Searcharxiv⌕ Search

arXiv subjects

Jiahui Zhang

Publications and source records attributed to Jiahui Zhang.

At least 19 recordsLinked to original sources

MoViC: Real-Time Humanoid Whole-Body Control from Monocular Video Streams

Real-time whole-body imitation from monocular video requires both a robust universal tracker and high-quality real-time reconstruction. We present MoViC, a framework that uses live RGB video as a control signal for humanoid robots without wearable tracking devices. The framework combines monocular human motion reconstruction, robot retargeting, and a transformer-based behavior foundation model. The policy receives proprioceptive history, a single explicit next-step reference, and a compact frequency-domain motion representation that supplies temporal context without explicitly stacking future reference frames, which reduces the input dimension and network size. During deployment, our extrapolation method bridges the 10-Hz visual estimation with 50-Hz controller, enabling asynchronous visual processing and policy execution. Hardware experiments further demonstrate highly dynamic motion tracking and device-free teleoperation of bimanual and single-arm manipulation tasks from live monocular RGB input. Project page: https://movicproject.github.io/ .

cs.RO↗

Forward Dynamics Models

Vision-language-action (VLA) models and world action models (WAMs) have advanced robotic policy learning by building on pretrained vision-language models (VLMs) and video generative models (VGMs), respectively. Yet VLAs learn without explicit supervision from future world states, while WAMs that condition actions on predicted futures incur extra inference cost and let visual prediction errors propagate into actions. We present Forward Dynamics Models (FDM), a family of robotic action models that couples action and future world-state prediction through an action-to-future paradigm. Future prediction is conditioned on action features, never the reverse: end-to-end training lets ground-truth future states supervise the policy through these features, while prediction errors cannot propagate into actions. At inference, FDM skips future generation entirely, avoiding its computational cost. The paradigm is backbone-agnostic, and we instantiate it with both VLM and VGM backbones. Experiments in simulation and on real robots demonstrate the effectiveness of FDM across both backbone families, achieving a state-of-the-art 99.4% average success rate on LIBERO and absolute gains of up to 13% over VLA and WAM methods on real-world tasks.

cs.RO↗

Spectral Tail Auxiliary Learning for AI-Generated Image Detection

As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for detection, typically described as frequency-domain artifacts or high-frequency discrepancies. However, the specific and recurring spectral regularities remain insufficiently understood and characterized. In this paper, we systematically analyze the one-dimensional radial log-power spectra of real and generated images. We find that generated images do not necessarily exhibit higher or lower energy across the entire spectrum or high-band range. Instead, their spectra deviate from the power-law decay and show an anomalous uplift in the ultra-high-frequency tail. We term this phenomenon spectral tail uplift. We further attribute this phenomenon to nonlinear harmonic accumulation in trained generative models, suggesting that it can serve as a structural cue across generative architectures. Based on this observation, we propose Spectral Tail Auxiliary Learning (STAL), a frequency-domain auxiliary supervision framework for generalizable AI-generated image detection. STAL transfers spectral-tail cues from a tail-aware frequency teacher to a spatial detector during training, while all frequency-domain modules are discarded at inference time. Consequently, STAL introduces no inference overhead. Extensive experiments on 9 public datasets show that STAL achieves strong generalization and stability across generators, data distributions, and real-world scenarios.

cs.CV↗

A quantum chemistry dataset containing S0-S1 conical-intersection structures of 259k molecules

Conical intersections are key to photoinduced reactions, but comprehensive datasets of their structures remain rare. To address this gap, we built the QCDGE-CI dataset, which contains ground-state and minimum-energy conical-intersection structures for more than 259k small molecules with up to ten heavy atoms (C, N, O, or F). The minimum-energy conical-intersection geometries were computed using the semi-empirical OM2/MRCI method and evaluated through systematic benchmarks with an enlarged active space and CASSCF calculations. These benchmarks support the reliability of the geometries. Cheminformatics analyses further reveal the broad chemical diversity covered by the dataset. The dataset is designed to support machine-learning and data-driven studies of excited-state chemistry, including nonadiabatic processes.

physics.chem-ph↗

Learning Human-Like Badminton Skills for Humanoid Robots

Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unlike standard locomotion or static manipulation, this task demands a seamless integration of explosive whole-body coordination and precise, timing-critical interception. While recent advances have achieved lifelike motion mimicry, bridging the gap between kinematic imitation and functional, physics-aware striking without compromising stylistic naturalness is non-trivial. To address this, we propose Imitation-to-Interaction, a progressive reinforcement learning framework designed to evolve a robot from a "mimic" to a capable "striker." Our approach establishes a robust motor prior from human data, distills it into a compact, model-based state representation, and stabilizes dynamics via adversarial priors. Crucially, to overcome the sparsity of expert demonstrations, we introduce a manifold expansion strategy that generalizes discrete strike points into a dense interaction volume. We validate our framework through the mastery of diverse skills, including lifts and drop shots, in simulation. Furthermore, we demonstrate the first zero-shot sim-to-real transfer of anthropomorphic badminton skills to a humanoid robot, successfully replicating the kinetic elegance and functional precision of human athletes in the physical world.

