Related papers: NOVA: Next-step Open-Vocabulary Autoregression for…
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to…
Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the…
Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the…
Multi-object tracking is a cornerstone capability of any robotic system. The quality of tracking is largely dependent on the quality of the detector used. In many applications, such as autonomous vehicles, it is preferable to over-detect…
3D object reconstruction and multilevel segmentation are fundamental to computer vision research. Existing algorithms usually perform 3D scene reconstruction and target objects segmentation independently, and the performance is not fully…
Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for…
In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT…
Referring understanding is a fundamental task that bridges natural language and visual content by localizing objects described in free-form expressions. However, existing works are constrained by limited language expressiveness, lacking the…
We present the Habitat-Matterport 3D Open Vocabulary Object Goal Navigation dataset (HM3D-OVON), a large-scale benchmark that broadens the scope and semantic range of prior Object Goal Navigation (ObjectNav) benchmarks. Leveraging the…
We introduce EMMA, an End-to-end Multimodal Model for Autonomous driving. Built upon a multi-modal large language model foundation like Gemini, EMMA directly maps raw camera sensor data into various driving-specific outputs, including…
Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed…
Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods. However, NAT models often suffer from the…
Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories using arbitrary textual descriptions. While existing methods leverage…
Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are constrained by their dependence on hand-crafted skills, extensive…
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…
While separately leveraging monocular 3D object detection and 2D multi-object tracking can be straightforwardly applied to sequence images in a frame-by-frame fashion, stand-alone tracker cuts off the transmission of the uncertainty from…
3D environment recognition is essential for autonomous driving systems, as autonomous vehicles require a comprehensive understanding of surrounding scenes. Recently, the predominant approach to define this real-life problem is through 3D…
Digitized histopathology analysis involves complex, time-intensive workflows and specialized expertise, limiting its accessibility. We introduce NOVA, an agentic framework that translates scientific queries into executable analysis…
Functional verification relies on large simulation-based regressions. Traditional test selection relies on static test features and overlooks actual coverage behavior, wasting substantial simulation time, while constrained random stimuli…
Autonomous driving (AD) perception today relies heavily on deep learning based architectures requiring large scale annotated datasets with their associated costs for curation and annotation. The 3D semantic data are useful for core…