Searcharxiv⌕ Search

arXiv subjects

Hua Chen

Publications and source records attributed to Hua Chen.

At least 19 recordsLinked to original sources
arXiv2026

FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence

Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of embodied policies, yet turning these algorithms into reliable robot systems remains constrained by fragmented data formats, training stacks, evaluation protocols, inference runtimes, and embodiment-specific interfaces. We present $\mathrm{FluxVLA}$ Engine, an open, configuration-driven platform that turns heterogeneous embodied-policy components into a reproducible data-to-deployment workflow. Rather than introducing another policy model, $\mathrm{FluxVLA}$ standardizes interfaces for datasets, visual-language and world models, action heads, reward- or advantage-weighted learning, distributed training, simulation evaluation, optimized inference, and robot operators. The engine further integrates compositional dual-arm simulation, scalable automatic data generation, and model-decoupled human-in-the-loop rollout, takeover, correction collection, and reward annotation. For responsive physical execution, it combines Real-Time Chunking (RTC) with accelerated inference backends, lightweight remote GPU serving, and configurable trajectory post-processing. Together, these capabilities connect offline learning, simulation validation, online correction, and real-robot execution through shared and auditable contracts. $\mathrm{FluxVLA}$ therefore targets the engineering bottlenecks separating promising embodied-learning algorithms from reproducible evaluation and dependable deployment. Code is available at https://github.com/FluxVLA/FluxVLA

cs.RO↗
arXiv2026

Robo2Process: Benchmarking and Learning Process-Aware Understanding in Vision-Language Robotic Manipulation

Vision-language models (VLMs) used as robotic critics, reward generators, and failure detectors must understand how manipulation unfolds, not only whether it succeeds. Yet fine-grained process supervision is not readily available in a unified form, and existing evaluations do not systematically diagnose these abilities. We introduce Robo2Process, a trace-grounded framework for scalable construction of process-aware supervision from heterogeneous robotic execution data. It aligns visual observations with source-native signals and annotations, extracts local process units (LPUs), and generates structured QA supervision through task-specific sampling, deterministic label construction, and ambiguity filtering. We instantiate this framework as RoboProcessBench, a diagnostic benchmark with 12 question families spanning \emph{static monitoring} and \emph{dynamic reasoning}, and ProcessData, a corpus of 57,892 QA pairs across four data sources and 260 manipulation tasks, split into ProcessData-SFT and ProcessData-Eval. Evaluation of a broad suite of VLMs reveals uneven process understanding. Supervision from ProcessData-SFT improves \textit{Qwen2.5-VL-7B} and \textit{InternVL-3-8B} on local state, motion, progress, and primitive-aware cues. External evaluation on RoboRewardBench shows Robo2Process enables out-of-distribution process-aware reasoning abilities. Overall, Robo2Process provides a source-aware pipeline, diagnostic benchmark, and learnable substrate for process-aware understanding in robotic manipulation.

cs.RO↗
arXiv2026

HWAM: Humanoid World Action Model With Joint State--Action Generation

Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from multimodal observations, while World Action Models (WAMs) further incorporate future visual prediction to improve action generation. However, in hierarchical humanoid systems, VLA and WAM policies output reference actions that are subsequently realized through whole-body control, robot dynamics, balance, and contact. This hierarchy creates an action--execution gap: the reference produced by the policy can differ from the motion realized by the robot. Without explicitly modeling the realized body state, future visual prediction must jointly explain scene evolution and discrepancies between reference actions and executed motion, making it difficult to associate an action with its physical outcome. We propose HWAM, a Humanoid World Action Model with joint state--action generation, which makes the robot's post-execution proprioceptive state an explicit prediction target. By jointly generating reference actions and their realized body states, HWAM directly incorporates supervision of executed motion into action learning. HWAM is trained through three complementary conditional paths. The Policy path jointly denoises state--action trajectories conditioned only on current observations, matching deployment conditions. Forward Dynamics Modeling (FDM) predicts future visual observations conditioned on actions and post-execution states, while Inverse Dynamics Modeling (IDM) reconstructs the joint trajectory from visual transitions. Together, these paths connect policy references, realized body motion, and visual outcomes. HWAM achieves the highest success rate among evaluated baselines on three real-robot tasks on the LimX OLI humanoid. On Candy Picking, HWAM achieves a 70.6% success rate, compared with 43.3% for Fast-WAM.