cs.RO↗

Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping

Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, recent systems use pretrained occupancy networks as world models that complete missing geometry. The predicted structure contributes to expected coverage gain and constrains feasible robot motion. Consequently, occupancy errors can change both what the robot chooses to explore and where it is able to move. We diagnose these effects by holding the planner fixed and varying only the occupancy representation provided to it. We consider planning without completion, with learned occupancy, with false positives removed by a ground truth oracle, with false negatives restored by an oracle, and with ground truth occupancy. Our experiments show that correcting false positives or false negatives alone does not consistently improve final coverage. This finding reveals a gap between occupancy accuracy and downstream planning performance. Ground truth occupancy provides a much larger improvement in coverage efficiency than in endpoint coverage, suggesting that planning and reachability remain important bottlenecks even when the geometric world model is accurate. Based on these findings, we introduce a dynamic filtering strategy that preserves predictions in unexplored space while suppressing repeatedly unsupported occupancy using online observations. Preliminary examples show that this strategy can redirect viewpoint selection toward reachable surfaces that would otherwise remain unobserved.

cs.RO↗

KuaiRP Series Role-playing Models Technical Report

This paper introduces the complete technical solution for the KuaiRP series of role-playing models. We aim to achieve four core objectives for a dedicated role-playing model: simplified prompt engineering, highly stable output quality, built-in domain world knowledge, and high-efficiency deployment with a small parameter size. However, effectively injecting deep domain knowledge often leads to a severe catastrophic forgetting of the model's general agent capabilities. To overcome this trade-off, we propose a multi-stage training pipeline. First, we design a standardized character template and construct an SFT data pipeline based on user behavior simulation and reverse profile filtering. Next, we utilize a rule-based composite reward function during the Reinforcement Learning (RL) phase to eliminate common degradation phenomena like length expansion and repetitive generation. Finally, to recover the general capabilities compromised during SFT and RL, we propose a novel self-distillation paradigm using Two-stage On-Policy Distillation (OPD) equipped with Cumulative-Divergence Decay (CDD). By using the domain-adapted model as the teacher and the original base model as the student, we effectively balance deep domain knowledge injection with the preservation of general agent capabilities. Experimental results demonstrate that the KuaiRP models not only match the current state-of-the-art proprietary models in role-playing fidelity within our target domains, but also successfully recover general agent capabilities, maintaining extremely low deployment costs.

cs.AI↗

Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filtering

Autonomous 3D active mapping requires a space robot to choose where to sense while building the geometry needed for navigation. Learned occupancy completion extends spatial context beyond the current field of view, but one predicted map often serves two planning roles: it scores expected surface gain and constrains collision-free motion. Unsupported occupancy can therefore distort both where the robot looks and where it believes it can travel. We study this coupled interface in a controlled closed-loop benchmark by holding the active-mapping system fixed and varying only its planner-facing occupancy across observation-only, learned, oracle-corrected, and ground-truth conditions. Improving occupancy accuracy does not monotonically improve closed-loop coverage: across 25 starts, planning with ground-truth occupancy reaches 70% of the learned baseline's final coverage 12.7 steps earlier on average, while increasing final coverage by only 0.031. Guided by this diagnosis, we introduce an observation-gated filter that retains completion in insufficiently observed regions and suppresses predictions only after repeated frustum exposure without nearby RGB-D support. The filter improves both targeted failure-prone starts without retraining or ground truth. These results motivate online revision of planner-facing geometry during autonomous intervals between communication windows. The current study assumes benchmark RGB-D observations and sufficiently accurate pose estimates; planetary sensing conditions and accumulated localization drift remain to be evaluated.

cs.RO↗

Verification of $K$- and Infinite-Step Strong/Weak Anonymity Using Concurrent Compositions

Anonymity is an information flow property that provides privacy protection in the sense of non-uniqueness of system information at certain moments with respect to observations. The notion of $K$-step anonymity in the context of discrete-event systems characterizes the scenario that the state estimates cannot be a singleton within at most $K$ observational steps prior to the current instant, while infinite-step anonymity is the same as $K$-step anonymity without considering the limit on $K$. In this paper, we lucubrate $K$- and infinite-step anonymity for partially-observed discrete-event systems modeled by non-deterministic finite-state automata. First, we define two strong types and two weak types of $K$- and infinite-step anonymity that are fundamentally different from the existing notions of $K$- and infinite-step anonymity due to the consideration of strong and weak anonymous projections. Then, we develop a new methodology by exploiting the concurrent-composition technique to verify these four types of anonymity. Based on the constructed concurrent compositions, verifiable necessary and sufficient conditions for the four types of anonymity are provided, along with their complexity analysis. Finally, the upper bounds on $K$ for $K$-step strong anonymity and weak anonymity are computed.

