3 accepted papers
Multi-token prediction (MTP) architecture is widely adopted in LLMs. MTP blocks can be appended to the tail of model to predict additional tokens. However, when training with pipeline parallel, MTP leads to more pipeline bubbles and deteriorates the pipeline efficiency. Based on in-depth analysis of…
Scene graph generation (SGG) is a structured approach to understanding real-world scenes with complex relations, which can enhance UAV autonomy in unfamiliar environments. However, SGG typically has numerous model parameters that require considerable computational resources. This paper proposes a re
The LiDAR-inertial odometry (LIO) and the ultra-wideband (UWB) have been integrated to achieve driftless positioning in global navigation satellite system (GNSS)-denied environments. However, the UWB may be affected by systematic range errors (such as the clock drift and the antenna phase center off