Zhiyuan Zhu

Zhan Liu, Changli Tang, Yuxin Wang et al.

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.

Yu Zhang, Changhao Pan, Wenxiang Guo et al.

The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singers, absence of multi-technique information and realistic music scores, and poor task suitability. To tackle these problems, we present GTSinger, a large global, multi-technique, free-to-use, high-quality singing corpus with realistic music scores, designed for all singing tasks, along with its benchmarks. Particularly, (1) we collect 80.59 hours of high-quality singing voices, forming the largest recorded singing dataset; (2) 20 professional singers across nine widely spoken languages offer diverse timbres and styles; (3) we provide controlled comparison and phoneme-level annotations of six commonly used singing techniques, helping technique modeling and control; (4) GTSinger offers realistic music scores, assisting real-world musical composition; (5) singing voices are accompanied by manual phoneme-to-audio alignments, global style labels, and 16.16 hours of paired speech for various singing tasks. Moreover, to facilitate the use of GTSinger, we conduct four benchmark experiments: technique-controllable singing voice synthesis, technique recognition, style transfer, and speech-to-singing conversion. The demos can be found at http://aaronz345.github.io/GTSingerDemo/. We provide the dataset and the code for processing data and conducting benchmarks at https://huggingface.co/datasets/AaronZ345/GTSinger and https://github.com/AaronZ345/GTSinger.

Yu Zhang, Wenxiang Guo, Changhao Pan et al.

Song generation focuses on producing controllable high-quality songs based on various prompts. However, existing methods struggle to generate vocals and accompaniments with prompt-based control and proper alignment. Additionally, they fall short in supporting various tasks. To address these challenges, we introduce VersBand, a multi-task song generation framework for synthesizing high-quality, aligned songs with prompt-based control. VersBand comprises these primary models: 1) VocalBand, a decoupled model, leverages the flow-matching method for generating singing styles, pitches, and mel-spectrograms, allowing fast, high-quality vocal generation with style control. 2) AccompBand, a flow-based transformer model, incorporates the Band-MOE, selecting suitable experts for enhanced quality, alignment, and control. This model allows for generating controllable, high-quality accompaniments aligned with vocals. 3) Two generation models, LyricBand for lyrics and MelodyBand for melodies, contribute to the comprehensive multi-task song generation system, allowing for extensive control based on multiple prompts. Experimental results show that VersBand outperforms baseline models across multiple song generation tasks using objective and subjective metrics. Demos and codes are available at https://aaronz345.github.io/VersBandDemo and https://github.com/AaronZ345/VersBand.

Yaofei Duan, Yuhao Huang, Xin Yang et al.

Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an optimal solution, yet is limited by time and scarce resources. Active learning (AL) offers an efficient approach to reduce annotation costs while maintaining performance, but struggles to handle the challenge posed by distribution variations across different datasets. In this study, we propose a novel unsupervised Active learning framework for Domain Adaptation, named ADAptation, which efficiently selects informative samples from multi-domain data pools under limited annotation budget. As a fundamental step, our method first utilizes the distribution homogenization capabilities of diffusion models to bridge cross-dataset gaps by translating target images into source-domain style. We then introduce two key innovations: (a) a hypersphere-constrained contrastive learning network for compact feature clustering, and (b) a dual-scoring mechanism that quantifies and balances sample uncertainty and representativeness. Extensive experiments on four breast ultrasound datasets (three public and one in-house/multi-center) across five common deep classifiers demonstrate that our method surpasses existing strong AL-based competitors, validating its effectiveness and generalization for clinical domain adaptation. The code is available at the anonymized link: https://github.com/miccai25-966/ADAptation.

Zhe Liu, Yuhao Huang, Lian Liu et al.

