Related papers: CodeMerge: Codebook-Guided Model Merging for Robus…
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into…
Autonomous driving sensors generate an enormous amount of data. In this paper, we explore learned multimodal compression for autonomous driving, specifically targeted at 3D object detection. We focus on camera and LiDAR modalities and…
Cameras and LiDARs are both important sensors for autonomous driving, playing critical roles in 3D object detection. Camera-LiDAR Fusion has been a prevalent solution for robust and accurate driving perception. In contrast to the vast…
In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts…
LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies focus on cross-dataset shifts, such as changes in…
Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…
3D object detection serves as the core basis of the perception tasks in autonomous driving. Recent years have seen the rapid progress of multi-modal fusion strategies for more robust and accurate 3D object detection. However, current…
Autonomous racing has rapidly gained research attention. Traditionally, racing cars rely on 2D LiDAR as their primary visual system. In this work, we explore the integration of an event camera with the existing system to provide enhanced…
Accurately localizing 3D objects like pedestrians, cyclists, and other vehicles is essential in Autonomous Driving. To ensure high detection performance, Autonomous Vehicles complement RGB cameras with LiDAR sensors, but effectively…
In medical imaging, vision-language models face a critical duality: pretrained networks offer broad robustness but lack subtle, modality-specific characteristics, while fine-tuned expert models achieve high in-distribution accuracy yet…
Model merging is an effective post-training strategy for composing capabilities in large language models without joint retraining. We study this in the supervised fine-tuning (SFT) stage, where multiple capability-based SFT checkpoints --…
3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance. To address this issue, we propose an advanced…
Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…
This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and…
Model merging combines knowledge from separately fine-tuned models, yet the factors driving its success remain poorly understood. While recent work treats mergeability as an intrinsic property of the models, we show with an…
Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount…
Autonomous Driving Systems (ADSs) rely on Deep Neural Networks, allowing vehicles to navigate complex, open environments. However, the unpredictability of these scenarios highlights the need for rigorous system-level testing to ensure…
The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving environments, which can lead to safety-critical failures in…
Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching…
Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conflicts by sparsifying task vectors or promoting orthogonality…