Searcharxiv⌕ Search

arXiv subjects

Shan Wang

Publications and source records attributed to Shan Wang.

At least 19 recordsLinked to original sources
arXiv2026

FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world. Yet methods that perform well in simulation can degrade substantially on real robots, especially in long-horizon deformable-object manipulation, where policies must track changing states and execute reliable multi-stage bimanual interactions. Existing real-robot benchmarks mainly focus on short-horizon rigid-object tasks and offer limited coverage of long-horizon deformable manipulation. We introduce FolDeX, a physical-world benchmark built entirely from real-robot data, with garment folding as its primary task. Since real-robot data collection is costly, FolDeX studies how heterogeneous physical experience can be reused efficiently. The benchmark is organized around four research axes: leveraging human intervention and recovery data collected during deployment; transferring data across tasks, including across garment categories and from rigid to deformable-object manipulation; reusing data across scenes with changes in lighting, background, and layout; and transferring data across robotic embodiments. FolDeX provides 2,000+ hours of real-robot data spanning 20+ tasks and 10+ embodiments. We also establish a fair real-robot evaluation platform for externally submitted policies, with standardized tasks, held-out physical objects, controlled initializations, and a unified execution protocol. The platform is publicly accessible at https://ai.midea.com/#/fold-challenge. We hope FolDeX will serve as a unified testbed for heterogeneous real-robot data reuse and reliable long-horizon deformable manipulation.

cs.RO↗
arXiv2026

DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents

High-quality structured organic reaction data are essential for developing artificial intelligence for chemistry (AI4Chem), yet much of this knowledge remains dispersed across patent text, images, and reaction schemes. We present DianShi-RxnDB, a large-scale, fine-grained organic reaction data platform built via a fully automated extraction and normalization pipeline integrating patent text, images, and reaction schemes. Its corpus covers organic synthesis patents from the USPTO and EPO published between 1976 and 2025, yielding approximately 24 million reaction instances, of which approximately 14.8 million (61.7%) pass automated qualification checks. Each instance represents a specific single-step experiment recording participants, roles, quantities, temperatures, reaction times, yields, experimental procedures, and provenance links to source patents. In a manual evaluation of 1,300 sampled qualified instances, the micro-averaged field-level accuracy was 92.95%. A matched comparison with Pistachio further indicated advantages in deduplicated record counts, representation granularity, and field-level exact agreement. The platform provides a Web research workbench for searching, filtering, comparing, and source-verifying records, and a Model Context Protocol (MCP) service offering AI agents composable structured retrieval tools. DianShi-RxnDB is available at https://dianshi.opendatalab.org.cn/ .

cs.CL↗
arXiv2026

MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos

Mental health understanding in long-form videos requires nuanced reasoning over observable behavior, interpersonal context, and latent psychological states. Existing benchmarks largely reduce this task to coarse-grained classification, providing limited insight into whether models truly understand psychological phenomena or rely on superficial correlations. To address this limitation, we introduce MMHBench, a comprehensive multimodal benchmark for multi-perspective mental health understanding, comprising 268 long-form videos and 2,184 carefully curated questions. MMHBench organizes the evaluation into two complementary settings: (1) third-person assessment, consisting of 605 questions that focus on the interpretation of observable behaviors and multimodal evidence, and (2) first-person perspective-taking, comprising 1,579 questions that require perspective-conditioned reasoning to identify the interpretation of the mental state supported by the available multimodal evidence. We propose a Multi-Agent Question Generation (MAQG) framework that simulates diverse social roles to synthesize questions from multiple perspectives. The generated questions are refined through multi-role feedback and iterative optimization, followed by expert-guided verification to ensure quality and validity. Extensive evaluation of 22 representative multimodal large language models (MLLMs), spanning both open-source and leading closed-source models, demonstrates that long-form video mental health understanding remains highly challenging.

cs.AI↗
arXiv2026

Second order necessary conditions for quantum stochastic optimal control problems

