arXiv subjects

Jingbo Wang

Publications and source records attributed to Jingbo Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation

Styled motion in-betweening is crucial for computer animation and gaming. However, existing methods typically encode motion styles by modeling whole-body motions, often overlooking the representation of individual body parts. This limitation reduces the flexibility of infilled motion, particularly in adjusting the motion styles of specific limbs independently. To overcome this challenge, we propose a novel framework that models motion styles at the body-part level, enhancing both the diversity and controllability of infilled motions. Our approach enables more nuanced and expressive animations by allowing precise modifications to individual limb motions while maintaining overall motion coherence. Leveraging phase-related insights, our framework employs periodic autoencoders to automatically extract the phase of each body part, capturing distinctive local style features. Additionally, we effectively decouple the motion source from synthesis control by integrating motion manifold learning and conditional generation techniques from both image and motion domains. This allows the motion source to generate high-quality motions across various styles, with extracted motion and style features readily available for controlled synthesis in subsequent tasks. Comprehensive evaluations demonstrate that our method achieves superior speed, robust generalization, and effective generation of extended motion sequences.

cs.CV↗

arXiv2025

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths, while GPT-based methods suffer from delayed response and error accumulation problem due to discretized non-causal tokenization. To solve these problems, we propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probabilistic autoregressive model. The continuous latents mitigate information loss caused by discretization and effectively reduce error accumulation during long-term autoregressive generation. In addition, by establishing temporal causal dependencies between current and historical motion latents, our model fully utilizes the available information to achieve accurate online motion decoding. Experiments show that our method outperforms existing approaches while offering more applications, including multi-round generation, long-term generation, and dynamic motion composition. Project Page: https://zju3dv.github.io/MotionStreamer/

cs.CV↗

arXiv2025

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Generating diverse and natural human motion sequences based on textual descriptions constitutes a fundamental and challenging research area within the domains of computer vision, graphics, and robotics. Despite significant advancements in this field, current methodologies often face challenges regarding zero-shot generalization capabilities, largely attributable to the limited size of training datasets. Moreover, the lack of a comprehensive evaluation framework impedes the advancement of this task by failing to identify directions for improvement. In this work, we aim to push text-to-motion into a new era, that is, to achieve the generalization ability of zero-shot. To this end, firstly, we develop an efficient annotation pipeline and introduce MotionMillion-the largest human motion dataset to date, featuring over 2,000 hours and 2 million high-quality motion sequences. Additionally, we propose MotionMillion-Eval, the most comprehensive benchmark for evaluating zero-shot motion generation. Leveraging a scalable architecture, we scale our model to 7B parameters and validate its performance on MotionMillion-Eval. Our results demonstrate strong generalization to out-of-domain and complex compositional motions, marking a significant step toward zero-shot human motion generation. The code is available at https://github.com/VankouF/MotionMillion-Codes.

cs.CV↗

arXiv2025

EHCube4P: Learning Epistatic Patterns Through Hypercube Graph Convolution Neural Network for Protein Fitness Function Estimation

Understanding the relationship between protein sequences and their functions is fundamental to protein engineering, but this task is hindered by the combinatorially vast sequence space and the experimental noise inherent in fitness measurements. In this study, we present a novel framework that models the sequence landscape as a hypercube $H(k,2)$ and integrates wavelet-based signal denoising with a graph convolutional neural network (GCN) to predict protein fitness across rugged fitness landscapes. Using a dataset of 419 experimentally measured mutant sequences of the Tobacco 5-Epi-Aristolochene Synthase (TEAS) enzyme, we preprocess the fitness signals using a 1-D discrete wavelet transform with a Daubechies-3 basis to suppress experimental noise while preserving local epistatic patterns. Our model comprises two GCN layers, allowing for beyond pairwise aggregation, followed by a multi-layer perceptron (MLP). We show that our approach, EHCube4P, generalizes well across different enzyme activity datasets and effectively captures higher-order mutational interactions. Performance varies with the ruggedness of the fitness landscape, with smoother signals yielding higher test set $r^2$ scores. These results demonstrate that combining wavelet preprocessing with graph-based deep learning enhances the robustness and generalization of fitness prediction, particularly for sparse and noisy biological datasets. The approach provides a scalable and interpretable framework for protein fitness estimation applicable to a broad range of combinatorial biological systems.

