4 citations · 12 across the 12 of their papers we have counts for
13 papers
Data-Free Continual Learning for World Action Model with Rectified Generative Replay
Kaipeng Fang, Hangxu Liu, Chaojian Shi +5
World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned tasks under sequential fine-tuning. Ex…
Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training
Ping Chen, Zhuohong Deng, Ping Li +6
Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed…
Saga: Capturing Multi-granularity Semantics from Massive Unlabelled IMU Data for User Perception
Yunzhe Li, Facheng Hu, Hongzi Zhu +4
Inertial measurement units (IMUs), have been prevalently used in a wide range of mobile perception applications such as activity recognition and user authentication, where a large…
Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception
Yunzhe Li, Facheng Hu, Hongzi Zhu +5
A wide range of user perception applications leverage inertial measurement unit (IMU) data for online prediction. However, restricted by the non-i.i.d. nature of IMU data collected…
A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices
Yunzhe Li, Hongzi Zhu, Zhuohong Deng +5
Emerging Artificial Intelligence of Things (AIoT) applications desire online prediction using deep neural network (DNN) models on mobile devices. However, due to the movement of de…
SimGen: Simulator-conditioned Driving Scene Generation
Yunsong Zhou, Michael Simon, Zhenghao Peng +4
Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the…
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
Quan Liu, Hongzi Zhu, Zhenxi Wang +3
Registration of point clouds collected from a pair of distant vehicles provides a comprehensive and accurate 3D view of the driving scenario, which is vital for driving safety rela…
Embodied Understanding of Driving Scenarios
Yunsong Zhou, Linyan Huang, Qingwen Bu +7
Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded…
Density-invariant Features for Distant Point Cloud Registration
Quan Liu, Hongzi Zhu, Yunsong Zhou +3
Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area…
DistSim: A performance model of large-scale hybrid distributed DNN training
Guandong Lu, Runzhe Chen, Yakai Wang +8
With the ever-increasing computational demand of DNN training workloads, distributed training has been widely adopted. A combination of data, model and pipeline parallelism strateg…
APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction
Quan Liu, Yunsong Zhou, Hongzi Zhu +2
For many driving safety applications, it is of great importance to accurately register LiDAR point clouds generated on distant moving vehicles. However, such point clouds have extr…
MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation
Yunsong Zhou, Quan Liu, Hongzi Zhu +3
Monocular 3D object detection (Mono3D) in mobile settings (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Due to the near-far disparity phenomenon o…
MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
Yunsong Zhou, Hongzi Zhu, Quan Liu +2
Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt…