27 papers
Skel-WAM: A Hand-Skeleton-Conditioned World Action Model for Human-to-Robot Manipulation Transfer
Zetao Cai, Yaping Li, Yiqun Wang +8
Robot demonstrations are expensive to collect and often provide limited distributional coverage of task variations. Human videos offer a low-cost source of complementary manipulati…
Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
Boyu Mi, Mengchen Ma, Yifei Yao +10
Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged…
RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
Ziqin Wang, Hao Li, Weijun Wang +5
Existing robot datasets remain expensive to curate, embodiment-specific, and insufficiently annotated with the fine-grained structure required for generalizable reasoning, executio…
Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation
Jiaqi Peng, Xiqian Yu, Delin Feng +10
While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying s…
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
Haoxiang Ma, Junhao Cai, Xiaoxu Xu +26
Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through future prediction. In pract…
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Chenming Zhu, Jingli Lin, Yilin Long +4
While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-or…
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
Zhen Luo, Yixuan Yang, Xudong Xu +5
Generating simulation-ready tabletop scenes from task instructions is an intriguing and promising research direction in the field of Embodied AI. However, existing task-to-scene ge…
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Tianshuo Yang, Guanyu Chen, Yutian Chen +8
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound rea…
FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
Xiaoxu Xu, Hao Li, Jinhui Ye +7
Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geomet…
UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data
Sizhe Yang, Yiman Xie, Zhixuan Liang +4
Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the…
InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
Junhao Cai, Zetao Cai, Jiafei Cao +39
Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, b…
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…
DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos
Juncheng Mu, Sizhe Yang, Yiming Bao +6
Data scarcity fundamentally limits the generalization of bimanual dexterous manipulation, as real-world data collection for dexterous hands is expensive and labor-intensive. Human…
RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
Hao Li, Ziqin Wang, Zi-han Ding +9
Advances in large vision-language models (VLMs) have stimulated growing interest in vision-language-action (VLA) systems for robot manipulation. However, existing manipulation data…
Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction
Sizhe Yang, Linning Xu, Hao Li +4
3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise an…
RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
Boyang Wang, Haoran Zhang, Shujie Zhang +8
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting la…
MM-ACT: Learn from Multimodal Parallel Generation to Act
Haotian Liang, Xinyi Chen, Bin Wang +12
A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we…
InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
Yang Tian, Yuyin Yang, Yiman Xie +13
Recent works explore how real and synthetic data contribute to Vision-Language-Action (VLA) models' generalization. While current VLA models have shown the strong effectiveness of…
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
Baoqi Pei, Yifei Huang, Jilan Xu +5
Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fi…
Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning
Weijie Shen, Yitian Liu, Yuhao Wu +10
Vision-Language-Action (VLA) models are experiencing rapid development and demonstrating promising capabilities in robotic manipulation tasks. However, scaling up VLA models presen…
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Xinyi Chen, Yilun Chen, Yanwei Fu +26
We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its…
X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
Jinliang Zheng, Jianxiong Li, Zhihao Wang +12
Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To…
Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
Ganlin Yang, Tianyi Zhang, Haoran Hao +15
While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (V…
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Shaopeng Zhai, Qi Zhang, Tianyi Zhang +7
Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLA…