arXiv subjects

Jiacheng Bao

Publications and source records attributed to Jiacheng Bao.

16 recordsLinked to original sources

arXiv2026

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors assume human biomechanics, actuation, mass distribution, and contact strategies. When such motions are directly retargeted to humanoid robots, the resulting trajectories may satisfy geometric constraints (e.g., joint limits and pose continuity) and appear kinematically reasonable. However, they frequently violate the physical feasibility required for real-world execution. To address these issues, we present PhyGile, a unified framework that closes the loop between robot-native motion generation and General Motion Tracking (GMT). PhyGile performs physics-prefix-guided robot-native motion generation at inference time, directly generating robot-native motions in a 262-dimensional skeletal space with physics-guided prefixes, thereby eliminating inference-time retargeting artifacts and reducing generation-execution discrepancies. Before physics-prefix adaptation, we train the GMT controller with a curriculum-based mixture-of-experts scheme, followed by post-training on unlabeled motion data to improve robustness over large-scale robot motions. During physics-prefix adaptation, the GMT controller is further fine-tuned with generated objectives under physics-derived prefixes, enabling agile and stable execution of complex motions on real robots. Extensive offline and real-robot experiments demonstrate that PhyGile expands the frontier of text-driven humanoid control, enabling stable tracking of agile, highly difficult whole-body motions that go well beyond walking and low-dynamic motions typically achieved by prior methods.

cs.RO↗

arXiv2026

Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot

The integration of imitation and reinforcement learning has enabled remarkable advances in humanoid whole-body control, facilitating diverse human-like behaviors. However, research on environment-dependent motions remains limited. Existing methods typically enforce rigid trajectory tracking while neglecting physical interactions with the environment. We observe that humans naturally exploit a "weightless" state during non-self-stabilizing (NSS) motions--selectively relaxing specific joints to allow passive body--environment contact, thereby stabilizing the body and completing the motion. Inspired by this biological mechanism, we design a weightlessness-state auto-labeling strategy for dataset annotation; and we propose the Weightlessness Mechanism (WM), a method that dynamically determines which joints to relax and to what level, together enabling effective environmental interaction while executing target motions. We evaluate our approach on 3 representative NSS tasks: sitting on chairs of varying heights, lying down on beds with different inclinations, and leaning against walls via shoulder or elbow. Extensive experiments in simulation and on the Unitree G1 robot demonstrate that our WM method, trained on single-action demonstrations without any task-specific tuning, achieves strong generalization across diverse environmental configurations while maintaining motion stability. Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.

cs.RO↗

arXiv2026

RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting

Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting remains particularly challenging due to the stringent requirements on agility and stability. While imitation learning enables robots to execute human-like fighting skills, existing approaches often rely on switching among multiple single-skill policies or employing a general policy to imitate input reference motions. These strategies suffer from instability when transitioning between skills, as the mismatch of initial and terminal states across skills or reference motions introduces out-of-domain disturbances, resulting in unsmooth or unstable behaviors. In this work, we propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition. Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions with stability and smoothness during skill transitions. Furthermore, we design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration that can be seamlessly interrupted or transit action policies at any time. Extensive experiments in simulation demonstrate the effectiveness of the proposed framework, and real-world deployment on the Unitree G1 humanoid robot further validates its robustness and applicability.

cs.RO↗

arXiv2026

ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data

Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperation-free framework that learns humanoid whole-body interaction from human egocentric videos paired with synchronized whole-body motion and text annotations. ZeroWBC adopts a generation-then-tracking formulation to tackle the static scene whole-body interaction control problem. Given an initial egocentric image and a language instruction, a fine-tuned Vision-Language Model generates future human whole-body motion tokens, which are decoded into continuous motions and retargeted to the humanoid. The resulting reference motions, together with root and key body-part trajectories, are then executed by a general interactive motion tracking policy. To improve interaction performance, we introduce an interaction-oriented tracking reward that prioritizes global root and key body-part trajectory alignment while preserving natural whole-body motion. Experiments on the Unitree G1 humanoid robot show that ZeroWBC enables diverse scene-aware behaviors without robot teleoperation demonstrations. These results suggest a scalable paradigm for learning natural humanoid whole-body interaction from human egocentric data.

cs.RO↗

arXiv2026

EO-1: An Open Unified Embodied Foundation Model for General Robot Control

The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, we introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models. Project Page: https://eo-robotics.ai/eo-1.

cs.RO↗

arXiv2026

StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians

Current 3D Gaussian Splatting stylization approaches are limited in their ability to represent diverse artistic styles, frequently defaulting to low-level texture replacement or yielding semantically inconsistent outputs. In this paper, we introduce StyleMe3D, a novel hierarchical framework that achieves comprehensive, high-fidelity stylization by disentangling multi-level style representations while preserving geometric fidelity. The cornerstone of StyleMe3D is Dynamic Style Score Distillation (DSSD), which harnesses latent priors from a style-aware diffusion model to provide high-level semantic guidance, ensuring robust and expressive style transfer. To further refine this distillation process, we propose a multi-modal alignment strategy using the CLIP latent space: a CLIP-based style stream evaluator (Contrastive Style Descriptor) that enforces middle-level stylistic similarity, and a CLIP-based content stream evaluator (3D Gaussian Quality Assessment) that acts as a global regularizer to mitigate typical GS quality degradation. Finally, a VGG-based Simultaneously Optimized Scale module is integrated to refine fine-grained texture details at the low-level. Extensive experiments demonstrate that our method consistently preserves intricate geometric details and achieves coherent stylistic effects across entire scenes, significantly surpassing state-of-the-art baselines in both qualitative and quantitative evaluations.

cs.CV↗

arXiv2026

Urban Neural Surface Reconstruction from Constrained Sparse Aerial Imagery with 3D SAR Fusion

Neural surface reconstruction (NSR) has recently shown strong potential for urban 3D reconstruction from multi-view aerial imagery. However, existing NSR methods often suffer from geometric ambiguity and instability, particularly under sparse-view conditions. This issue is critical in large-scale urban remote sensing, where aerial image acquisition is limited by flight paths, terrain, and cost. To address this challenge, we present the first urban NSR framework that fuses 3D synthetic aperture radar (SAR) point clouds with aerial imagery for high-fidelity reconstruction under constrained, sparse-view settings. 3D SAR can efficiently capture large-scale geometry even from a single side-looking flight path, providing robust priors that complement photometric cues from images. Our framework integrates radar-derived spatial constraints into an SDF-based NSR backbone, guiding structure-aware ray selection and adaptive sampling for stable and efficient optimization. We also construct the first benchmark dataset with co-registered 3D SAR point clouds and aerial imagery, facilitating systematic evaluation of cross-modal 3D reconstruction. Extensive experiments show that incorporating 3D SAR markedly enhances reconstruction accuracy, completeness, and robustness compared with single-modality baselines under highly sparse and oblique-view conditions, highlighting a viable route toward scalable high-fidelity urban reconstruction with advanced airborne and spaceborne optical-SAR sensing.

cs.CV↗

arXiv2026

Microwave vortex beam lasing via photonic time crystals

Microwave lasing carrying orbital angular momentum (OAM) holds significant potential for advanced applications in fields such as high-capacity communications, precision sensing, and radar imaging. However, conventional approaches to masers fail to produce emission with embedded OAM. The recent emergence of photonic time crystals (PTCs)-artificially structured media with periodically varying electromagnetic properties in time-offers a paradigm shift toward resonance-free lasing without the need for gain media. Yet, pioneering PTC designs have been based on three-dimensional bulk structures, which lack a surface-emitting configuration, and do not possess the capability to modulate OAM, thus hindering the realization of surface-emitted PTC masing that carries OAM. Here, we report the first experimental demonstration of non-resonant, gain medium-free, and surface-emitted microwave vortex beam lasing OAM using ring-shaped PTCs. By developing a multiplier-driven time-varying metamaterial that achieves over 100% equivalent permittivity modulation depth, we establish momentum bandgaps (k gaps) with sufficient bandwidth to overcome intrinsic losses and enable self-sustained coherent microwave amplification. Furthermore, space-time modulation induces non-reciprocity between clockwise and counterclockwise k gap modes within the circularly symmetric PTC structure, facilitating the selective generation of microwave lasing carrying OAM-a capability beyond the reach of conventional maser technologies. Our work bridges PTC physics with coherent OAM-carrying microwave emission, establishing a transformative platform for next-generation wireless communications, advanced sensing systems, and OAM-based technologies.