This paper aims to establish second order necessary conditions for optimal control in quantum stochastic systems. We employ a variational approach, analogous to methods in classical stochastic control, to analyze systems governed by quantum stochastic differential equations driven by fermionic Brownian motion, where the control enters both the drift and diffusion terms. This result provides a theoretical foundation for further exploration of optimization problems and their practical applications in the field of quantum stochastic control.

math.OC↗
arXiv2026

Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps

We propose Light-Geometry Interaction (LGI) maps, a novel representation that encodes light-aware occlusion from monocular depth. Unlike ray tracing, which requires full 3D reconstruction, LGI captures essential light-shadow interactions reliably and accurately, computed from off-the-shelf 2.5D depth map predictions. LGI explicitly ties illumination direction to geometry, providing a physics-inspired prior that constrains generative models. Without such prior, these models often produce floating shadows, inconsistent illumination, and implausible shadow geometry. Building on this representation, we propose a unified pipeline for joint shadow generation and relighting - unlike prior methods that treat them as disjoint tasks - capturing the intrinsic coupling of illumination and shadowing essential for modeling indirect effects. By embedding LGI into a bridge-matching generative backbone, we reduce ambiguity and enforce physically consistent light-shadow reasoning. To enable effective training, we curated the first large-scale benchmark dataset for joint shadow and relighting, covering reflections, transparency, and complex interreflections. Experiments show significant gains in realism and consistency across synthetic and real images. LGI thus bridges geometry-inspired rendering with generative modeling, enabling efficient, physically consistent shadow generation and relighting.

cs.CV↗
arXiv2025

Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference

The rapid advancement of large language models (LLMs) and domain-specific AI agents has greatly expanded the ecosystem of AI-powered services. User queries, however, are highly diverse and often span multiple domains and task types, resulting in a complex and heterogeneous landscape. This diversity presents a fundamental routing challenge: how to accurately direct each query to an appropriate execution unit while optimizing both performance and efficiency. To address this, we propose MoMA (Mixture of Models and Agents), a generalized routing framework that integrates both LLM and agent-based routing. Built upon a deep understanding of model and agent capabilities, MoMA effectively handles diverse queries through precise intent recognition and adaptive routing strategies, achieving an optimal balance between efficiency and cost. Specifically, we construct a detailed training dataset to profile the capabilities of various LLMs under different routing model structures, identifying the most suitable tasks for each LLM. During inference, queries are dynamically routed to the LLM with the best cost-performance efficiency. We also introduce an efficient agent selection strategy based on a context-aware state machine and dynamic masking. Experimental results demonstrate that the MoMA router offers superior cost-efficiency and scalability compared to existing approaches.

cs.MA↗
arXiv2025

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection

Multimodal large language models achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the overreliance on prompts and prior outputs, and co-occurrence bias, spurious correlations between frequently paired objects. We propose Gradient-based Influence-Aware Constrained Decoding (GACD), an inference-based method, that addresses both biases without auxiliary models, and is readily applicable to existing models without finetuning. The core of our approach is bias estimation, which uses first-order Taylor gradients to understand the contribution of individual tokens-visual features and text tokens-to the current output. Based on this analysis, GACD mitigates hallucinations through two components: (1) suppressing spurious visual features correlated with the output objects, and (2) rebalancing cross-modal contributions by strengthening visual features relative to text. Experiments across multiple benchmarks demonstrate that GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.

cs.CV↗
arXiv2025

Time Tells All: Deanonymization of Blockchain RPC Users with Zero Transaction Fee (Extended Version)

