Yiru Yang

Yiru Yang, Junling Wang, Nishant Kumar Singh et al.

A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which will make slightly distinct kinds of predictions and errors on the same data, and thus improve the average predictions and robustness. However, making predictions using a whole ensemble of models is cumbersome and computationally too expensive to allow deployment to a large number of users, especially if the models are large neural nets. In response to this, we introduce a layer and point wise projection mapping, which maps student and teacher representations into an aligned high-dimensional embedding space during training process. The proposed approach combined with LoRA injection reduces the student model trainable parameters to less than 1% of the teacher model, while significantly improving word error rate (WER) compared to other distillation methods, as demonstrated in ablation studies. Unlike a mixture of experts, our method can be trained rapidly and in parallel.

Yiru Yang, Zhuojie Wu, Quentin Marguet et al.

In the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes serve as the critical bridge connecting low-level geometric sensing with high-level semantic understanding. We present DINO\_4D, introducing frozen DINOv3 features as structural priors, injecting semantic awareness into the reconstruction process to effectively suppress semantic drift during dynamic tracking. Experiments on the Point Odyssey and TUM-Dynamics benchmarks demonstrate that our method maintains the linear time complexity $O(T)$ of its predecessors while significantly improving Tracking Accuracy (APD) and Reconstruction Completeness. DINO\_4D establishes a new paradigm for constructing 4D World Models that possess both geometric precision and semantic understanding.

Longxiang Jiao, Lukas Hofmann, Yiru Yang et al.

While micro-scale traffic simulations provide essential data for urban planning, they are rarely coupled with the high-fidelity visualization or auralization necessary for effective stakeholder communication. In this work, we present a real-time 4D visualization framework that couples the SUMO traffic with a photorealistic, geospatially accurate VR representation of Zurich in Unreal Engine 5. Our architecture implements a robust C++ data pipeline for synchronized vehicle visualization and features an Open Sound Control (OSC) interface to support external auralization engines. We validate the framework through a user study assessing the correlation between simulated traffic dynamics and human perception. Results demonstrate a high degree of perceptual alignment, where users correctly interpret safety risks from the 4D simulation. Furthermore, our findings indicate that the inclusion of spatialized audio alters the user's sense of safety, showing the importance of multimodality in traffic simulations.