cs.RO↗
arXiv2026

Sharp stability near sums of ground states for fractional Schrödinger equations

We study quantitative stability for the fractional Schrödinger equation $(-Δ)^s u+u-|u|^αu=0$ near finite sums of widely separated positive ground states. For every $n\ge1$, $0 0$, we estimate the $H^s$ distance to the family of such sums in terms of the $H^{-s}$ norm of the equation's residual. The optimal rate changes at $α=n/[2(n+2s)]$, with a logarithmic correction at the threshold. Above the threshold the rate is $t^{(n+2s)/(n+2s+1)}$; below it the exponent is $[(1+α)(n+2s)-n/2]/(n+2s+1)$. The proof combines uniform invertibility away from the translation modes with precise interaction estimates and a weighted correction of the approximate configuration. This correction resolves the translation interactions even when the nonlinearity has a small exponent. We also construct nonnegative configurations that attain these rates. The estimates quantify the effect of the algebraic decay of fractional ground states on stability.

math.AP↗
arXiv2026

Klein Tunneling of Dirac Fermions through Electromagnetic Barriers

The Lorentz covariance of relativistic Dirac equations serves as a fundamental principle underlying the laws of electromagnetism across different inertial frames. Exploiting the covariance, we obtain the general solutions for Dirac fermions under both the in-plane electric $\boldsymbol{E}$ and perpendicular magnetic $\boldsymbol{B}$ fields, which reduce to either a magnetic or electric field in the inertial frame with drift velocity along the $\boldsymbol{E}\times\boldsymbol{B}$ direction. This dichotomy defines the magnetic and electric regimes, separated by the critical field ratio $E/B=v_\text{F}$ with $v_\text{F}$ denoting the Fermi velocity of Dirac fermions. Using these solutions, we revisit Klein tunneling through a heterojunction with generalized electromagnetic potentials. In the magnetic regime, the transmission exhibits oscillations governed by the Fabry-Pérot interference. In the electric regime, perfect transmission occurs at normal incidence in the drifted frame. The interference phase is further analyzed in terms of the solid angles on the Bloch sphere, providing a geometric interpretation of Klein tunneling. Finally, we briefly discuss the relation between the tilting of Dirac cones and the in-plane electric field, establishing the correspondence of the undertilted and overtilted cases to the magnetic and electric regimes, respectively. Our findings reveal the manipulation of Klein tunneling by electromagnetic fields, offering a theoretical basis for designing novel electronic devices.

quant-ph↗
arXiv2026

Learning Holistic Whole-Body Loco-Manipulation with a Bipedal Mobile Manipulator

Bipedal loco-manipulation enables robots to interact with objects beyond the nominal workspace of their arms by coordinating locomotion and manipulation. Realizing this capability requires a low-level whole-body controller that translates task-level manipulation goals into coordinated arm and leg motions while maintaining balance. We present a unified whole-body controller trained with reinforcement learning that directly maps 6-DoF end-effector targets to coordinated actions for the bipedal base and robotic arm. Given only an end-effector target, the learned controller autonomously coordinates reaching, postural adaptation, and stepping without explicit base-velocity or footstep commands. A reward-gating strategy regulates the trade-offs among end-effector tracking, locomotion, and balance during training, while a temporal context estimator combines windowed Transformer encoding, recurrent GRU memory, and auxiliary dynamics prediction to extract dynamics-relevant information from observation history. Real-robot experiments demonstrate that the same controller supports reaching, postural adaptation, and stepping under commands from VR teleoperation, a learned diffusion policy, and scripted trajectories, providing a common end-effector interface for diverse manipulation tasks.

cs.RO↗
arXiv2026

MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting

Accurate station-level precipitation nowcasting is critical for agriculture, water resource management, and disaster prevention, which typically is formulated as a time series forecasting problem. However, conventional time-series modeling techniques face two major challenges in addressing station-level precipitation nowcasting: (1) Lack of Physics-Guided Modeling}, where meteorological variables are treated as a homogeneous set without accounting for their distinct roles in precipitation formation, leads to predictions that deviate from the physical processes governing precipitation. (2) Severe zero inflation in precipitation, where dry intervals dominate the dataset, obscuring meaningful precipitation patterns and complicating the predictive modeling. To address these challenges, we propose \textbf{MZ-Rain}, a moisture-budget-guided zero-inflated sLSTM framework for station-level precipitation nowcasting. Guided by the moisture budget equation, MZ-Rain decomposes the precipitation formation process into process-specific pathways corresponding to moisture storage, moisture transport, surface evaporation, and precipitation persistence, and captures their temporal evolution through dedicated sLSTM branches. To account for the zero-inflated nature of precipitation, MZ-Rain introduces an adaptive Tweedie modeling strategy that adaptively modulates the rainfall mean while jointly learning precipitation occurrence as an auxiliary task, enabling the model to better balance dry-wet discrimination and quantitative precipitation estimation. Extensive experiments across diverse geographical and climatic regimes demonstrate that MZ-Rain consistently outperforms strong baselines on multiple evaluation metrics, including CSI, FAR, MSE, and MAE. In particular, the model exhibits superior skill in forecasting heavy precipitation events, while benefiting from physically grounded process modeling.

