8 papers
AutoPruner: Agentic Depth Pruning for Vision-Language-Action Models
Tao Lin, Yikeng Chen, Qiwei Liang +3
Layer pruning reduces the size and inference cost of vision-language-action (VLA) models, but selecting a deployable configuration requires deciding both which layers to remove and…
Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model
Zizhao Yuan, Zhengtu Liang, Taowen Wang +7
Recent advances in action-conditioned world models show promising progress in modeling complex interactions and forecasting future states under diverse action sequences. While thes…
CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
Junhao Cai, Junyu Chen, Deyu Zeng +4
Few-shot anomaly detection remains challenging due to limited training data. Multi-modal anomaly detection (MAD) offers a viable solution, leveraging 3D geometric cues to enrich 2D…
Action-Effect Memory Pretraining for Robot Manipulation
Yijing Zhou, Qiwei Liang, Sitong Zhuang +5
We present AEM, an Action-Effect Memory pretraining framework for robot manipulation that learns compact temporal representations from vision-action history. Unlike prior robot rep…
SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection
Jiaming Liang, Yifeng Zhan, Chunlin Liu +6
Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts. Benefiting from the emergence of large-scale vision--…
Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?
Boyang Cai, Qiwei Liang, Jiawei Li +11
Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling be…
Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning
Qiwei Liang, Boyang Cai, Minghao Lai +6
Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the…
FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors
Tao Lin, Qingwang Wang, Qiwei Liang +2
Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors,…