physics.optics↗

arXiv2025

On the Casimir number and formal codegree of Haagerup-Izumi fusion rings

For any cyclic group $\mathbb{Z}_n$, we first determine the Casimir number and determinant of the Haagerup-Izumi fusion ring $\mathcal{HI}_{\mathbb{Z}_n}$, it turns out that they do not share the same set of prime factors. Then we show that all finite-dimensional irreducible representations of $\mathcal{HI}_{\mathbb{Z}_n}$ are defined over certain cyclotomic fields. As a direct result, we obtain the formal codegrees of $\mathcal{HI}_{\mathbb{Z}_n}$, which satisfy the pseudo-unitary inequality.

math.QA↗

arXiv2025

Deep Learning-based Cross-modal Reconstruction of Vehicle Target from Sparse 3D SAR Image

Three-dimensional synthetic aperture radar (3D SAR) is an advanced active microwave imaging technology widely utilized in remote sensing area. To achieve high-resolution 3D imaging,3D SAR requires observations from multiple aspects and altitude baselines surrounding the target. However, constrained flight trajectories often lead to sparse observations, which degrade imaging quality, particularly for anisotropic man-made small targets, such as vehicles and aircraft. In the past, compressive sensing (CS) was the mainstream approach for sparse 3D SAR image reconstruction. More recently, deep learning (DL) has emerged as a powerful alternative, markedly boosting reconstruction quality and efficiency. However, existing DL-based methods typically rely solely on high-quality 3D SAR images as supervisory signals to train deep neural networks (DNNs). This unimodal learning paradigm prevents the integration of complementary information from other data modalities, which limits reconstruction performance and reduces target discriminability due to the inherent constraints of electromagnetic scattering. In this paper, we introduce cross-modal learning and propose a Cross-Modal 3D-SAR Reconstruction Network (CMAR-Net) for enhancing sparse 3D SAR images of vehicle targets by fusing optical information. Leveraging cross-modal supervision from 2D optical images and error propagation guaranteed by differentiable rendering, CMAR-Net achieves efficient training and reconstructs sparse 3D SAR images, which are derived from highly sparse-aspect observations, into visually structured 3D vehicle images. Trained exclusively on simulated data, CMAR-Net exhibits robust generalization to real-world data, outperforming state-of-the-art CS and DL methods in structural accuracy within a large-scale parking lot experiment involving numerous civilian vehicles, thereby demonstrating its strong practical applicability.

cs.CV↗

arXiv2024

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a novel framework, which enables compelling motion generation from zero-shot open-vocabulary text prompts. Our key idea is to carefully tailor the pretrain-then-finetune paradigm into the text-to-motion generation. At the pre-training stage, our model improves the generation ability by learning the rich out-of-domain inherent motion traits. To this end, we scale up a large unconditional diffusion model up to 1B parameters, so as to utilize the massive unlabeled motion data up to over 20M motion instances. At the subsequent fine-tuning stage, we introduce motion ControlNet, which incorporates text prompts as conditioning information, through a trainable copy of the pre-trained model and the proposed novel Mixture-of-Controllers (MoC) block. MoC block adaptively recognizes various ranges of the sub-motions with a cross-attention mechanism and processes them separately with the text-token-specific experts. Such a design effectively aligns the CLIP token embeddings of text prompts to various ranges of compact and expressive motion features. Extensive experiments demonstrate that our OMG achieves significant improvements over the state-of-the-art methods on zero-shot text-to-motion generation. Project page: https://tr3e.github.io/omg-page.

cs.CV↗

arXiv2021

Observation of hybrid higher-order skin-topological effect in non-Hermitian topolectrical circuits

Robust boundary states epitomize how deep physics can give rise to concrete experimental signatures with technological promise. Of late, much attention has focused on two distinct mechanisms for boundary robustness - topological protection, as well as the non-Hermitian skin effect. In this work, we report the first experimental realizations of hybrid higher-order skin-topological effect, in which the skin effect selectively acts only on the topological boundary modes, not the bulk modes. Our experiments, which are performed on specially designed non-reciprocal 2D and 3D topolectrical circuit lattices, showcases how non-reciprocal pumping and topological localization dynamically interplays to form various novel states like 2D skin-topological, 3D skin-topological-topological hybrid states, as well as 2D and 3D higher-order non-Hermitian skin states. Realized through our highly versatile and scalable circuit platform, theses states have no Hermitian nor lower-dimensional analog, and pave the way for new applications in topological switching and sensing through the simultaneous non-trivial interplay of skin and topological boundary localizations.

