Related papers: LISA: Language-guided Interference-aware Spatial-F…
Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous…
Channel and spatial attentions have respectively brought significant improvements in extracting feature dependencies and spatial structure relations for various downstream vision tasks. While their combination is more beneficial for…
Traffic prediction has gradually attracted the attention of researchers because of the increase in traffic big data. Therefore, how to mine the complex spatio-temporal correlations in traffic data to predict traffic conditions more…
Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans perform such a correlation with a strong linguistic understanding of the visual world. However, even the best performing…
When uncertainty is high, self-driving vehicles may halt for safety and benefit from the access to remote human operators who can provide high-level guidance. This paradigm, known as {shared autonomy}, enables autonomous vehicle and remote…
The looking-in-looking-out (LILO) framework has enabled intelligent vehicle applications that understand both the outside scene and the driver state to improve safety outcomes, with examples in smart airbag deployment, takeover time…
The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…
Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers from inherent limitations: (1) the attention kernel is not…
Accurate environmental perception is critical for advanced driver assistance systems (ADAS). Light detection and ranging (LiDAR) systems play a crucial role in ADAS; they can reliably detect obstacles and help ensure traffic safety.…
Data from the Laser Interferometer Space Antenna (LISA) is expected to be dominated by frequency noise from its lasers. However the noise from any one laser appears more than once in the data and there are combinations of the data that are…
Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than…
Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two…
Modeling task-driven attention in driving is a fundamental challenge for both autonomous vehicles and cognitive science. Existing methods primarily predict where drivers look by generating spatial heatmaps, but fail to capture the cognitive…
We discuss the baseline optical configuration for the Laser Interferometer Space Antenna (LISA) mission, in which the lasers are not free-running, but rather one of them is used as the main frequency reference generator (the {\it master})…
The sparse object detection paradigm shift towards dense 3D semantic occupancy prediction is necessary for dealing with long-tail safety challenges for autonomous vehicles. Nonetheless, the current voxelization methods commonly suffer from…
Foresighted robot navigation in dynamic indoor environments with cost-efficient hardware necessitates the use of a lightweight yet dependable controller. So inferring the scene dynamics from sensor readings without explicit object tracking…
A unique challenge for data analysis with the Laser Interferometer Space Antenna (LISA) is that the noise backgrounds from instrumental noise and astrophysical sources will change significantly over both the year and the entire mission.…
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this…
Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly…
In recent years, the integration of vision and language understanding has led to significant advancements in artificial intelligence, particularly through Vision-Language Models (VLMs). However, existing VLMs face challenges in handling…