Remote Procedure Call (RPC) services have become a primary gateway for users to access public blockchains. While they offer significant convenience, RPC services also introduce critical privacy challenges that remain insufficiently examined. Existing deanonymization attacks either do not apply to blockchain RPC users or incur costs like transaction fees assuming an active network eavesdropper. In this paper, we propose a novel deanonymization attack that can link an IP address of a RPC user to this user's blockchain pseudonym. Our analysis reveals a temporal correlation between the timestamps of transaction confirmations recorded on the public ledger and those of TCP packets sent by the victim when querying transaction status. We assume a strong passive adversary with access to network infrastructure, capable of monitoring traffic at network border routers or Internet exchange points. By monitoring network traffic and analyzing public ledgers, the attacker can link the IP address of the TCP packet to the pseudonym of the transaction initiator by exploiting the temporal correlation. This deanonymization attack incurs zero transaction fee. We mathematically model and analyze the attack method, perform large-scale measurements of blockchain ledgers, and conduct real-world attacks to validate the attack. Our attack achieves a high success rate of over 95% against normal RPC users on various blockchain networks, including Ethereum, Bitcoin and Solana.

cs.CR↗
arXiv2025

Starfish: Rebalancing Multi-Party Off-Chain Payment Channels

Blockchain technology has revolutionized the way transactions are executed, but scalability remains a major challenge. Payment Channel Network (PCN), as a Layer-2 scaling solution, has been proposed to address this issue. However, skewed payments can deplete the balance of one party within a channel, restricting the ability of PCNs to transact through a path and subsequently reducing the transaction success rate. To address this issue, the technology of rebalancing has been proposed. However, existing rebalancing strategies in PCNs are limited in their capacity and efficiency. Cycle-based approaches only address rebalancing within groups of nodes that form a cycle network, while non-cycle-based approaches face high complexity of on-chain operations and limitations on rebalancing capacity. In this study, we propose Starfish, a rebalancing approach that captures the star-shaped network structure to provide high rebalancing efficiency and large channel capacity. Starfish requires only $N$-time on-chain operations to connect independent channels and aggregate the total budget of all channels. To demonstrate the correctness and advantages of our method, we provide a formal security proof of the Starfish protocol and conduct comparative experiments with existing rebalancing techniques.

cs.CR↗
arXiv2025

Inorganic Catalyst Efficiency Prediction Based on EAPCR Model: A Deep Learning Solution for Multi-Source Heterogeneous Data

The design of inorganic catalysts and the prediction of their catalytic efficiency are fundamental challenges in chemistry and materials science. Traditional catalyst evaluation methods primarily rely on machine learning techniques; however, these methods often struggle to process multi-source heterogeneous data, limiting both predictive accuracy and generalization. To address these limitations, this study introduces the Embedding-Attention-Permutated CNN-Residual (EAPCR) deep learning model. EAPCR constructs a feature association matrix using embedding and attention mechanisms and enhances predictive performance through permutated CNN architectures and residual connections. This approach enables the model to accurately capture complex feature interactions across various catalytic conditions, leading to precise efficiency predictions. EAPCR serves as a powerful tool for computational researchers while also assisting domain experts in optimizing catalyst design, effectively bridging the gap between data-driven modeling and experimental applications. We evaluate EAPCR on datasets from TiO2 photocatalysis, thermal catalysis, and electrocatalysis, demonstrating its superiority over traditional machine learning methods (e.g., linear regression, random forest) as well as conventional deep learning models (e.g., ANN, NNs). Across multiple evaluation metrics (MAE, MSE, R2, and RMSE), EAPCR consistently outperforms existing approaches. These findings highlight the strong potential of EAPCR in inorganic catalytic efficiency prediction. As a versatile deep learning framework, EAPCR not only improves predictive accuracy but also establishes a solid foundation for future large-scale model development in inorganic catalysis.

cs.LG↗
arXiv2024

New Insights on the High Reconnection Rate and the Diminishment of Ion Outflow

The recently discovered electron-only reconnection has drawn great interests due to abnormal features like lack of ion outflows and high reconnection rates. Using particle-in-cell simulations, we investigate their physical mechanisms. The reconnection rate, when normalized by ion parameters ($R_i$), may appear anomalously high, whereas that normalized by electron parameters ($R_e$) remains ~0.1. We propose that the essence of high $R_i$ is insufficient field line bending outside the electron diffusion region, indicating an incomplete development of the ion diffusion region. It may result from bursty reconnection in thin current sheets, or small system sizes. The ion outflow diminishes at high $\beta_i$ when the gyroradius ($\rho_i$) exceeds the system size. Low-velocity ions still experience notable acceleration from Hall fields. However, a local distribution includes many high-velocity ions that experience random accelerations from different electric fields across $\rho_i$, resulting in near-zero bulk velocities. Our study helps understand reconnection structures and the underlying physics for transitions between different regimes.

