9 papers
HeartMuLa: A Family of Open Sourced Music Foundation Models
Dongchao Yang, Yuxin Xie, Yuguo Yin +26
We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework con…
ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval
Siyuan Fu, Xuchen Guo, Mingjun Liu +7
The dominant paradigm for Audio-Text Retrieval (ATR) relies on dual-encoder architectures optimized via mini-batch contrastive learning. However, restricting optimization to local…
SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Jiehui Luo, Yuguo Yin, Yuxin Xie +6
Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of application…
DermoGPT: Open Weights and Open Data for Morphology-Grounded Dermatological Reasoning MLLMs
Jinghan Ru, Siyuan Yan, Yuguo Yin +2
Multimodal Large Language Models (MLLMs) show promise for medical applications, yet progress in dermatology lags due to limited training data, narrow task coverage, and lack of cli…
Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
Lexiang Tang, Xianwei Zhuang, Bang Yang +5
Large vision-language models (LVLMs) have demonstrated impressive capabilities across diverse multimodal tasks, yet they remain highly susceptible to visual hallucinations (VH), of…
ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors
Yuguo Yin, Yuxin Xie, Wenyuan Yang +5
Multilingual audio-text retrieval (ML-ATR) is a challenging task that aims to retrieve audio clips or multilingual texts from databases. However, existing ML-ATR schemes suffer fro…