SparkLab

SparkLab is a research group whose founding team comes from Tsinghua University and the University of Hong Kong, united by a shared commitment to advancing trustworthy physical intelligence. Guided by a research-driven vision, we pursue foundational work across algorithms, evaluation, hardware, and data, building a full-stack research team where ideas are not only conceived, but rigorously tested, embodied in real systems, and made reliable in the physical world.

If you are interested in research collaboration or have any questions, please contact us at sparklab@xsparkai.com.We also have several open research positions. See our Career Opportunities page for details.

Algorithm

Our Embodied AI Model is On The Way.

Coming Soon

Method

HumanTouch: A Multimodal System for Scalable Human-Hand Tactile Acquisition

Motion shows what a hand does; touch reveals how the physical world responds. This connection is essential for robots to understand contact-rich interaction rather than merely imitate trajectories. Yet tactile data is useful only when real contact can be distinguished from sensor artifacts and drift. HumanTouch combines touch, hand motion, and vision within a calibrated and traceable acquisition system. It treats scalability not simply as recording more hours, but as collecting contact data that remains interpretable and trustworthy.

Human Touch tactile capture system overview

Theory

Trustworthy Embodied Systems: Framework and Levels

Toward trustworthy embodied intelligence: we systematically review prior work and propose a six-level framework (T0–T5) for grading trustworthiness.

Trustworthiness levels for embodied intelligence systems from T0 to T5

2026/7/28

Research

Previous research

Nature Sensors

Published:2026/1/15

Biomimetic multimodal tactile sensing enables human-like robotic perception

SuperTac fits pigeon-inspired multispectral vision, triboelectric sensing, and inertial sensing into a 1-millimeter flexible tactile skin. Paired with DOVE, an 8.5-billion-parameter tactile-language model, it transforms complex tactile signals into interpretable, actionable semantic information. Achieving over 94% accuracy across texture, material, slip, collision, and color recognition, SuperTac advances robotic touch from signal acquisition toward human-like perception and world understanding.

Overview of the RoboTwin 2.0 data generator and benchmark

ICML 2026

Published:2025/6/28

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

We built a general-purpose bimanual manipulation data generator and benchmark, introducing strong domain randomization as an evaluation measure. RoboTwin is now among the most cited bimanual manipulation benchmarks in the community. As of July 30, 2026, the series has received more than 600 Google Scholar citations, 2,500 GitHub stars, and 600,000 Hugging Face downloads.

Overview of the UniVTAC simulation, learning, and benchmarking platform

ICRA 2026 ViTac · Best Paper

Published:2026/8/10

UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking

We present the field's first visuo-tactile simulation data synthesizer and evaluation suite, systematically study tactile data synthesis methods, and close the gap from simulation to real world deployment.

ManiTwin's 100,000-object manipulation-ready dataset

Under Review

ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K

Together with Deemos Tech, we introduce the first large-scale rigid-object dataset with 100,000 manipulation-annotated assets, ready to plug directly into simulation-based data generation pipelines.