q-bio.QM↗

arXiv2025

The Chinese Pulsar Timing Array data release I. Single pulsar noise analysis

The Chinese Pulsar Timing Array (CPTA) has collected observations from 57 millisecond pulsars using the Five-hundred-meter Aperture Spherical Radio Telescope (FAST) for close to three years, for the purpose of searching for gravitational waves (GWs). To robustly search for ultra-low-frequency GWs, pulsar timing arrays (PTAs) need to use models to describe the noise from the individual pulsars. We report on the results from the single pulsar noise analysis of the CPTA data release I (DR1). Conventionally, power laws in the frequency domain are used to describe pulsar red noise and dispersion measurement (DM) variations over time. Employing Bayesian methods, we found the choice of number and range of frequency bins with the highest evidence for each pulsar individually. A comparison between a dataset using DM piecewise measured (DMX) values and a power-law Gaussian process to describe the DM variations shows strong Bayesian evidence in favour of the power-law model. Furthermore, we demonstrate that the constraints obtained from four independent software packages are very consistent with each other. The short time span of the CPTA DR1, paired with the large sensitivity of FAST, has proved to be a challenge for the conventional noise model using a power law. This mainly shows in the difficulty to separate different noise terms due to their covariances with each other. Nineteen pulsars are found to display covariances between the short-term white noise and long-term red and DM noise. With future CPTA datasets, we expect that the degeneracy can be broken. Finally, we compared the CPTA DR1 results against the noise properties found by other PTA collaborations. While we can see broad agreement, there is some tension between different PTA datasets for some of the overlapping pulsars. This could be due to the differences in the methods and frequency range compared to the other PTAs.

astro-ph.HE↗

arXiv2025

Benchmarking Quantum Heuristics: Non-Variational QWOA for Weighted Maxcut

We present benchmarking results for the non-variational Quantum Walk Optimisation Algorithm (non-variational QWOA) applied to the weighted maxcut problem, using classical simulations for problem sizes up to $n = 31$. The amplified quantum state, prepared using a quadratic number of alternating unitaries, achieves a constant average-case measurement probability for globally optimal solutions across these problem sizes. This behaviour contrasts with that of classical heuristics, which, for NP-hard optimisation problems, typically exhibit solve probabilities that decay as problem size increases. Performance comparisons with two local-search heuristics on the same benchmark instances suggest that the non-variational QWOA may offer a meaningful advantage by scaling more favourably with problem size. These results provide supporting evidence for the potential of this quantum heuristic to achieve quantum advantage, though further work is needed to assess whether the observed performance scaling persists at larger problem sizes, and to confirm whether similar performance trends are observed for the other problem classes to which the non-variational QWOA is designed to generalise.

quant-ph↗

arXiv2025

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding abilities, but also integrate visual-spatial reasoning and physical interaction capabilities. Nevertheless,existing methods struggle to unify these capabilities due to their fundamental differences.In this paper, we present the Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world. VeBrain reformulates robotic control into common text-based MLLM tasks in the 2D visual space, thus unifying the objectives and mapping spaces of different tasks. Then, a novel robotic adapter is proposed to convert textual control signals from MLLMs to motion policies of real robots. From the data perspective, we further introduce VeBrain-600k, a high-quality instruction dataset encompassing various capabilities of VeBrain. In VeBrain-600k, we take hundreds of hours to collect, curate and annotate the data, and adopt multimodal chain-of-thought(CoT) to mix the different capabilities into a single conversation. Extensive experiments on 13 multimodal benchmarks and 5 spatial intelligence benchmarks demonstrate the superior performance of VeBrain to existing MLLMs like Qwen2.5-VL. When deployed to legged robots and robotic arms, VeBrain shows strong adaptability, flexibility, and compositional capabilities compared to existing methods. For example, compared to Qwen2.5-VL, VeBrain not only achieves substantial gains on MMVet by +5.6%, but also excels in legged robot tasks with +50% average gains.

