11 papers
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
Wencheng Ye, Yi Bin, Yujuan Ding +7
Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening eviden…
WSA: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
Jiahao Jiang, Jianing Zhang, Zhenhan Yin +8
Recent advances in embodied AI have established robot foundation models (RFMs) as the dominant approach for generalist robotic systems to date. By leveraging imitation learning on…
TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
Xiao Cai, Pengpeng Zeng, Ji Zhang +3
Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-traine…
DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
Siyuan Xu, Tianshi Wang, Fengling Li +2
Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and…
DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset
Hengyu Shen, Tiancheng Gu, Bin Qin +10
Vision-Language Pre-training (VLP) models have achieved remarkable success by leveraging large-scale image-text pairs. While English-centric models like CLIP and SigLIP benefit fro…
Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
Yipeng Chen, Wentao Tan, Lei Zhu +4
Existing Vision-Language-Action (VLA) models often struggle to generalize to long-horizon tasks due to their heavy reliance on immediate observations. While recent studies incorpor…