Searcharxiv⌕ Search

arXiv subjects

Jianan Wang

Publications and source records attributed to Jianan Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action models and world models struggle with accurate 3D geometry and physically meaningful forecasting. We propose PhysMani, a framework that couples a physics-principled 3D Gaussian world model with a future-aware action policy model. The world model learns a divergence-free Gaussian velocity field via online optimization for fast and physically grounded future dynamics prediction. The policy model integrates the predicted 3D scene future dynamics through a learnable token based cross-attention module. We introduce PhysMani-Bench, a dynamic manipulation benchmark with 16 tasks, and demonstrate a superior success rate over strong baselines in both simulation and real-world robot experiments.

cs.RO↗
arXiv2026

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

JD$.$com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production for massive SKUs, and diverse downstream requirements. To address these challenges, we present the JD Oxygen AI Item Center (Oxygen AIIC), an industrial-scale platform built on LLMs/VLMs for item-knowledge production and service. Oxygen AIIC is built around four core pillars: (i) ontology engineering driven by efficient human-AI collaboration, which supports the dynamic evolution and agile expansion of an ontology with millions of entries; (ii) a "Semantic Search then Discrimination"(S2D) knowledge identification architecture that, combined with throughput improvement strategies, enables scalable, extensible, and high-throughput AI Item Library production for tens of billions of SKUs; (iii) self-evolving item-understanding LLMs/VLMs that improve in a stable and controllable manner, enabling knowledge production with 94.2% precision and 82.8% recall; and (iv) a unified item tunnel that serves as the data and service hub. Oxygen AIIC now covers tens of thousands of JD categories and processes hundreds of millions of item updates per day on Huawei Ascend NPUs. It has accumulated hundreds of billions of item-knowledge assets. Deployed across core business scenarios-including search, recommendation, operations, category planning-Oxygen AIIC has delivered measurable gains at scale. Search-traffic coverage reaches 80.4%, item-information quality issues drop by 37%, the automated fill rate of core attributes during item listing exceeds 80%.

cs.AI↗
arXiv2026

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos

Generalist Vision-Language-Action models remain constrained by the scarcity of robotic data relative to the abundance of human video demonstrations. Existing Latent Action Models attempt to use video data but often suffer from visual entanglement, encoding noise rather than manipulation skills. To address this limitation, we propose Contrastive Latent Action Pretraining (CLAP), a framework that first uses Act-VAE to learn an executable action-token vocabulary from robot trajectories and then aligns human visual transitions with this vocabulary through contrastive learning. This alignment maps unlabeled human videos into a physically grounded latent action space rather than reconstructing appearance. Building on the aligned tokens, we train CLAP-NTP as an autoregressive VLA using robot demonstrations and pseudo-labeled human videos, preserving instruction following and object generalization. For deployment and target-domain adaptation, we further introduce a post-training strategy that combines CLAP-RF, a Rectified Flow action head for low-latency continuous action chunk prediction, with Knowledge Matching regularization to preserve pretrained semantic knowledge during fine-tuning. Extensive experiments show that CLAP achieves strong performance against competitive baselines while enabling effective skill transfer from human videos to robotic execution.

cs.RO↗
arXiv2026

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km

With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often leads to overfitting to individual scenes. In this paper, we introduce a holistic solution that integrates a structured spatial reasoning knowledge system, scale-aware modeling, and a progressive training paradigm, as the first attempt to broaden the all-scale spatial intelligence of MLLMs to the best of our knowledge. Using a task-specific, specialist-driven automated pipeline, we curate over 38K video scenes across 5 spatial scales to create SpaceVista-1M, a dataset comprising approximately 1M spatial QA pairs spanning 19 diverse task types. While specialist models can inject useful domain knowledge, they are not reliable for evaluation. We then build an all-scale benchmark with precise annotations by manually recording, retrieving, and assembling video-based data. However, naive training with SpaceVista-1M often yields suboptimal results due to the potential knowledge conflict. Accordingly, we introduce SpaceVista-7B, a spatial reasoning model that accepts dense inputs beyond semantics and uses scale as an anchor for scale-aware experts and progressive rewards. Finally, extensive evaluations across 5 benchmarks, including our SpaceVista-Bench, demonstrate competitive performance, showcasing strong generalization across all scales and scenarios. Our dataset, model, and benchmark will be released on https://peiwensun2000.github.io/mm2km .