Color Doppler echocardiography is a crucial tool for diagnosing mitral regurgitation (MR). Recent studies have explored intelligent methods for MR diagnosis to minimize user dependence and improve accuracy. However, these approaches often fail to align with clinical workflow and may lead to suboptimal accuracy and interpretability. In this study, we introduce an automated MR diagnosis model (MReg) developed on the 4-chamber cardiac color Doppler echocardiography video (A4C-CDV). It follows comprehensive feature mining strategies to detect MR and assess its severity, considering clinical realities. Our contribution is threefold. First, we formulate the MR diagnosis as a regression task to capture the continuity and ordinal relationships between categories. Second, we design a feature selection and amplification mechanism to imitate the sonographer's diagnostic logic for accurate MR grading. Third, inspired by the Mixture-of-Experts concept, we introduce a feature summary module to extract the category-level features, enhancing the representational capacity for more accurate grading. We trained and evaluated our proposed MReg on a large in-house A4C-CDV dataset comprising 1868 cases with three graded regurgitation labels. Compared to other weakly supervised video anomaly detection and supervised classification methods, MReg demonstrated superior performance in MR diagnosis. Our code is available at: https://github.com/cskdstz/MReg.

Yu Zhang, Wenxiang Guo, Changhao Pan et al.

Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limiting their robustness in zero-shot scenarios and producing poor transitions between phonemes and notes. Moreover, they also lack effective multi-level style control via diverse prompts. To overcome these challenges, we introduce TCSinger 2, a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. TCSinger 2 mainly includes three key modules: 1) Blurred Boundary Content (BBC) Encoder, predicts duration, extends content embedding, and applies masking to the boundaries to enable smooth transitions. 2) Custom Audio Encoder, uses contrastive learning to extract aligned representations from singing, speech, and textual prompts. 3) Flow-based Custom Transformer, leverages Cus-MOE, with F0 supervision, enhancing both the synthesis quality and style modeling of the generated singing voice. Experimental results show that TCSinger 2 outperforms baseline models in both subjective and objective metrics across multiple related tasks. Singing voice samples are available at https://aaronz345.github.io/TCSinger2Demo/.

Yaofei Duan, Tao Tan, Zhiyuan Zhu et al.

Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies. However, obtaining a comprehensive, multi-plane annotated fetal US dataset remains challenging, particularly for rare or complex anomalies owing to their low incidence and numerous subtypes. This poses difficulties in training novice radiologists and developing robust AI models, especially for detecting abnormal fetuses. In this study, we introduce a Flexible Fetal US image generation framework (FetalFlex) to address these challenges, which leverages anatomical structures and multimodal information to enable controllable synthesis of fetal US images across diverse planes. Specifically, FetalFlex incorporates a pre-alignment module to enhance controllability and introduces a repaint strategy to ensure consistent texture and appearance. Moreover, a two-stage adaptive sampling strategy is developed to progressively refine image quality from coarse to fine levels. We believe that FetalFlex is the first method capable of generating both in-distribution normal and out-of-distribution abnormal fetal US images, without requiring any abnormal data. Experiments on multi-center datasets demonstrate that FetalFlex achieved state-of-the-art performance across multiple image quality metrics. A reader study further confirms the close alignment of the generated results with expert visual assessments. Furthermore, synthetic images by FetalFlex significantly improve the performance of six typical deep models in downstream classification and anomaly detection tasks. Lastly, FetalFlex's anatomy-level controllable generation offers a unique advantage for anomaly simulation and creating paired or counterfactual data at the pixel level. The demo is available at: https://dyf1023.github.io/FetalFlex/.

Hongcheng Liu, Yuhao Wang, Zhe Chen et al.

Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring synergistic omni-modal reasoning. Beyond understanding global multimodal context, effective reasoning also hinges on fine-grained cross-modal alignment, especially identifying shared referents across modalities, yet this aspect has been largely overlooked. To bridge this gap, we formalize the challenge as a cross-modal coreference problem, where a model must localize a referent in a source modality and re-identify it in a target modality. Building on this paradigm, we introduce CrossOmni, a dataset comprising nine tasks equipped with human-designed reasoning rationales to evaluate and enhance this capability. Experiments on 13 Omni-LLMs reveal systematic weaknesses in cross-modal coreference, which we attribute to the absence of coreference-aware thinking patterns. To address this, we enhance cross-modal alignment via two strategies: a training-free In-Context Learning method and a training-based SFT+GRPO framework designed to induce such thinking patterns. Both approaches yield substantial performance gains and generalize effectively to collaborative reasoning tasks. Overall, our findings highlight cross-modal coreference as a crucial missing piece for advancing robust omni-modal reasoning.

