10 papers
Acting Through Registers
Yiwei Zhang, Yantai Yang, Jin Gao +7
World Action Models (WAMs) use generative visual representations to condition robot actions, yet how these representations organize action-relevant information remains poorly under…
Exploring the Limits of Combinatorial Generalization in Embodied Manipulation
Xupeng Zhang, Yantai Yang, Chang Guo +2
In embodied manipulation, Vision Language Action (VLA) models can execute atomic skills, but long-horizon manipulation requires recombining these skills without demonstrations for…
GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
Jiawei Zhang, Yiming Yan, Chao Liang +8
Training embodied agents in the real world requires skilled operators and expensive hardware. Simulation environments offer a compelling alternative by enabling large-scale, cost-e…
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
Junlong Ke, Zichen Wen, Boxue Yang +6
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment.…
QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
Yuhao Xu, Yantai Yang, Zhenyang Fan +4
The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on r…
Grounding and Enhancing Informativeness and Utility in Dataset Distillation
Shaobo Wang, Yantai Yang, Guo Chen +5
Dataset Distillation (DD) seeks to create a compact dataset from a large, real-world dataset. While recent methods often rely on heuristic approaches to balance efficiency and qual…
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
Shuai Yuan, Yantai Yang, Xiaotian Yang +4
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offlin…
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
Yantai Yang, Yuhao Wang, Zichen Wen +5
Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high co…
DRUPI: Dataset Reduction Using Privileged Information
Shaobo Wang, Youxin Jiang, Tianle Niu +9
Dataset Condensation (DC) seeks to select or distill samples from large datasets into smaller subsets while preserving performance on target tasks. Existing methods primarily focus…
Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation
Shaobo Wang, Yantai Yang, Qilong Wang +3
Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical explo…