cs.CV↗
arXiv2026

MetaphorVU: Towards Metaphorical Video Understanding

Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.

cs.CV↗
arXiv2026

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models when encountering unseen real-world visual disturbances, particularly under imperfect visual conditions. In this work, we conduct a systematic study based on recent state-of-the-art VLA models and reveal a significant performance drop when visual disturbances absent from the training data are introduced. To mitigate this issue, we propose a lightweight adapter module grounded in information theory, termed the Information Bottleneck Adapter (IB-Adapter), which selectively filters potential noise from visual inputs. Without requiring any extra data or augmentation strategies, IB-Adapter consistently improves over the baseline by an average of 30%, while adding fewer than 10M parameters, demonstrating notable efficiency and effectiveness. Furthermore, even with a 14x smaller backbone (0.5B parameters) and no pre-training on the Open X-Embodiment dataset, our model StableVLA achieves robustness competitive with 7B-scale state-of-the-art VLAs. With negligible parameter overhead (<10M), our approach maintains accuracy on long-horizon tasks and surpasses OpenPi under both synthetic and physical visual corruptions.

cs.CV↗
arXiv2026

Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation

Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past observations for interpreting ongoing actions, we propose FrameCache, a training-free, causality-consistent reference frame framework. FrameCache explicitly converts historical generation results into causal guidance through two complementary mechanisms. First, at the reference level, a novel Screen-Cache-Match (SCM) strategy constructs a dynamic, high-quality reference memory, ensuring motion-consistent appearance guidance to reduce identity drift. Second, at the generative level, a Trajectory-Aware Autoregressive Generation (TAAG) mechanism aligns denoising trajectories across adjacent video chunks. This is achieved through an overlap-aware latent propagation and a dual-domain fusion strategy that seamlessly blends low-frequency structural layouts with high-frequency textural details. Extensive experiments on standard benchmarks demonstrate that FrameCache consistently improves temporal coherence and visual stability while integrating seamlessly with diverse diffusion baselines. Code will be made publicly available.

cs.GR↗
arXiv2026

Fronto-parietal and fronto-temporal EEG coherence as predictive neuromarkers of transcutaneous auricular vagus nerve stimulation response in treatment-resistant schizophrenia: A machine learning study

Response variability limits the clinical utility of transcutaneous auricular vagus nerve stimulation (taVNS) for negative symptoms in treatment-resistant schizophrenia (TRS). This study aimed to develop an electroencephalography (EEG)-based machine learning (ML) model to predict individual response and explore associated neurophysiological mechanisms. We used ML to develop and validate predictive models based on pre-treatment EEG data features (power, coherence, and dynamic functional connectivity) from 50 TRS patients enrolled in the taVNS trial, within a nested cross-validation framework. Participants received 20 sessions of active or sham taVNS (n = 25 each) over two weeks, followed by a two-week follow-up. The prediction target was the percentage change in the positive and negative syndrome scale-factor score for negative symptoms (PANSS-FSNS) from baseline to post-treatment, with further evaluation of model specificity and neurophysiological relevance.The optimal model accurately predicted taVNS response in the active group, with predicted PANSS-FSNS changes strongly correlated with observed changes (r = 0.87, p < .001); permutation testing confirmed performance above chance (p < .001). Nine consistently retained features were identified, predominantly fronto-parietal and fronto-temporal coherence features. Negligible predictive performance in the sham group and failure to predict positive symptom change support the predictive specificity of this oscillatory signature for taVNS-related negative symptom improvement. Two coherence features within fronto-parietal-temporal networks showed post-taVNS changes significantly associated with symptom improvement, suggesting dual roles as predictors and potential therapeutic targets. EEG oscillatory neuromarkers enable accurate prediction of individual taVNS response in TRS, supporting mechanism-informed precision neuromodulation strategies.