cs.CV↗

arXiv2025

SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control

This paper presents a novel framework that enables real-world humanoid robots to maintain stability while performing human-like motion. Current methods train a policy which allows humanoid robots to follow human body using the massive retargeted human data via reinforcement learning. However, due to the heterogeneity between human and humanoid robot motion, directly using retargeted human motion reduces training efficiency and stability. To this end, we introduce SMAP, a novel whole-body tracking framework that bridges the gap between human and humanoid action spaces, enabling accurate motion mimicry by humanoid robots. The core idea is to use a vector-quantized periodic autoencoder to capture generic atomic behaviors and adapt human motion into physically plausible humanoid motion. This adaptation accelerates training convergence and improves stability when handling novel or challenging motions. We then employ a privileged teacher to distill precise mimicry skills into the student policy with a proposed decoupled reward. We conduct experiments in simulation and real world to demonstrate the superiority stability and performance of SMAP over SOTA methods, offering practical guidelines for advancing whole-body control in humanoid robots.

cs.RO↗

arXiv2025

Quantum Compiler Design for Qubit Mapping and Routing: A Cross-Architectural Survey of Superconducting, Trapped-Ion, and Neutral Atom Systems

Quantum hardware development is progressing rapidly with substantial advancements achieved across leading platforms, including superconducting circuits, trapped-ion systems, and neutral atom arrays. As the pursuit of practical quantum advantage continues, efficient quantum program compilation becomes essential for transforming high-level representations of quantum algorithms into physically executable circuits. A fundamental challenge in this process is qubit mapping and gate scheduling, which play a critical role in adapting compiled circuits to the architectural constraints and physical limitations of specific quantum hardware. In this survey, we systematically review and categorize research on the qubit mapping and routing problems across the three mainstream quantum hardware platforms. We primarily explore the development of hardware-aware compilers for superconducting platforms, classifying existing methods into solver-based, heuristic-based, and machine learning-based approaches, and analyze their optimization targets, including gate count, circuit duration, fidelity, and scalability. Furthermore, we examine the evolution of trapped-ion and neutral atom devices, analyzing the distinct challenges posed by their hardware characteristics and highlighting specialized compilers tailored to these unique physical constraints. Finally, we summarize the key challenges and identify some promising opportunities for future research in quantum compiler design across these hardware platforms.

quant-ph↗

arXiv2025

Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems

Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular mechanisms governing agents, critical to performance and scalability, remain underexplored. This study systematically investigates four dimensions of collaboration strategies: (1) agent governance, (2) participation control, (3) interaction dynamics, and (4) dialogue history management. Through rigorous experimentation under two context-dependent scenarios: Distributed Evidence Integration (DEI) and Structured Evidence Synthesis (SES), we quantify the impact of these strategies on both task accuracy and computational efficiency. Our findings reveal that centralized governance, instructor-led participation, ordered interaction patterns, and instructor-curated context summarization collectively optimize the trade-off between decision quality and resource utilization with the support of the proposed Token-Accuracy Ratio (TAR). This work establishes a foundation for designing adaptive, scalable multi-agent systems, shifting the focus from structural novelty to strategic interaction mechanics.

cs.MA↗

arXiv2025

SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations

We address a fundamental challenge in Reinforcement Learning from Interaction Demonstration (RLID): demonstration noise and coverage limitations. While existing data collection approaches provide valuable interaction demonstrations, they often yield sparse, disconnected, and noisy trajectories that fail to capture the full spectrum of possible skill variations and transitions. Our key insight is that despite noisy and sparse demonstrations, there exist infinite physically feasible trajectories that naturally bridge between demonstrated skills or emerge from their neighboring states, forming a continuous space of possible skill variations and transitions. Building upon this insight, we present two data augmentation techniques: a Stitched Trajectory Graph (STG) that discovers potential transitions between demonstration skills, and a State Transition Field (STF) that establishes unique connections for arbitrary states within the demonstration neighborhood. To enable effective RLID with augmented data, we develop an Adaptive Trajectory Sampling (ATS) strategy for dynamic curriculum generation and a historical encoding mechanism for memory-dependent skill learning. Our approach enables robust skill acquisition that significantly generalizes beyond the reference demonstrations. Extensive experiments across diverse interaction tasks demonstrate substantial improvements over state-of-the-art methods in terms of convergence stability, generalization capability, and recovery robustness.