Zhe Chen, Yusheng Liao, Shuyang Jiang et al.

Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable outputs, posing risks in real-world diagnostics. While retrieval-augmented generation has emerged as a potential solution, current medical multimodal RAG systems are unable to perform effective retrieval across heterogeneous sources. The irrelevance of retrieved reports affects the factuality of analysis, while insufficient knowledge affects the credibility of clinical decision-making. To bridge the gap, we construct MedAtlas, which includes extensive multimodal report repositories and diverse text corpora. Based on it, we present HeteroRAG, a novel framework that enhances Med-LVLMs through heterogeneous knowledge sources. The framework introduces Modality-specific CLIPs for effective report retrieval and a Multi-corpora Query Generator for dynamically constructing queries for diverse corpora. Incorporating knowledge from such multifaceted sources, Med-LVLM is then trained with Heterogeneous Knowledge Preference Tuning to achieve cross-modality and multi-source knowledge alignment. Extensive experiments across 12 datasets and 3 modalities demonstrate that the proposed HeteroRAG achieves state-of-the-art performance in most medical vision language benchmarks, significantly improving factual accuracy and reliability of Med-LVLMs.

Zhiyuan Zhu, Jian Wang, Yong Jiang et al.

Accurate carotid plaque grading (CPG) is vital to assess the risk of cardiovascular and cerebrovascular diseases. Due to the small size and high intra-class variability of plaque, CPG is commonly evaluated using a combination of transverse and longitudinal ultrasound views in clinical practice. However, most existing deep learning-based multi-view classification methods focus on feature fusion across different views, neglecting the importance of representation learning and the difference in class features. To address these issues, we propose a novel Corpus-View-Category Refinement Framework (CVC-RF) that processes information from Corpus-, View-, and Category-levels, enhancing model performance. Our contribution is four-fold. First, to the best of our knowledge, we are the foremost deep learning-based method for CPG according to the latest Carotid Plaque-RADS guidelines. Second, we propose a novel center-memory contrastive loss, which enhances the network's global modeling capability by comparing with representative cluster centers and diverse negative samples at the Corpus level. Third, we design a cascaded down-sampling attention module to fuse multi-scale information and achieve implicit feature interaction at the View level. Finally, a parameter-free mixture-of-experts weighting strategy is introduced to leverage class clustering knowledge to weight different experts, enabling feature decoupling at the Category level. Experimental results indicate that CVC-RF effectively models global features via multi-level refinement, achieving state-of-the-art performance in the challenging CPG task.

Yuhao Wang, Zhiyuan Zhu, Heyang Liu et al.

Multimodal large language models (MLLMs) excel at multimodal perception and understanding, yet their tendency to generate hallucinated or inaccurate responses undermines their trustworthiness. Existing methods have largely overlooked the importance of refusal responses as a means of enhancing MLLMs reliability. To bridge this gap, we present the Information Boundary-aware Learning Framework (InBoL), a novel approach that empowers MLLMs to refuse to answer user queries when encountering insufficient information. To the best of our knowledge, InBoL is the first framework that systematically defines the conditions under which refusal is appropriate for MLLMs using the concept of information boundaries proposed in our paper. This framework introduces a comprehensive data generation pipeline and tailored training strategies to improve the model's ability to deliver appropriate refusal responses. To evaluate the trustworthiness of MLLMs, we further propose a user-centric alignment goal along with corresponding metrics. Experimental results demonstrate a significant improvement in refusal accuracy without noticeably compromising the model's helpfulness, establishing InBoL as a pivotal advancement in building more trustworthy MLLMs.