cs.LG↗
arXiv2026

Context and Diversity Matter: The Emergence of In-Context Learning in World Models

The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with novel or rare configurations. We investigate in-context learning (ICL) of world models, shifting attention from zero-shot performance to the growth and asymptotic limits of the world model. Our contributions are three-fold: (1) we formalize ICL of a world model and identify two core mechanisms: environment recognition (ER) and environment learning (EL); (2) we derive error upper-bounds for both mechanisms that expose how the mechanisms emerge; and (3) we empirically confirm that distinct ICL mechanisms exist in the world model, and we further investigate how data distribution and model architecture affect ICL in a manner consistent with theory. These findings demonstrate the potential of self-adapting world models and highlight the key factors behind the emergence of EL/ER, most notably the necessity of long context and diverse environments.

cs.LG↗
arXiv2026

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency in geometry, material properties, and light-matter interactions. Existing training-free methods offer broad applicability across editing tasks but struggle with precise color control and often introduce visual inconsistency in both edited and non-edited regions. In this work, we present ColorCtrl, a training-free color editing method that leverages the attention mechanisms of modern Multi-Modal Diffusion Transformers (MM-DiT). By disentangling structure and color through targeted manipulation of attention maps and value tokens, our method enables accurate and consistent color editing, along with word-level control of attribute intensity. Our method modifies only the intended regions specified by the prompt, leaving unrelated areas untouched. Extensive experiments on both SD3 and FLUX.1-dev demonstrate that ColorCtrl outperforms existing training-free approaches and achieves state-of-the-art performances in both edit quality and consistency. Furthermore, our method surpasses strong commercial models such as FLUX.1 Kontext Max and GPT-4o Image Generation in terms of consistency. When extended to video models like CogVideoX, our approach exhibits greater advantages, particularly in maintaining temporal coherence and editing stability. Finally, our method also generalizes to instruction-based editing diffusion models such as Step1X-Edit and FLUX.1 Kontext dev, further demonstrating its versatility.

cs.GR↗
arXiv2026

Plasma Decay of Nanosecond Pulsed Laser-Produced Ar and Ar-H2O Sparks at Atmospheric Pressure

Time-resolved diagnostics were applied to investigate free-electron properties in nanosecond laser-produced discharges sustained at atmospheric pressure in Ar and in Ar with 3% H2O. The discharges were generated using 23 ns, 1064 nm laser pulses. Broadband plasma imaging and laser Thomson scattering were combined with optical emission spectroscopy, with particular emphasis on Stark broadening of the Halpha and Hbeta lines. The plasma exhibited a bright emission that persisted for up to 30--40 us after breakdown, followed by a very weak glow lasting up to 19 ms. Peak electron number density of about 2 x 10^17 cm-3 and electron temperature of about 7 eV were measured. Excellent agreement between both techniques was obtained for absolute electron number densities. The inferred temporal decay of free electrons is consistent with processes dominated by ambipolar expansion and two- and three-body electron-ion recombination. These results provide benchmark data for modeling nanosecond laser discharges and demonstrate the reliability of combining Thomson scattering with Stark broadening in atmospheric laser sparks.

