Hongyu Wang

Hui Li, Changhao Jiang, Hongyu Wang et al.

The ability to reason from audio, including speech, paralinguistic cues, environmental sounds, and music, is essential for AI agents to interact effectively in real-world scenarios. Existing benchmarks mainly focus on static or single-scene settings and do not fully capture scenarios where multiple speakers, unfolding events, and heterogeneous audio sources interact. To address these challenges, we introduce MDAR, a benchmark for evaluating models on complex, multi-scene, and dynamically evolving audio reasoning tasks. MDAR comprises 3,000 carefully curated question-answer pairs linked to diverse audio clips, covering five categories of complex reasoning and spanning three question types. We benchmark 26 state-of-the-art audio language models on MDAR and observe that they exhibit limitations in complex reasoning tasks. On single-choice questions, Qwen2.5-Omni (open-source) achieves 76.67% accuracy, whereas GPT-4o Audio (closed-source) reaches 68.47%; however, GPT-4o Audio substantially outperforms Qwen2.5-Omni on the more challenging multiple-choice and open-ended tasks. Across all three question types, no model achieves 80% performance. These findings underscore the unique challenges posed by MDAR and its value as a benchmark for advancing audio reasoning research.Code and benchmark can be found at https://github.com/luckyerr/MDAR.

Hongyu Wang, Xiaotao Liu, Yifan Li et al.

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the target based on the appearance matching results. However, these RGBT trackers have very limited exploitation of temporal information, either ignoring temporal information or exploiting it through online sampling and training. The former struggles to cope with the object state changes, while the latter neglects the correlation between spatial and temporal information. To alleviate these limitations, we propose a novel Temporal Adaptive RGBT Tracking framework, named as TATrack. TATrack has a spatio-temporal two-stream structure and captures temporal information by an online updated template, where the two-stream structure refers to the multi-modal feature extraction and cross-modal interaction for the initial template and the online update template respectively. TATrack contributes to comprehensively exploit spatio-temporal information and multi-modal information for target localization. In addition, we design a spatio-temporal interaction (STI) mechanism that bridges two branches and enables cross-modal interaction to span longer time scales. Extensive experiments on three popular RGBT tracking benchmarks show that our method achieves state-of-the-art performance, while running at real-time speed.

Hongyu Wang, Jingquan Wang, Dan Negrut

Data-driven modeling of constrained multibody systems faces two persistent challenges: high computational cost and limited long-term prediction accuracy. To address these issues, we introduce the Flow-Matching Neural Ordinary Differential Equation (FNODE), a framework that learns acceleration vector fields directly from trajectory data. By reformulating the training objective to supervise accelerations rather than integrated states, FNODE eliminates the need for backpropagation through an ODE solver, which represents a bottleneck in traditional Neural ODEs. Acceleration targets are computed efficiently using numerical differentiation techniques, including a hybrid Fast Fourier Transform (FFT) and Finite Difference (FD) scheme. We evaluate FNODE on a diverse set of benchmarks, including the single and triple mass-spring-damper systems, double pendulum, slider-crank, and cart-pole. Across all cases, FNODE consistently outperforms existing approaches such as Multi-Body Dynamic Neural ODE (MBD-NODE), Long Short-Term Memory (LSTM) networks, and Fully Connected Neural Networks (FCNN), demonstrating good accuracy, generalization, and computational efficiency.

Pingping Zhang, Wei Liu, Dong Wang et al.

In this paper, we propose a novel effective non-rigid object tracking framework based on the spatial-temporal consistent saliency detection. In contrast to most existing trackers that utilize a bounding box to specify the tracked target, the proposed framework can extract accurate regions of the target as tracking outputs. It achieves a better description of the non-rigid objects and reduces the background pollution for the tracking model. Furthermore, our model has several unique features. First, a tailored fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a novel multi-scale multi-region mechanism is proposed to generate local saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, local saliency maps are fused via a weighted entropy method, resulting in a final discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the predicted saliency maps. By utilizing a spatial-temporal consistent saliency map (STCSM), we conduct target-background classification and use a simple fine-tuning scheme for online updating. Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.

Yifan Wang, Lijun Wang, Hongyu Wang et al.

One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN. As opposed to existing approaches, the proposed method conducts upsampling in the latent feature space with filters that are optimized for the task of image SR. In addition, the HR reconstruction is performed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information, ensuring more accurate restoration of HR images. To facilitate network training, a new training approach is designed, which jointly trains the proposed deep network with a relatively shallow network, leading to faster convergence and more superior performance. The proposed method is extensively evaluated on widely adopted data sets and improves the performance of state-of-the-art methods with a considerable margin. Moreover, in-depth ablation studies are conducted to verify the contribution of different network designs to image SR, providing additional insights for future research.