cond-mat.mes-hall↗

arXiv2021

Experimental Observation of Higher-Order Topological Anderson Insulators

Recently, a new family of symmetry-protected higher-order topological insulators has been proposed and was shown to host lower-dimensional boundary states. However, with the existence of the strong disorder in the bulk, the crystal symmetry is broken, and the associated corner states are disappeared. It is well known that the emergence of robust edge states and quantized transport can be induced by adding sufficient disorders into a topologically trivial insulator, that is the so-called topological Anderson insulator. The question is whether disorders can also cause the higher-order topological phase. This is not known so far, because interactions between disorders and the higher-order topological phases are completely different from those with the first-order topological system. Here, we demonstrate theoretically that the disorderinduced higher-order topological corner state and quantized fraction corner charge can appear in a modified Haldane model. In experiments, we construct the classical analog of such higherorder topological Anderson insulators using electric circuits and observe the disorder-induced corner state through the voltage measurement. Our work defies the conventional view that the disorder is detrimental to the higher-order topological phase, and offers a feasible platform to investigate the interaction between disorders and higher-order topological phases.

cond-mat.mes-hall↗

arXiv2021

High-performance parallel classical scheme for simulating shallow quantum circuits

Recently, constant-depth quantum circuits are proved more powerful than their classical counterparts at solving certain problems, e.g., the two-dimensional (2D) hidden linear function (HLF) problem regarding a symmetric binary matrix. To further investigate the boundary between classical and quantum computing models, in this work we propose a high-performance two-stage classical scheme to solve a full-sampling variant of the 2D HLF problem, which combines traditional classical parallel algorithms and a gate-based classical circuit model together for exactly simulating the target shallow quantum circuits. Under reasonable parameter assumptions, a theoretical analysis reveals our classical simulator consumes less runtime than that of near-term quantum processors for most problem instances. Furthermore, we demonstrate the typical all-connected 2D grid instances by moderate FPGA circuits, and show our designed parallel scheme is a practically scalable, high-efficient and operationally convenient tool for simulating and verifying graph-state circuits performed by current quantum hardware.

quant-ph↗

arXiv2020

Topolectrical-circuit realization of 4D hexadecapole insulator

Recently, the theory of quantized dipole polarization has been extended to account for electric multipole moments, giving rise to the discovery of multipole topological insulators (TIs). Both two-dimensional (2D) quadrupole and three-dimensional (3D) octupole TIs with robust zero-dimensional (0D) corner states have been realized in various classical systems. However, due to the intrinsic 3D limitation, the higher dimensional multipole TIs, such as four-dimensional (4D) hexadecapole TIs, are supposed to be extremely hard to construct in real space, although some of their properties have been discussed through the synthetic dimensions. Here, we theoretically propose and experimentally demonstrate the realization of classical analog of 4D hexadecapole TI based on the electric circuits in fully real space. The explicit construction of 4D hexadecapole circuits, where the connection of nodes is allowed in any desired way free from constraints of locality and dimensionality, is provided. By direct circuit simulations and impedance measurements, the in-gap corner states protected by the quantized hexadecapole moment in the 4D circuit lattices are observed and the robustness of corner state is also demonstrated. Our work offers a new pathway to study the higher order/dimensional topological physics in real space.

cond-mat.mes-hall↗

arXiv2019

Topolectrical-circuit octupole insulator with topologically protected corner states

Recent theoretical studies have extended the Berry phase framework to account for higher electric multipole moments, quadrupole and octupole topological phases have been proposed. Although the two-dimensional quantized quadrupole insulators have been demonstrated experimentally, octupole topological phases have not previously been observed experimentally. Here we report on the experimental realization of classical analog of octupole topological insulator in the electric circuit system. Three-dimensional topolectrical circuits for realizing such topological phases are constructed experimentally. We observe octupole topological states protected by the topology of the bulk, which are localized at the corners. Our results provide conclusive evidence of a form of robustness against disorder and deformation, which is characteristic of octupole topological insulators. Our study opens a new route toward higher-order topological phenomena in three-dimensions and paves the way for employing topolectrical circuitry to study complex topological phenomena.

cond-mat.mes-hall↗