5 citations · 6 across the 13 of their papers we have counts for
17 papers
Fusion Anything: A Generalized Multimodal Foundation Model
Huizi Cui, Zongbo Han, Chenggong Ding +6
Making prediction with multimodal data is widely used in diverse scenarios. Existing multimodal fusion models, once deployed, can only handle predefined modalities (e.g., vision, t…
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
Jing Li, Pan Liu, Meng Zhao +7
Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source d…
Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
Zhe Zhang, Jing Li, Wanli Xue +4
Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transf…
TEMPO: Scaling Test-time Training for Large Reasoning Models
Qingyang Zhang, Xinke Kong, Haitao Wu +7
Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. De…
Quantum Visual Word Sense Disambiguation: Unraveling Ambiguities Through Quantum Inference Model
Wenbo Qiao, Peng Zhang, Qinghua Hu
Visual word sense disambiguation focuses on polysemous words, where candidate images can be easily confused. Traditional methods use classical probability to calculate the likeliho…
Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework
Jingjing Wang, Pengyu Liang, Tingyu Wang +12
Solar activity drives space weather, affecting Earth's magnetosphere and technological infrastructure, which makes accurate solar flare forecasting critical. Current space weather…
Generalized Few-Shot Out-of-Distribution Detection
Pinxuan Li, Bing Cao, Changqing Zhang +1
Few-shot Out-of-Distribution (OOD) detection has emerged as a critical research direction in machine learning for practical deployment. Most existing Few-shot OOD detection methods…
Semantic Energy: Detecting LLM Hallucination Beyond Entropy
Huan Ma, Jiadong Pan, Jing Liu +7
Large Language Models (LLMs) are being increasingly deployed in real-world applications, but they remain susceptible to hallucinations, which produce fluent yet incorrect responses…
Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach
Leyan Xue, Zongbo Han, Guangyu Wang +3
Vision-Language Models (VLMs) like CLIP achieve cross-modal semantic alignment through contrastive learning, exhibiting robust zero-shot generalization. Traditional prompt engineer…
Dig2DIG: Dig into Diffusion Information Gains for Image Fusion
Bing Cao, Baoshuo Cai, Changqing Zhang +1
Image fusion integrates complementary information from multi-source images to generate more informative results. Recently, the diffusion model, which demonstrates unprecedented gen…
Online Clustering of Dueling Bandits
Zhiyong Wang, Jiahang Sun, Mingze Kong +4
The contextual multi-armed bandit (MAB) is a widely used framework for problems requiring sequential decision-making under uncertainty, such as recommendation systems. In applicati…
Out-Of-Distribution Detection with Diversification (Provably)
Haiyun Yao, Zongbo Han, Huazhu Fu +3
Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outli…
DOTA: Distributional Test-Time Adaptation of Vision-Language Models
Zongbo Han, Jialong Yang, Guangyu Wang +4
Vision-language foundation models (VLMs), such as CLIP, exhibit remarkable performance across a wide range of tasks. However, deploying these models can be unreliable when signific…
Predictive Dynamic Fusion
Bing Cao, Yinan Xia, Yi Ding +2
Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and a…
Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Qingyang Zhang, Yake Wei, Zongbo Han +8
Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of s…
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Huan Ma, Yan Zhu, Changqing Zhang +5
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, th…
Selective Learning: Towards Robust Calibration with Dynamic Regularization
Zongbo Han, Yifeng Yang, Changqing Zhang +3
Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which…