physics.plasm-ph↗
arXiv2025

ERIENet: An Efficient RAW Image Enhancement Network under Low-Light Environment

RAW images have shown superior performance than sRGB images in many image processing tasks, especially for low-light image enhancement. However, most existing methods for RAW-based low-light enhancement usually sequentially process multi-scale information, which makes it difficult to achieve lightweight models and high processing speeds. Besides, they usually ignore the green channel superiority of RAW images, and fail to achieve better reconstruction performance with good use of green channel information. In this work, we propose an efficient RAW Image Enhancement Network (ERIENet), which parallelly processes multi-scale information with efficient convolution modules, and takes advantage of rich information in green channels to guide the reconstruction of images. Firstly, we introduce an efficient multi-scale fully-parallel architecture with a novel channel-aware residual dense block to extract feature maps, which reduces computational costs and achieves real-time processing speed. Secondly, we introduce a green channel guidance branch to exploit the rich information within the green channels of the input RAW image. It increases the quality of reconstruction results with few parameters and computations. Experiments on commonly used low-light image enhancement datasets show that ERIENet outperforms state-of-the-art methods in enhancing low-light RAW images with higher effiency. It also achieves an optimal speed of over 146 frame-per-second (FPS) for 4K-resolution images on a single NVIDIA GeForce RTX 3090 with 24G memory.

cs.CV↗
arXiv2025

Mind to Hand: Purposeful Robotic Control via Embodied Reasoning

Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abilities in physical action remains a major challenge. We introduce Lumo-1, a generalist vision-language-action (VLA) model that unifies robot reasoning ("mind") with robot action ("hand"). Our approach builds upon the general multi-modal reasoning capabilities of pre-trained vision-language models (VLMs), progressively extending them to embodied reasoning and action prediction, and ultimately towards structured reasoning and reasoning-action alignment. This results in a three-stage pre-training pipeline: (1) Continued VLM pre-training on curated vision-language data to enhance embodied reasoning skills such as planning, spatial understanding, and trajectory prediction; (2) Co-training on cross-embodiment robot data alongside vision-language data; and (3) Action training with reasoning process on trajectories collected on Astribot S1, a bimanual mobile manipulator with human-like dexterity and agility. Finally, we integrate reinforcement learning to further refine reasoning-action consistency and close the loop between semantic inference and motor control. Extensive experiments demonstrate that Lumo-1 achieves significant performance improvements in embodied vision-language reasoning, a critical component for generalist robotic control. Real-world evaluations further show that Lumo-1 surpasses strong baselines across a wide range of challenging robotic tasks, with strong generalization to novel objects and environments, excelling particularly in long-horizon tasks and responding to human-natural instructions that require reasoning over strategy, concepts and space.

cs.RO↗
arXiv2025

ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking

Large Language Models (LLMs) have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as cloud-based services, allowing users to access powerful LLMs via the Internet. However, this deployment model introduces a new class of threat: denial-of-service (DoS) attacks via unbounded reasoning, where adversaries craft specially designed inputs that cause the model to enter excessively long or infinite generation loops. These attacks can exhaust backend compute resources, degrading or denying service to legitimate users. To mitigate such risks, many LLM providers adopt a closed-source, black-box setting to obscure model internals. In this paper, we propose ThinkTrap, a novel input-space optimization framework for DoS attacks against LLM services even in black-box environments. The core idea of ThinkTrap is to first map discrete tokens into a continuous embedding space, then undertake efficient black-box optimization in a low-dimensional subspace exploiting input sparsity. The goal of this optimization is to identify adversarial prompts that induce extended or non-terminating generation across several state-of-the-art LLMs, achieving DoS with minimal token overhead. We evaluate the proposed attack across multiple commercial, closed-source LLM services. Our results demonstrate that, even far under the restrictive request frequency limits commonly enforced by these platforms, typically capped at ten requests per minute (10 RPM), the attack can degrade service throughput to as low as 1% of its original capacity, and in some cases, induce complete service failure.

cs.CR↗
arXiv2025

Refaçade: Editing Object with Given Reference Texture

Recent advances in diffusion models have brought remarkable progress in image and video editing, yet some tasks remain underexplored. In this paper, we introduce a new task, Object Retexture, which transfers local textures from a reference object to a target object in images or videos. To perform this task, a straightforward solution is to use ControlNet conditioned on the source structure and the reference texture. However, this approach suffers from limited controllability for two reasons: conditioning on the raw reference image introduces unwanted structural information, and it fails to disentangle the visual texture and structure information of the source. To address this problem, we propose Refaçade, a method that consists of two key designs to achieve precise and controllable texture transfer in both images and videos. First, we employ a texture remover trained on paired textured/untextured 3D mesh renderings to remove appearance information while preserving the geometry and motion of source videos. Second, we disrupt the reference global layout using a jigsaw permutation, encouraging the model to focus on local texture statistics rather than the global layout of the object. Extensive experiments demonstrate superior visual quality, precise editing, and controllability, outperforming strong baselines in both quantitative and human evaluations. Code is available at https://github.com/fishZe233/Refacade.