cs.AI↗
arXiv2026

MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios

Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available.

cs.CV↗
arXiv2026

Switchable chiral antiferromagnetism through nonlinear magnetic susceptibility

Antiferromagnets (AFM) have attracted considerable attention in recent years because a number of nontrivial, technologically relevant properties associated with time-reversal symmetry (TRS) breaking are discovered in many materials. However, time-reversal (TR) partners of AFM states are generally challenging to be selected deterministically except in a few cases with nonzero net magnetization. Recently, it has been shown that the TR partners of the kagome spin ice ground state in HoAgGe with strictly zero net magnetization can be selected through a nonlinear magnetic susceptibility $χ^{(1)}$. In this work, we generalize this scenario to a broad class of chiral AFM with zero net magnetization but field-switchable ground states through $χ^{(1)}$. After a general discussion of $χ^{(1)}$ and its symmetry constraints, we first present a first-principles formalism for calculating it including both mean-field and self-consistent corrections, and then apply the approach to the noncollinear AFM family Mn$_3X$N ($X=$ Ni, Ag, Ga, Zn, Sn) in the $Γ_{5g}$ phase. An intuitive picture of the origin of $χ^{(1)}$ in similar noncollinear AFM is illustrated using 3-sublattice toy model. The model also predicts a nontrivial temperature dependence of $χ^{(1)}$ due to competitions between the longitudinal and transverse single-spin susceptibilities. Our work shows that nonlinear susceptibility can serve as a general protocol for accessing and switching TR partners in fully compensated AFM.

cond-mat.mtrl-sci↗
arXiv2026

SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering

Driving scene reconstruction and rendering, especially with 3D Gaussian Splatting, has become an important component of autonomous driving simulation. However, rendered views often degrade under extrapolated ego trajectories and scene edits, producing blurry structures, temporal flicker, and foreground-background misalignment. Existing refinement methods are commonly designed for a specific setting, such as image-level novel-view repair or object-editing correction. In this paper, we introduce SPVC, a structured and panoptic video fixing framework for cross-dataset driving scene rendering. The name summarizes four design principles. (1) Structured fixing denotes the use of explicit spatial conditions, including camera pose, 3D bounding boxes, and HD maps, to guide the repair process and reduce uncontrolled hallucination. (2) Panoptic fixing refers to correcting both background rendering artifacts, such as distorted roads, buildings, and lanes, and foreground vehicle artifacts introduced by scene editing, such as inconsistent object appearance. (3) Video fixing means that the model operates on driving sequences rather than isolated frames, allowing temporal cues to be used during artifact correction. (4) Cross-dataset fixing means that a single shared network is trained and applied across multiple driving datasets, reducing the need for dataset-specific or scene-specific fixers. Concretely, we construct paired degraded-clean training data by simulating under-constrained 3DGS rendering and foreground vehicle insertion artifacts, and train a two-stage controllable video diffusion model that first addresses video-level appearance and then refines scene layout with structured controls.

cs.CV↗
arXiv2026

Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception

Legged robots require robust agility to perceive and interact with complex and dynamic environments within a constrained time. However, most existing quadruped locomotion works rely on velocity-tracking policy, which struggle to reach precise targets within strict temporal constraints. Moreover, integrating real-time perception with agile locomotion for highly dynamic targets remains challenging due to sensor latency and processing delays. To concretely study and benchmark such agility in dynamic settings, we introduce a challenging ball-catching task for legged robots. This paper proposes an integrated framework that combines a vision module for landing point and time prediction with a direct position and time conditioned RL locomotion policy, instead of intermediate velocity commands. Beyond the method design, this work presents a system-level contribution that completes real-time robotic interception system that integrates multi-camera perception, online trajectory prediction, low-latency target communication, and sim-to-real locomotion control into a closed-loop deployment pipeline. By explicitly predicting the future spatial-temporal target, our approach mitigates perception latency during dynamic interception. We conducted extensive ball-catching experiments for the legged robot. Through comparative experiments against a velocity-tracking baseline, our direct target-conditioned approach achieves a higher success rate in catching balls with predicted landing spots within 2 meters and flight times between 0.8 and 1.2 seconds. This shows that the robot has successfully completed the dynamic ball-catching task under our tested setup. Furthermore, our policy exhibits a smaller performance gap after deployment, suggesting improved sim-to-real behavior in these trials.

