Jian Liang +2
Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and…
Interactive Symbolic Regression through Offline Reinforcement Learning: A Co-Design Framework
Yuan Tian, Wenqi Zhou, Michele Viscione +3
Symbolic Regression (SR) holds great potential for uncovering underlying mathematical and physical relationships from observed data. However, the vast combinatorial space of possib…
Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization
Hao Dong, Eleni Chatzi, Olga Fink
Test-time adaptation (TTA) has demonstrated significant potential in addressing distribution shifts between training and testing data. Open-set test-time adaptation (OSTTA) aims to…
Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models
Hao Dong, Moru Liu, Kaiyang Zhou +4
In real-world scenarios, achieving domain adaptation and generalization poses significant challenges, as models must adapt to or generalize across unknown target distributions. Ext…
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework
Ismail Nejjar, Hao Dong, Olga Fink
Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where novel classes - also referred to as target-private unknown…