12 papers
Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation
Yao He, Gan Sun, Wenqi Liang +2
Similar to the natural capabilities of humans to sequentially learn new tasks, robots with Vision-Language-Action (VLA) models should possess lifelong learning ability to learn a n…
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
Jiahua Dong, Wenqi Liang, Hongliu Li +7
Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistic…
FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
Qian He, Zhenshuo Yang, Wenqi Liang +3
Visuomotor policies aim to learn complex manipulation tasks from expert demonstrations. However, generating smooth and coherent trajectories remains challenging, as it requires bal…
Bring Your Dreams to Life: Continual Text-to-Video Customization
Jiahua Dong, Xudong Wang, Wenqi Liang +7
Customized text-to-video generation (CTVG) has recently witnessed great progress in generating tailored videos from user-specific text. However, most CTVG methods assume that perso…
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
Wenqi Liang, Gan Sun, Yao He +5
Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale…
Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation
Jiahua Dong, Hui Yin, Wenqi Liang +5
Video instance segmentation (VIS) has gained significant attention for its capability in tracking and segmenting object instances across video frames. However, most of the existing…
GLAM: Global-Local Variation Awareness in Mamba-based World Model
Qian He, Wenqi Liang, Chunhui Hao +2
Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithm…
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Jiahua Dong, Wenqi Liang, Hongliu Li +5
Custom diffusion models (CDMs) have attracted widespread attention due to their astonishing generative ability for personalized concepts. However, most existing CDMs unreasonably a…
MuseumMaker: Continual Style Customization without Catastrophic Forgetting
Chenxi Liu, Gan Sun, Wenqi Liang +3
Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting…
Never-Ending Behavior-Cloning Agent for Robotic Manipulation
Wenqi Liang, Gan Sun, Yao He +3
Relying on multi-modal observations, embodied robots (e.g., humanoid robots) could perform multiple robotic manipulation tasks in unstructured real-world environments. However, mos…
Create Your World: Lifelong Text-to-Image Diffusion
Gan Sun, Wenqi Liang, Jiahua Dong +3
Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image transla…
I3DOD: Towards Incremental 3D Object Detection via Prompting
Wenqi Liang, Gan Sun, Chenxi Liu +2
3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could caus…