Author name cluster

Meng Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning

Shu Wu
Chenxing Li
Wenfu Wang
Hao Zhang
Hualei Wang
Meng Yu
Dong Yu

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning utilizing rule-based rewards. However, the explicit reasoning process has not yet yielded substantial benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of achieving human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs through improved adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that assist the model in distinguishing between valid and flawed reasoning paths during training. Experimental results demonstrate that Audio-Thinker models outperform existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DegVoC: Revisiting Neural Vocoder from a Degradation Perspective

Andong Li
Tong Lei
Lingling Dai
Kai Li
Rilin Chen
Meng Yu
Xiaodong Li
Dong Yu

Existing neural vocoders have demonstrated promising performance by leveraging Mel-spectrum as an acoustic feature for conditional audio generation. Nonetheless, they remain constrained by an inherent ``performance-cost'' dilemma that significantly hinders the development of this field. This paper revisits this foundational task from a novel degradation perspective, where Mel-spectrum is regarded as a special signal degradation process from the target spectrum. Drawing inspiration from traditional sparse signal recovery problems, we propose DegVoC, a GAN-based neural vocoder with a two-step solution procedure. First, by exploiting degradation priors, we attempt to retrieve the initial spectral structure from Mel-domain representations as an initial solution via a simple linear transformation. Based on that, we introduce a deep prior solver that accounts for the heterogeneous distribution of sub-bands in the time-frequency domain. A convolution-style attention module with a large kernel size is specially devised for efficient inter-frame and inter-band contextual modeling. With 3.89 M parameters and substantially reduced inference complexity, DegVoC achieves state-of-the-art performance across objective and subjective evaluations, outperforming existing GAN-, DDPM- and flow-matching-based baselines.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Bias Mitigation in Graph Diffusion Models

Meng Yu
Kun Zhang

Most existing graph diffusion models have significant bias problems. We observe that the forward diffusion’s maximum perturbation distribution in most models deviates from the standard Gaussian distribution, while reverse sampling consistently starts from a standard Gaussian distribution, which results in a reverse-starting bias. Together with the inherent exposure bias of diffusion models, this results in degraded generation quality. This paper proposes a comprehensive approach to mitigate both biases. To mitigate reverse-starting bias, we employ a newly designed Langevin sampling algorithm to align with the forward maximum perturbation distribution, establishing a new reverse-starting point. To address the exposure bias, we introduce a score correction mechanism based on a newly defined score difference. Our approach, which requires no network modifications, is validated across multiple models, datasets, and tasks, achieving state-of-the-art results.

Details

IJCAI Conference 2025 Conference Paper

BridgeVoC: Neural Vocoder with Schrödinger Bridge

Tong Lei
Zhiyu Zhang
Rilin Chen
Meng Yu
Jing Lu
Chengshi Zheng
Dong Yu
Andong Li

While previous diffusion-based neural vocoders typically follow a noise-to-data generation pipe-line, the linear-degradation prior of the mel-spectrogram is often neglected, resulting in limited generation quality. By revisiting the vocoding task and excavating its connection with the signal restoration task, this paper proposes a time-frequency (T-F) domain-based neural vocoder with the Schrödinger Bridge, called BridgeVoC, which is the first to follow the data-to-data generation paradigm. Specifically, the mel-spectrogram can be projected into the target linear-scale domain and regarded as a degraded spectral representation with a deficient rank distribution. Based on this, the Schrödinger Bridge is leveraged to establish a connection between the degraded and target data distributions. During the inference stage, starting from the degraded representation, the target spectrum can be gradually restored rather than generated from a Gaussian noise process. Quantitative experiments on LJSpeech and LibriTTS show that BridgeVoC achieves faster inference and surpasses existing diffusion-based vocoder baselines, while also matching or exceeding non-diffusion state-of-the-art methods across evaluation metrics.

PDF Details DOI

ICRA Conference 2025 Conference Paper

CDMFusion: RGB-T Image Fusion Based on Conditional Diffusion Models via Few Denoising Steps in Open Environments

Luojie Yang
Meng Yu
Lijin Fang
Yi Yang 0009
Yufeng Yue

Multi-modal fusion can improve perceptual robustness and accuracy by fully utilizing multi-source sensor data. Current RGB-T fusion methods still falter with adverse illumination and weather. Recent advances in generative methods have shown the ability to enhance and restore visible images in adverse conditions. However, the fusion of RGB-T based on generative methods has not been studied in depth, due to limited attention given to the degradation of multi-modal features under challenging circumstances. Motivated by this observation, we propose CDMFusion, a three-branch conditional diffusion model that achieves fusion with dynamically enhancing multi-modal features and suppressing high-frequency interference. Specifically, we achieve feature-preserving fusion through three branches and establish a dynamic gating prediction module to adjust the enhancement of multi-modal features adaptively. In addition, considering the high time cost of existing diffusion models for generating fused images, we propose a skip patrol mechanism to achieve accelerated high-quality generation with no need for additional training. Experiments demonstrate our method achieves excellent performance in multiple datasets. The code and datasets are available at https://github.com/yangluojie/CDMFusion.

Details

ICRA Conference 2025 Conference Paper

Open-RGBT: Open-Vocabulary RGB-T Zero-Shot Semantic Segmentation in Open-World Environments

Meng Yu
Yufeng Yue
Luojie Yang
Xunjie He
Yi Yang 0009
Mengyin Fu

Semantic segmentation is a critical technique for effective scene understanding. Traditional RGB-T semantic segmentation models often struggle to generalize across diverse scenarios due to their reliance on pretrained models and predefined categories. Recent advancements in Visual Language Models (VLMs) have facilitated a shift from closedset to open-vocabulary semantic segmentation methods. However, these models face challenges in dealing with intricate scenes, primarily due to the heterogeneity between RGB and thermal modalities. To address this gap, we present Open-RGBT, a novel open-vocabulary RGB-T semantic segmentation model. Specifically, we obtain instance-level detection proposals by incorporating visual prompts to enhance category understanding. Additionally, we employ the CLIP model to assess image-text similarity, which helps correct semantic consistency and mitigates ambiguities in category identification. Empirical evaluations demonstrate that Open-RGBT achieves superior performance in diverse and challenging real-world scenarios, even in the wild, significantly advancing the field of RGB-T semantic segmentation. The project page of Open-RGBT is available at https://OpenRGBT.github.io/.

Details

IROS Conference 2025 Conference Paper

ORA-NET: Enhancing Image Feature Matching through Oriented Overlapping Region Alignment

Te Cui
Meiling Wang 0002
Guangyan Chen
Meng Yu
Yufeng Yue

Image feature matching is a fundamental task in computer vision. Existing local feature matching methods can establish robust correspondences between image pairs. However, these methods heavily rely on dense local image features, making them susceptible to significant perspective differences, characterized by rotation and scale changes. To alleviate this limitation, we introduce a novel oriented Overlapping Region Alignment method, named ORA-NET, which presents a concise and efficient approach to enhance the performance of image feature matching methods. We introduce the Multidirectional Cross-scale Feature Aggregation module to aggregate rotation-equivariant features across multiple scales and model long-range dependencies. Additionally, the Oriented Overlap Alignment module estimates scale and rotation differences within overlapping regions using a coarse-to-fine rotation correction approach. Importantly, our method serves as a plug-and-play module that can be seamlessly integrated into other correspondence matching pipelines. Experimental results demonstrate that ORA-NET significantly enhances the matching performance of existing local feature matching methods, particularly in scenarios involving substantial perspective differences.

Details

IROS Conference 2025 Conference Paper

TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models

Meng Yu
Te Cui
Qitong Chu
Wenjie Song 0001
Yi Yang 0009
Yufeng Yue

Reliable semantic segmentation of open environments is essential for intelligent systems, yet significant problems remain: 1) Existing RGB-T semantic segmentation models mainly rely on low-level visual features and lack high-level textual information, which struggle with accurate segmentation when categories share similar visual characteristics. 2) While SAM excels in instance-level segmentation, integrating it with thermal images and text is hindered by modality heterogeneity and computational inefficiency. To address these, we propose TASeg, a text-aware RGB-T segmentation framework by using Low-Rank Adaptation (LoRA) fine-tuning technology to adapt vision foundation models. Specifically, we propose a Dynamic Feature Fusion Module (DFFM) in the image encoder, which effectively merges features from multiple visual modalities while freezing SAM’s original transformer blocks. Additionally, we incorporate CLIP-generated text embeddings in the mask decoder to enable semantic alignment, which further rectifies the classification error and improves the semantic understanding accuracy. Experimental results across diverse datasets demonstrate that our method achieves superior performance in challenging scenarios with fewer trainable parameters.

Details