cs.LG↗

arXiv2025

S-SYNC: Shuttle and Swap Co-Optimization in Quantum Charge-Coupled Devices

The Quantum Charge-Coupled Device (QCCD) architecture is a modular design to expand trapped-ion quantum computer that relies on the coherent shuttling of qubits across an array of segmented electrodes. Leveraging trapped ions for their long coherence times and high-fidelity quantum operations, QCCD technology represents a significant advancement toward practical, large-scale quantum processors. However, shuttling increases thermal motion and consistently necessitates qubit swaps, significantly extend execution time and negatively affect application success rates. In this paper, we introduce S-SYNC -- a compiler designed to co-optimize the number of shuttling and swapping operations. S-SYNC exploits the unique properties of QCCD and incorporates generic SWAP operations to efficiently manage shuttle and SWAP counts simultaneously. Building on the static topology formulation of QCCD, we develop scheduling heuristics to enhance overall performance. Our evaluations demonstrate that our approach reduces the shuttling number by 3.69x on average and improves the success rate of quantum applications by 1.73x on average. Moreover, we apply S-SYNC to gain insights into executing applications across various QCCD topologies and to compare the trade-offs between different initial mapping methods.

quant-ph↗

arXiv2025

The Chinese pulsar timing array data release I. Polarimetry for 56 millisecond pulsars

We present polarization pulse profiles for 56 millisecond pulsars (MSPs) monitored by the Chinese Pulsar Timing Array (CPTA) collaboration using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The observations centered at 1.25 GHz with a raw bandwidth of 500 MHz. Due to the high sensitivity ($\sim$16 K/Jy) of the FAST telescope and our long integration time, the high signal-to-noise ratio polarization profiles show features hardly detected before. Among 56 pulsars, the polarization profiles of PSRs J0406$+$3039, J1327$+$3423, and J2022$+$2534 were not previously reported. 80\% of MSPs in the sample show weak components below 3\% of peak flux, 25\% of pulsars show interpulse-like structures, and most pulsars show linear polarization position angle jumps. Six pulsars seem to be emitting for full rotation phase, with another thirteen pulsars being good candidates for such a 360$^\circ$ radiator. We find that the distribution of the polarization percentage in our sample is compatible with the normal pulsar distribution. Our detailed evaluation of the MSP polarization properties suggests that the wave propagation effects in the pulsar magnetosphere are important in shaping the MSP polarization pulse profiles.

astro-ph.HE↗

arXiv2025

DreamRelation: Bridging Customization and Relation Generation

Customized image generation is essential for creating personalized content based on user prompts, allowing large-scale text-to-image diffusion models to more effectively meet individual needs. However, existing models often neglect the relationships between customized objects in generated images. In contrast, this work addresses this gap by focusing on relation-aware customized image generation, which seeks to preserve the identities from image prompts while maintaining the relationship specified in text prompts. Specifically, we introduce DreamRelation, a framework that disentangles identity and relation learning using a carefully curated dataset. Our training data consists of relation-specific images, independent object images containing identity information, and text prompts to guide relation generation. Then, we propose two key modules to tackle the two main challenges: generating accurate and natural relationships, especially when significant pose adjustments are required, and avoiding object confusion in cases of overlap. First, we introduce a keypoint matching loss that effectively guides the model in adjusting object poses closely tied to their relationships. Second, we incorporate local features of the image prompts to better distinguish between objects, preventing confusion in overlapping cases. Extensive results on our proposed benchmarks demonstrate the superiority of DreamRelation in generating precise relations while preserving object identities across a diverse set of objects and relationships.

cs.CV↗

arXiv2025

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Synthesizing diverse and physically plausible Human-Scene Interactions (HSI) is pivotal for both computer animation and embodied AI. Despite encouraging progress, current methods mainly focus on developing separate controllers, each specialized for a specific interaction task. This significantly hinders the ability to tackle a wide variety of challenging HSI tasks that require the integration of multiple skills, e.g., sitting down while carrying an object. To address this issue, we present TokenHSI, a single, unified transformer-based policy capable of multi-skill unification and flexible adaptation. The key insight is to model the humanoid proprioception as a separate shared token and combine it with distinct task tokens via a masking mechanism. Such a unified policy enables effective knowledge sharing across skills, thereby facilitating the multi-task training. Moreover, our policy architecture supports variable length inputs, enabling flexible adaptation of learned skills to new scenarios. By training additional task tokenizers, we can not only modify the geometries of interaction targets but also coordinate multiple skills to address complex tasks. The experiments demonstrate that our approach can significantly improve versatility, adaptability, and extensibility in various HSI tasks. Website: https://liangpan99.github.io/TokenHSI/

cs.CV↗

arXiv2025

Learning out-of-time-ordered correlators with classical kernel methods

Out-of-Time Ordered Correlators (OTOCs) are widely used to investigate information scrambling in quantum systems. However, directly computing OTOCs with classical computers is an expensive procedure. This is due to the need to classically simulate the dynamics of quantum many-body systems, which entails computational costs that scale rapidly with system size. Similarly, exact simulation of the dynamics with a quantum computer (QC) will either only be possible for short times with noisy intermediate-scale quantum (NISQ) devices, or will require a fault-tolerant QC which is currently beyond technological capabilities. This motivates a search for alternative approaches to determine OTOCs and related quantities. In this study, we explore four parameterised sets of Hamiltonians describing local one-dimensional quantum systems of interest in condensed matter physics. For each set, we investigate whether classical kernel methods (KMs) can accurately learn the XZ-OTOC and a particular sum of OTOCs, as functions of the Hamiltonian parameters. We frame the problem as a regression task, generating small batches of labelled data with classical tensor network methods for quantum many-body systems with up to 40 qubits. Using this data, we train a variety of standard kernel machines and observe that the Laplacian and radial basis function (RBF) kernels perform best, achieving a coefficient of determination ($R^2$) on the testing sets of at least 0.7167, with averages between 0.8112 and 0.9822 for the various sets of Hamiltonians, together with small root mean squared error and mean absolute error. Hence, after training, the models can replace further uses of tensor networks for calculating an OTOC function of a system within the parameterised sets. Accordingly, the proposed method can assist with extensive evaluations of an OTOC function.

quant-ph↗

arXiv2025

ARMO: Autoregressive Rigging for Multi-Category Objects

Recent advancements in large-scale generative models have significantly improved the quality and diversity of 3D shape generation. However, most existing methods focus primarily on generating static 3D models, overlooking the potentially dynamic nature of certain shapes, such as humanoids, animals, and insects. To address this gap, we focus on rigging, a fundamental task in animation that establishes skeletal structures and skinning for 3D models. In this paper, we introduce OmniRig, the first large-scale rigging dataset, comprising 79,499 meshes with detailed skeleton and skinning information. Unlike traditional benchmarks that rely on predefined standard poses (e.g., A-pose, T-pose), our dataset embraces diverse shape categories, styles, and poses. Leveraging this rich dataset, we propose ARMO, a novel rigging framework that utilizes an autoregressive model to predict both joint positions and connectivity relationships in a unified manner. By treating the skeletal structure as a complete graph and discretizing it into tokens, we encode the joints using an auto-encoder to obtain a latent embedding and an autoregressive model to predict the tokens. A mesh-conditioned latent diffusion model is used to predict the latent embedding for conditional skeleton generation. Our method addresses the limitations of regression-based approaches, which often suffer from error accumulation and suboptimal connectivity estimation. Through extensive experiments on the OmniRig dataset, our approach achieves state-of-the-art performance in skeleton prediction, demonstrating improved generalization across diverse object categories. The code and dataset will be made public for academic use upon acceptance.

cs.CV↗

arXiv2025

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form scripts, providing a rich foundation for motion planning. A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues, simultaneously perceiving environmental geometries and accomplishing task goals. By integrating the retrieval-augmented script generation with the multi-condition controller, our approach provides a unified solution for generating stylized HSI motions. We further introduce a comprehensive planning dataset produced by RAG and a stylized motion dataset featuring diverse locomotions and interactions. Extensive experiments demonstrate SIMS's effectiveness in executing various tasks and generalizing across different scenarios, significantly outperforming previous methods.

cs.CV↗