12 accepted papers
Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the support set for task induction. In standard ICL setting, once the task is induced, its decision boundary, i.e., the criterion, remains fixed. However, in re…
Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered, previously unseen scene. Existing proposal-based approaches…
Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the sampled outputs of the target model. Existing methods mainly ac
We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGB-D cameras and a HoloLens headset for data collection, avoiding the use of expensive 3D scanners or motion capture systems. We propos…
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity…
This letter introduces <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Nav</b>igation <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Tr</b>ansformer (NavTr), a novel framework for object-goal navigation
Dynamic early exit has demonstrated great potential in coping with the sharply increasing number of pre-trained language model parameters, which can achieve a good trade-off between performance and efficiency. The existing early exit paradigm relies on training parametrical internal classifiers at e…
Agile quadrotor flight relies on rapidly planning and accurately tracking time-optimal trajectories, a technology critical to their application in the wild. However, the computational burden of computing time-optimal trajectories based on the full quadrotor dynamics (typically on the order of minute
With the development of multilingual pre-trained language models (mPLMs), zero-shot cross-lingual transfer shows great potential. To further improve the performance of cross-lingual transfer, many studies have explored representation misalignment caused by morphological differences but neglected the…
Distribution-to-distribution-based lidar odometry is known for its good accuracy, while it cannot run in real-time when the number of points is large. To alleviate this problem, Faster Generalized Iterative Closest Point (FasterGICP) is proposed in this letter, in which an acceptance-rejection sampl
Loop closure can effectively eliminate the accumulated error and plays an important role in Simultaneous Localization and Mapping (SLAM). There remains challenges in loop detection and loop correction due to the large viewpoints difference and the environment appearance changes. In this letter, we p
This letter presents a point cloud based loop-closure method to correct long-term drifts in Light Detection and Ranging based Simultaneous Localization and Mapping systems. In the method, we formulate each keyframe as a fully-connected graph with nodes representing planes. To detect loop-closures, t