Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hui Wang

Hui Wang

6 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

ML×4Vision×3AI×3Sound×2NLP×1Multimedia×1Crypto×1

Frequent co-authors

Zixian Su2×
Hongkai Zhang2×
Fan Gao2×
Encheng Su2×
Taiping Qu2×
Jingwei Guo2×

Research Timeline

2026
Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to mitigate this risk.

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reality gap' and perform poorly when simulating real-world cardiac interpretation workflows.

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reality gap' and perform poorly when simulating real-world cardiac interpretation workflows.

Latent World Recovery for Multimodal Learning with Missing Modalities

The paper proposes a framework for multimodal learning under missing modalities, called Latent World Recovery (LWR), which aligns modality-specific embeddings in a shared latent space and fuses available modalities for robust prediction.

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

The paper proposes a method called self-guidance to improve the reconstruction fidelity of neural speech codecs based on Vector-Quantized VAEs.

Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

This paper introduces Omni Demand Understanding (ODU), a benchmark for evaluating AI assistants' ability to infer user demands from multimodal interaction.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CVcs.MMEmpiricalRecentSep 18, 2026

Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

Qi Chen, Yunfei Chu, Haolin He, Yifan Yang +14 more

This paper introduces Omni Demand Understanding (ODU), a benchmark for evaluating AI assistants' ability to infer user demands from multimodal interaction.

View →
cs.SDcs.LGEmpirical
Recent
Jun 11, 2026

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

Xiang Li, Yixuan Zhou, Jingran Xie, Zhiyong Wu +1 more

The paper proposes a method called self-guidance to improve the reconstruction fidelity of neural speech codecs based on Vector-Quantized VAEs.

View →
cs.LGcs.AIEmpiricalRecentJun 10, 2026

Latent World Recovery for Multimodal Learning with Missing Modalities

Hui Wang, Tianyu Ren, Joseph Butler, Christopher Baker +2 more

The paper proposes a framework for multimodal learning under missing modalities, called Latent World Recovery (LWR), which aligns modality-specific embeddings in a shared latent space and fuses availa…

View →
cs.CVcs.AIcs.LGRecentMay 28, 2026

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

Zixian Su, Hongkai Zhang, Fan Gao, Encheng Su +11 more

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

View →
cs.CVcs.AIcs.LGRecentMay 28, 2026

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

Zixian Su, Hongkai Zhang, Fan Gao, Encheng Su +11 more

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

View →
cs.CRMay 1, 2026

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set

Jie Fu, Nima Naderloui, Da Zhong, Yuan Hong +1 more

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to…

View →