cs.RO↗
arXiv2026

Long-Term Memory for VLA-based Agents in Open-World Task Execution

Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical laboratory automation remains restricted by limited long-horizon reasoning and the absence of persistent experience accumulation. Existing frameworks typically treat planning and execution as decoupled processes, often failing to consolidate successful strategies, which results in inefficient trial-and-error in multi-stage protocols. In this paper, we propose ChemBot, a dual-layer, closed-loop framework that integrates an autonomous AI agent with a progress-aware VLA model (Skill-VLA) for hierarchical task decomposition and execution. ChemBot utilizes a dual-layer memory architecture to consolidate successful trajectories into retrievable assets, while a Model Context Protocol (MCP) server facilitates efficient sub-agent and tool orchestration. To address the inherent limitations of VLA models, we further implement a future-state-based asynchronous inference mechanism to mitigate trajectory discontinuities. Extensive experiments on collaborative robots demonstrate that ChemBot achieves superior operational safety, precision, and task success rates compared to existing VLA baselines in complex, long-horizon chemical experimentation.

cs.RO↗
arXiv2026

World Translation: Minimizing Sim-to-Real Gap with Backward Dynamics Extraction and Unpaired Domain Translation

The gap between simulation and reality remains a fundamental challenge in deploying simulation-trained robotic policies in the real world. Real-to-sim methods narrow this gap from the real side, learning transition dynamics from real data to build a more realistic digital world. Learned dynamics models are their dominant instance. Such methods, however, face a partial observability problem: the same observation may branch to different transitions due to unobservable factors. Existing methods assume these factors can be recovered from observation history. However, this may fail whenever observation history is uninformative, such as a sudden contact event with no prior warning. To address this limitation, we propose \textit{World Translation}, which exploits a complementary strength of simulators and learned dynamics. Simulators are deterministic but physically imperfect, while learned models are accurate but underdetermined under partial observability. Rather than predicting transitions forward from history, we extract the unobservable dynamics information backward from an observed transition, then translate this feature across simulation and reality as an unpaired domain-translation problem that preserves dynamics content while transferring domain style. Experiments across humanoid, quadruped, and manipulator platforms show that our method achieves more accurate dynamics modeling than baselines, with the largest gains when unobservable factors cannot be recovered from observation history. Real-robot deployment on Go2 quadruped confirms improved policy transfer.

cs.RO↗
arXiv2026

Temperature-invariant magneto-optical Kerr effect in a noncollinear antiferromagnet

Noncollinear antiferromagnets exhibit anomalous Hall and magneto-optical Kerr effects driven by Berry curvature despite negligible net magnetization, promising ultrafast spintronic applications. While both effects are theoretically expected to reveal the intrinsic Berry curvature that serves as a spintronic memory bit, their quantitative interpretation is complicated by additional temperature-dependent contributions superimposed on the magnetic order parameter: extrinsic skew scattering in dc Hall transport, and optical-resonance effects in visible-wavelength Kerr measurements. Here we perform polar Kerr measurements at the infrared telecommunication wavelength (1550 nm) on epitaxial, stoichiometric Mn3NiN single crystal films, revealing for the first time a spontaneous Kerr signal that remains stable within a few percent over a 200 K range below the Néel temperature. This temperature-invariant intrinsic Kerr response contrasts with the strongly temperature-dependent anomalous Hall effect in the same sample dominated by extrinsic skew scattering. Our findings establish infrared Kerr effect as a robust, local probe of Berry curvature in noncollinear antiferromagnets, enabling quantitative characterization and advancing antiferromagnetic spintronic technologies.

cond-mat.str-el↗
arXiv2026

Multi-Embodiment Robotic Retargeting via Guided Diffusion Model

Motion retargeting for specific robot from existing motion datasets is one critical step in transferring motion patterns from human behaviors to and across various robots. However, inconsistencies in topological structure, geometrical parameters as well as joint correspondence make it difficult to handle diverse embodiments with a unified retargeting architecture. In this work, we propose a novel unified graph-conditioned diffusion-based motion generation framework for retargeting reference motions across diverse embodiments. The intrinsic characteristics of heterogeneous embodiments are represented with graph structure that effectively captures topological and geometrical features of different robots. Such a graph-based encoding further allows for knowledge exploitation at the joint level with a customized attention mechanisms developed in this work. For lacking ground truth motions of the desired embodiment, we utilize an energy-based guidance formulated as retargeting losses to train the diffusion model. As one of the first cross-embodiment motion retargeting methods in robotics, our experiments validate that the proposed model can retarget motions across heterogeneous embodiments in a unified manner. Moreover, it demonstrates a certain degree of generalization to both diverse skeletal structures and similar motion patterns.

