21 papers
Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement
Jiarui Yang, Jiajin Zhang, Bin Zhu +2
Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually collected experience. We pr…
OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots
Kaixiang Lu, Haiyu Lan, Chunxiao Qiao +6
Assembly, wear, and component replacement perturb the sensor extrinsics and joint zeros encoded by a humanoid CAD model. Existing procedures calibrate one sensor pair or require ex…
OVIP-SG: Open-Vocabulary Instance-Preserving Scene Graphs for Mapping and Retrieval of Small, Fine-Grained Objects
Tianjing Hao, Haiyu Lan, Angsong Li +6
Integrating open-vocabulary perception into object-level 3D scene graphs is a double-edged sword. While vision-language detectors recover long-tail categories and small, fine-grain…
TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation
Jiarui Yang, Yehao Lu, Yuning Su +9
Vision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not reliably capture recent phys…
V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models
Yehao Lu, Jiarui Yang, Yuning Su +10
Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation by integrating visual perception, language understanding, and continuous action c…
StructRL: Structured Action-Space Exploration for Flow-Based VLAs
Jiarui Yang, Bin Zhu, Jingjing Chen +4
Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emerging as a key technique for ad…
GDLAM: Group-Disentangled Latent Action Model for Highly Disentangled Embodied Pretraining
Jiarui Yang, Jiawei Li, Jiale Zhang +5
Latent action models (LAMs) learn action-related representations from action-free videos via self-supervised future prediction, offering a scalable paradigm for embodied intelligen…
In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use
Jiarui Yang, Wen Huang, Jiale Zhang +2
Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior cloning: a policy imitates expe…
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models
Jiarui Yang, Jiale Zhange, Jiawei Li +5
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by…
Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies
Jiarui Yang, Yehao Lu, Yuning Su +9
Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation, yet complex contact-rich tasks often benefit from multi-camera observations that joint…
IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion
Lizhou Lin, Songpengcheng Xia, Zengyuan Lai +3
Capturing full-body human motion with object interactions is crucial for AR/VR and robotics applications, yet it remains challenging for conventional vision-based methods due to oc…
RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
Wen Huang, Jiarui Yang, Tao Dai +4
Visual manipulation localization (VML) aims to identify tampered regions in images and videos, a task that has become increasingly challenging with the rise of advanced editing too…
RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence
Zengyuan Lai, Jiarui Yang, Songpengcheng Xia +6
Millimeter-wave radar offers a privacy-preserving and environment-robust alternative to vision-based sensing, enabling human motion analysis in challenging conditions such as low l…
Suite-IN++: A FlexiWear BodyNet Integrating Global and Local Motion Features from Apple Suite for Robust Inertial Navigation
Lan Sun, Songpengcheng Xia, Jiarui Yang +1
The proliferation of wearable technology has established multi-device ecosystems comprising smartphones, smartwatches, and headphones as critical enablers for ubiquitous pedestrian…
mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction
Jiarui Yang, Songpengcheng Xia, Zengyuan Lai +4
Millimeter-wave (mmWave) radar offers robust sensing capabilities in diverse environments, making it a highly promising solution for human body reconstruction due to its privacy-fr…
Suite-IN: Aggregating Motion Features from Apple Suite for Robust Inertial Navigation
Lan Sun, Songpengcheng Xia, Junyuan Deng +4
With the rapid development of wearable technology, devices like smartphones, smartwatches, and headphones equipped with IMUs have become essential for applications such as pedestri…
SMART: Scene-motion-aware human action recognition framework for mental disorder group
Zengyuan Lai, Jiarui Yang, Songpengcheng Xia +4
Patients with mental disorders often exhibit risky abnormal actions, such as climbing walls or hitting windows, necessitating intelligent video behavior monitoring for smart health…
Generative Pre-Trained Diffusion Paradigm for Zero-Shot Time Series Forecasting
Jiarui Yang, Tao Dai, Naiqi Li +6
In recent years, generative pre-trained paradigms such as Large Language Models (LLMs) and Large Vision Models (LVMs) have achieved revolutionary advancements and widespread real-w…
MMBaT: A Multi-task Framework for mmWave-based Human Body Reconstruction and Translation Prediction
Jiarui Yang, Songpengcheng Xia, Yifan Song +2
Human body reconstruction with Millimeter Wave (mmWave) radar point clouds has gained significant interest due to its ability to work in adverse environments and its capacity to mi…
Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors
Yu Zhang, Songpengcheng Xia, Lei Chu +3
This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages…
Timestamp-supervised Wearable-based Activity Segmentation and Recognition with Contrastive Learning and Order-Preserving Optimal Transport
Songpengcheng Xia, Lei Chu, Ling Pei +3
Human activity recognition (HAR) with wearables is one of the serviceable technologies in ubiquitous and mobile computing applications. The sliding-window scheme is widely adopted…