cs.FL↗

Anisotropic Maxwell neural operator for rapid parametric full-wave modelling of ion cyclotron resonance heating

Full-wave calculations of ion cyclotron resonance heating (ICRH) under different plasma dielectric conditions require repeated assembly and solution of large-scale discretised systems, limiting parameter sweeps and multi-case response analysis. We therefore propose an anisotropic Maxwell neural operator (AMNO) for rapid parametric modelling of ICRH full-wave responses for the Experimental Advanced Superconducting Tokamak (EAST), which learns, within the one-parameter dielectric-field family generated by varying the hydrogen minority fraction X_H over 0.01-0.05 under otherwise fixed settings, a shared solution operator from the spatially varying complex anisotropic dielectric-tensor field to the three-component complex electric field under frequency-domain Maxwell constraints. It represents global spatial coupling through spectral operator layers and local fine-scale responses, and combines sparse reference-field supervision with the frequency-domain Maxwell-equation residual. Comparisons with COMSOL reference solutions for the same EAST frequency-domain Maxwell-dielectric model show that AMNO reconstructs the principal spatial and spectral features and maintains stable accuracy for unseen interpolation test cases. With reference-field points reduced to 7.5% of the dense full-wave set, AMNO reduces the relative L_2 error by 66.1%-89.9% compared with a sparsely supervised Fourier neural operator (FNO-Sparse) under the same supervision and requires about 0.25 s for single-case inference. AMNO thus reduces dependence on dense reference-field supervision while enabling subsecond parametric complex-field inference, providing a physics-constrained and data-efficient surrogate for rapid in-range X_H sweeps and cross-case response analysis within the modelled EAST configuration.

physics.plasm-ph↗

MILD: Tractable Terrain Modeling for Learning Improved Bipedal Locomotion on Deformable Surfaces

Enabling robots to walk on yielding terrain is vital for applications ranging from disaster response to planetary exploration. While bipedal robots hold immense potential, their locomotion on deformable surfaces remains limited as current simulators fail to capture the spatiotemporal heterogeneity of such yielding substrates. We present MILD, featuring a physics-grounded discrete-element contact solver that accurately simulates spatially varying foot-terrain interactions. Complementing this model, we train a terrain-aware locomotion controller via deep reinforcement learning with latent modulation and proprioceptive estimation. Quantitative comparisons against state-of-the-art methods show our approach generates more diverse and realistic contact scenarios during training, resulting in controllers that exhibit natural adaptation on real deformable surfaces. Through hardware experiments, we demonstrate the system's capability for online terrain identification and adaptation across a wide range of surface stiffness.

cs.RO↗

Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space

Although legged animals are capable of performing explosive motions while traversing confined spaces, replicating this behavior in quadrupedal robots has been a longstanding challenge. Here, we propose a hierarchical reinforcement learning pipeline that empowers the robots to perform aggressive locomotion through constrained obstacles--a narrow gate. The imitation learning technique is used to train the low-level policy, which mimics the behaviors of real animals and forms a set of diverse skills. The high-level controller, having an awareness of the capability of low-level skills and acquiring the gate information via vision-based detection, determines the suitable maneuvers with collision-free trajectories to traverse it dynamically. Notably, we also verify that this framework can be extended to other highly dynamic tasks. This is one of the first works that perform autonomous and agile aerial gate traversal tasks on ground-walking robots, extending the lifelike agility of legged robots to match that of their biological counterparts.

cs.RO↗

Optimal Poisson subsampling for quantile regression with large-scale longitudinal data

To address the computational challenges arising from large-scale longitudinal data, an optimal Poisson subsampling algorithm is proposed for quantile regression. The proposed method can substantially alleviate computational burden. Under some regularity conditions, we derive the asymptotic properties of the estimators from weighted quantile generalized estimating equations. For practical implementation, an efficient algorithm is proposed for parameter estimation. Furthermore, asymptotic theory is established for penalized weighted smooth quantile generalized estimating equations, and regularized parameter estimation is performed within the optimal Poisson subsampling framework. Both numerical simulations and a real data application demonstrate that the proposed optimal Poisson subsampling algorithm outperforms the uniform Poisson subsampling algorithm, and the regularized estimation exhibits satisfactory performance as well.

