22 accepted papers
3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or as training constrai…
Online high-definition (HD) map construction is crucial for scaling autonomous driving systems. While Transformer-based methods have become prevalent in online HD map construction, most existing approaches overlook the inherent spatial dependencies and semantic relationships among map elements, whic…
Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and control, despite semantic inference being inherently delayed…
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to more compact student models. However, vanilla KD for image super-resolution (SR) networks yields only limited improvements due to the inherent nature of SR…
Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities. However, current VLA models often struggle with physically infeasible action outputs, complex model structures, or unnecessarily l…
Post-training quantization (PTQ) has played a pivotal role in compressing large language models (LLMs) at ultra-low costs. Although current PTQ methods have achieved promising results by addressing outliers and employing layer- or block-wise loss optimization techniques, they still suffer from signi…
Knowledge distillation (KD) is a promising yet challenging model compression approach that transmits rich learning representations from robust but resource-demanding teacher models to efficient student models. Previous methods for image super-resolution (SR) are often tailored to specific teacher-st…
Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a nov…
Large language models (LLMs) have shown that generative pretraining can distill vast world knowledge into compact token representations. While LLMs encapsulate extensive world knowledge, they remain limited in modeling the behavioral knowledge contained within user interaction histories. User behavi…
In this paper, we introduce a novel estimator for vision-aided inertial navigation systems (VINS), the Preconditioned Cholesky-based Square Root Information Filter (PC-SRIF). When solving linear systems, employing Cholesky decomposition offers superior efficiency but can compromise numerical stabili
Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' information across different spatial locations but ignores…
"In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warped content in non-overlapping regions, despite image stitching having endeavored to preserve the natural structures. Th…
Simultaneous localization and mapping based on 3-D light detection and ranging (LiDAR) tends to degenerate in structural-less environments, leading to a distinct reduction in localization accuracy and mapping precision. This article proposes a point-line LiDAR-visual-inertial odometry (PL-LIVO) base
Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However most AT methods suffer from robust overfitting i.e. a significant generalization gap in adversarial robustness between the training and testing…
Achieving short-distance flight helps improve the efficiency of bipedal robots moving in complex environments (e.g., crossing large obstacles or reaching high places) for rapid emergency missions. This study proposes a design of a flying bipedal robot named Jet-HR2 ( <xref ref-type="fig" rid="fig1"
Animals can use the maneuver of a flipping body and flapping wings to reduce the normal rebound force of impact during landing, decreasing the adsorption force required by the contact point. This capability aids aerial vehicles with landing not only on vertical surfaces, but also on inclined surface
Most SLAM (Simultaneous Localization and Mapping) algorithms are based on the assumption that the scene is static. However, in practice, most real scenes usually contain moving objects. In this letter, we introduce DymSLAM, a dynamic stereo visual SLAM system being capable of reconstructing a 4D (3D
The recent progress of an ongoing project utilizing a ducted-fan propulsion system to improve a humanoid robot's ability to step over large ditches is reported. A novel method (GAS) based on the genetic algorithm with smoothness constraint can effectively minimize the thrust by optimizing the robot'…
The Just Noticeable Difference (JND) reveals the minimum distortion that the Human Visual System (HVS) can perceive. Traditional studies on JND mainly focus on background luminance adaptation and contrast masking. However, the HVS does not perceive visual content based on individual pixels or blocks…
This paper addresses the challenging problem of estimating the general visual attention of people in images. Our proposed method is designed to work across multiple naturalistic social scenarios and provides a full picture of the subject’s attention and gaze. In contrast, earlier works on gaze and a…
This paper reports the latest progress of an ongoing project utilizing a ducted-fan propulsion system to improve a humanoid robot's ability to step over a broad ditch with a height difference between the two sides. This work focuses on the methods of calculating the boundary and optimizing stepping…
In practice, multiple types of distortions are associated with an image quality degradation process. The existing machine learning (ML) based image quality assessment (IQA) approaches generally established a unified model for all distortion types, or each model is trained independently for each dist…