cs.RO↗
arXiv2026

CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation

Achieving everyday tasks with humanoid robots requires coordinating stable locomotion with versatile manipulation. However, existing whole-body controllers still face significant challenges. Methods trained solely via command sampling, without motion-capture (MoCap) data, often struggle with sparse rewards and require carefully tuned curricula to converge. This is especially problematic for upper-body control, where the resulting motions deviate from human-like statistics and degrade whole-body coordination. Conversely, approaches that imitate full-body MoCap data suffer from dataset imbalance, as many locomotion trajectories are overly aggressive for stable-locomotion scenarios, necessitating extensive data filtering and augmentation. To address this, we present Composite Whole-Body Imitation (CWI), a framework that decouples the use of MoCap data for upper-body manipulation and lower-body locomotion. This decoupling allows us to exploit the full MoCap dataset of diverse manipulation references, while stable, command-conditioned lower-body locomotion is guided by dual discriminators trained on curated expert-quality walking and squatting clips via an Adversarial Motion Prior (AMP). A multi-critic architecture reduces conflicts among locomotion, manipulation, and motion-style objectives, and a teacher--student distillation stage yields a whole-body policy conditioned only on bimanual hand poses and velocity/height commands. We evaluate CWI through simulation experiments and real-world deployment on a full-size LimX Oli humanoid. The results show competitive loco-manipulation performance, robust whole-body coordination, and practical teleoperation without full-body motion-capture equipment. A project page with supplementary material can be found at https://cwi-ral.github.io/CWI-RAL-Webpage.

cs.RO↗
arXiv2026

AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior

Reliable depth perception is critical for robotic manipulation, especially for non-Lambertian objects such as transparent or highly specular surfaces, where raw depth measurements are often corrupted or missing. These failures frequently propagate to motion planning, resulting in invalid grasp poses and execution errors. We propose AISPO, a depth completion framework that improves depth reliability for manipulation in challenging sensing conditions. AISPO combines multi-scale RGB-D feature fusion with an affine-invariant shape prior to enforce geometric consistency and mitigate catastrophic depth failures. Unlike methods that focus primarily on average depth accuracy, our approach emphasizes physical plausibility and structural integrity of the predicted depth maps. Extensive benchmark evaluations demonstrate competitive performance and strong generalization to unseen objects and novel scenes. Real-world grasping experiments further show that enhanced depth reliability significantly improves manipulation success rates, particularly for transparent objects where many existing methods fail to produce physically usable depth estimates.

cs.RO↗
arXiv2026

Critical Sobolev inequalities and global extremals for homogeneous Hörmander vector fields on $\mathbb{R}^n$

We study critical Sobolev inequalities and Sobolev extremal functions for homogeneous Hörmander vector fields on $\mathbb R^n$. The focus is the non-equiregular case. In this setting, the sub-Riemannian flag may have different growth at different points, the volume of subunit balls is not governed by a single local dimension, and the translation structure available on Carnot groups is absent in general. These features make both the range of admissible Sobolev exponents and the attainment of the optimal Sobolev constant substantially more delicate, especially on unbounded domains. We first give a domain-dependent description of the admissible Sobolev exponents in terms of the volume growth rates of subunit balls. This description separates the roles of the pointwise homogeneous dimension, the non-isotropic dimension of the domain, and the singular strata that may be approached at infinity. As a consequence, we prove a global Sobolev inequality for all homogeneous Hörmander vector fields on $\mathbb R^n$, without assuming any underlying group law. We then prove that the optimal Sobolev constant is attained. The main new geometric ingredient is a smooth family of maps $T(w,x)$ along the maximal level set $H$ of the pointwise homogeneous dimension. These maps preserve Lebesgue measure and the horizontal gradient, and they play the role of left translations in a setting where no group multiplication is available. In this sense, $T(w,x)$ compensates for the lack of an intrinsic translation structure and allows one to recenter minimizing sequences in the critical concentration-compactness argument. The compactness theorem obtained in this way applies to all homogeneous Hörmander vector fields. We also prove that, on every open set meeting this maximal level set, the optimal Sobolev constant is independent of the domain.

math.AP↗