stat.CO↗

Reinforcing Action Policies by Prophesying

Vision-Language-Action (VLA) policies excel in aligning language, perception, and robot control. However, most VLAs are trained purely by imitation, which overfits to demonstrations, and is brittle under distribution shift. Reinforcement learning (RL) directly optimizes task reward and thus addresses this misalignment, but real-robot interaction is expensive and conventional simulators are hard to engineer and transfer. We address both data efficiency and optimization stability in VLA post-training via a learned world model and an RL procedure tailored to flow-based action heads. Specifically, we first introduce Prophet, a unified action-to-video robot world model pretrained on large-scale, heterogeneous robot data to learn reusable action-outcome dynamics and then few-shot adapted to new robots, objects, and environments, yielding a rollout-ready simulator. Upon Prophet, we reinforce action policies with our proposed FlowScale, which couples Flow-GRPO with intrinsic stepwise reweighting to stabilize gradients. Together, our solution provides a practical, data- and compute-efficient path to VLA post-training. Experiments show 5-17% success gains on public benchmarks and 24-30% on real robots across diverse VLA backbones.

cs.RO↗

Selection criteria for the compressible Euler equations: numerical study

We numerically investigate selection criteria for dissipative weak solutions of the compressible Euler equations. Using the Kelvin-Helmholtz problem as a benchmark, we compare four standard numerical schemes - the viscous finite volume (VFV) method, the discrete velocity Boltzmann finite volume (DVBFV) method, the Runge-Kutta discontinuous Galerkin (RKDG) method, and the discontinuous Galerkin spectral element method (DGSEM), and demonstrate that each may converge to a different dissipative weak solution. We evaluate these solutions with respect to several selection criteria based on entropy production, total energy, and energy defect, and examine the sensitivity of selection functionals to the numerical diffusion inherent in each scheme.

math-ph↗

TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation

Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue evidence supports the judgment. We propose TRACE Bench, a task-driven agentic checklist evaluation framework. It decomposes each role profile offline into a fixed checklist, then uses a User Agent to converse naturally with the target roleplay model while privately updating checklist states from model responses. Scores therefore trace back to checklist items and supporting dialogue turns rather than a black-box holistic impression. For coverage cross-validation, we audit released M2 free-dialogue transcripts from the MiniMax Role-play Benchmark against the same role-derived checklist. The released free-chat transcripts cover only 73.74% of key role-profile points, whereas TRACE Bench reaches 99.91% coverage in fewer turns. Robustness experiments show stable rankings under repeated runs and User Agent replacement. Across 26 models, TRACE Bench reports overall rankings together with capability breakdowns and checklist traces. It also supports Closed-Loop Benchmark Evolution, distilling verification methods proven effective in failed traces so later evaluations can more reliably elicit and examine observed failure modes.

cs.CL↗

Shortcuts to adiabaticity in five-level systems using counter-diabatic driving and time-rescaling optimization

Shortcuts to adiabaticity (STA) is a common protocol to realize high-fidelity and robust quantum control in various quantum systems. To date, STA has been widely applied in two- and three-level systems, whereas designing feasible strategies to achieve perfect quantum state engineering in multi-level systems still remains a challenging task. Here, we propose to use counterdiabatic (CD) driving and time-rescaling (TR) methods to construct multi-state stimulated Raman shortcut-to-adiabatic passage protocols for realizing robust and fast population transfer in chainwise-connected five-state systems. The first protocol is implemented by initially reducing the original five-state system to an equivalent two-state counterpart, and then designing the corresponding driving field by combining CD driving and unitary transformation. Further, we introduce the TR method to optimize the first protocol and thus offers an alternative solution. Numerical calculations show that both protocols can achieve complete population transfer and effectively suppress transient populations of all intermediate states. Compared with the first protocol, the optimized second exhibits better performance within a shorter evolution time.

quant-ph↗

Learning Transferable Dynamics Priors from Action to World Modeling

We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual scene evolution, the resulting world model captures reusable interaction dynamics beyond appearance-level video generation. Concretely, we pretrain a multi-view interactive base diffusion world model, A2World, on large-scale robot manipulation data with real action annotations. We validate the learned dynamics priors from two complementary perspectives. First, we adapt A2World into a task- or scene-specialized real-world simulator, A2World-sim, whose long-horizon rollouts support simulator-based policy evaluation and scalable what-if analysis by replacing real-robot rollouts with world model rollouts. Second, starting from the same pretrained weights, we adapt A2World into a video-action joint prediction model, A2World-policy, that predicts actions under visual and instruction conditioning. Experiments across simulation benchmarks and real-robot settings demonstrate that action-conditioned world model pretraining yields transferable dynamics priors that benefit both simulator-centric and policy-centric robot learning.

cs.RO↗