8 papers · 1 filter
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
Kuanning Wang, Ke Fan, Chenhao Qiu +5
Robust robotic manipulation requires not only predicting how the scene evolves over time, but also recognizing task-relevant objects in complex scenes. However, existing VLA models…
Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making
Shufeng Nan, Mengtian Li, Sixiao Zheng +3
We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative…
ST4VLA: Spatially Guided Training for Vision-Language-Action Models
Jinhui Ye, Fangjing Wang, Ning Gao +9
Large vision-language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor ac…
Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
Haitao Lin, Hanyang Yu, Jingshun Huang +5
Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-spec…
ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
Zhenyang Liu, Yongchong Gu, Yikai Wang +2
Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action pr…
DST-Calib: A Dual-Path, Self-Supervised, Target-Free LiDAR-Camera Extrinsic Calibration Network
Zhiwei Huang, Yanwei Fu, Yi Zhou +3
LiDAR-camera extrinsic calibration is essential for multi-modal data fusion in robotic perception systems. However, existing approaches typically rely on handcrafted calibration ta…
MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation
Changli Wu, Haodong Wang, Jiayi Ji +5
Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with o…
VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
Sixiao Zheng, Minghao Yin, Wenbo Hu +3
Video world models aim to simulate dynamic, real-world environments, yet existing methods struggle to provide unified and precise control over camera and multi-object motion, as vi…