cs.CV↗
arXiv2025

SimTac: A Physics-Based Simulator for Vision-Based Tactile Sensing with Biomorphic Structures

Tactile sensing in biological organisms is deeply intertwined with morphological form, such as human fingers, cat paws, and elephant trunks, which enables rich and adaptive interactions through a variety of geometrically complex structures. In contrast, vision-based tactile sensors in robotics have been limited to simple planar geometries, with biomorphic designs remaining underexplored. To address this gap, we present SimTac, a physics-based simulation framework for the design and validation of biomorphic tactile sensors. SimTac consists of particle-based deformation modeling, light-field rendering for photorealistic tactile image generation, and a neural network for predicting mechanical responses, enabling accurate and efficient simulation across a wide range of geometries and materials. We demonstrate the versatility of SimTac by designing and validating physical sensor prototypes inspired by biological tactile structures and further demonstrate its effectiveness across multiple Sim2Real tactile tasks, including object classification, slip detection, and contact safety assessment. Our framework bridges the gap between bio-inspired design and practical realisation, expanding the design space of tactile sensors and paving the way for tactile sensing systems that integrate morphology and sensing to enable robust interaction in unstructured environments.

cs.RO↗
arXiv2025

DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation

Learning whole-body mobile manipulation via imitation is essential for generalizing robotic skills to diverse environments and complex tasks. However, this goal is hindered by significant challenges, particularly in effectively processing complex observation, achieving robust generalization, and generating coherent actions. To address these issues, we propose DSPv2, a novel policy architecture. DSPv2 introduces an effective encoding scheme that aligns 3D spatial features with multi-view 2D semantic features. This fusion enables the policy to achieve broad generalization while retaining the fine-grained perception necessary for precise control. Furthermore, we extend the Dense Policy paradigm to the whole-body mobile manipulation domain, demonstrating its effectiveness in generating coherent and precise actions for the whole-body robotic platform. Extensive experiments show that our method significantly outperforms existing approaches in both task performance and generalization ability. Project page is available at: https://selen-suyue.github.io/DSPv2Net/.

cs.RO↗
arXiv2025

BeSimulator: A Large Language Model Powered Text-based Behavior Simulator

Traditional robot simulators focus on physical process modeling and realistic rendering, often suffering from high computational costs, inefficiencies, and limited adaptability. To handle this issue, we concentrate on behavior simulation in robotics to analyze and validate the logic behind robot behaviors, aiming to achieve preliminary evaluation before deploying resource-intensive simulators and thus enhance simulation efficiency. In this paper, we propose BeSimulator, a modular and novel LLM-powered framework, as an attempt towards behavior simulation in the context of text-based environments. By constructing text-based virtual environments and performing semantic-level simulation, BeSimulator can generalize across scenarios and achieve long-horizon complex simulation. Inspired by human cognition paradigm, it employs a ``consider-decide-capture-transfer'' four-phase simulation process, termed Chain of Behavior Simulation (CBS), which excels at analyzing action feasibility and state transition. Additionally, BeSimulator incorporates code-driven reasoning to enable arithmetic operations and enhance reliability, and reflective feedback to refine simulation. Based on our manually constructed behavior-tree-based simulation benchmark, BTSIMBENCH, our experiments show a significant performance improvement in behavior simulation compared to baselines, ranging from 13.60% to 24.80%. Code and data are available at https://github.com/Dawn888888/BeSimulator.

cs.RO↗