physics.plasm-ph↗
arXiv2024

Revisit of discrete energy bands in Galilean moon's footprint tails: remote signals of particle absorption

Recent observations from the Juno spacecraft during its transit over flux tubes of the Galilean moons have identified sharp enhancements of particle fluxes at discrete energies. These banded structures have been suspected to originate from a bounce resonance between particles and standing Alfven waves generated by the moon-magnetospheric interaction. Here, we show that predictions from the above hypothesis are inconsistent with the observations, and propose an alternative interpretation that the banded structures are remote signals of particle absorption at the moons. In this scenario, whether a particle would encounter the moon before reaching Juno depends on the number of bounce cycles it experiences within a fixed section of drift motion determined by moon-spacecraft longitudinal separation. Therefore, the absorption bands are expected to appear at discrete, equally-spaced velocities consistent with the observations. This finding improves our understanding of moon-plasma interactions and provides a potential way to evaluate the Jovian magnetospheric models.

astro-ph.EP↗
arXiv2024

Optimal control of quantum stochastic systems in fermion fields: The Pontryagin-type maximum principle (II)

In the present paper, by using the relaxed transposition method[29], we solve the second-order adjoint equations, corresponding to the optimal control of quantum stochastic systems in fermion fields, which plays the fundamental roles in the study of the Pointryagin-type maximum principle in quantum stochastic optimal control. The second-order adjoint equation is a backard operator valued quantum stochastic differential equation, which has no definition in the algebra of bounded operators, and the solution derived from the relaxed transposition method makes sense in W*-topology.

math.OC↗
arXiv2024

Global existence and uniqueness of the density-dependent incompressible Navier-Stokes-Korteweg system with variable capillarity and viscosity coefficients

We consider the global well-posedness of the inhomogeneous incompressible Navier-Stokes-Korteweg system with a general capillary term. Based on the maximal regularity property, we obtain the global existence and uniqueness of solutions to the incompressible Navier-Stokes-Korteweg system with variable viscosity and capillary terms. By assuming the initial density $\rho_0$ is close to a positive constant, additionally, the initial velocity $u_0$ and the initial density $\nabla \rho_0$ are small in critical space $\dot B^{-1+d/p}_{p,1}(\mathbb R^{d})$ $(1<p<d).$ This work relies on the maximal regularity property of the heat equation, of the Stokes equation, and of the Lam\'e equation.

math.AP↗
arXiv2024

Optimal control of quantum system in fermion fields: Pontryagin-type maximum principle(I)

In this paper, the Pontryagin-type maximum principle for optimal control of quantum stochastic systems in fermion fields is obtained. These systems have gained significant prominence in numerous quantum applications ranging from physical chemistry to multi-dimensional nuclear magnetic resonance experiments. Furthermore, we establish the existence and uniqueness of solutions to backward quantum stochastic differential equations driven by fermion Brownian motion. The application of noncommutative martingale inequalities and the martingale representation theorem enables this achievement.

math.OC↗
arXiv2024

Direct observations of cross-scale energy transfer in space plasmas

The collisionless plasmas in space and astrophysical environments are intrinsically multiscale in nature, behaving as conducting fluids at macroscales and kinetically at microscales comparable to ion- and/or electron-gyroradii. A fundamental question in understanding the plasma dynamics is how energy is transported and dissipated across different scales. Here, we present spacecraft measurements in the solar wind upstream of the terrestrial bow shock, in which the macroscale ultra-low-frequency waves and microscale whistler waves simultaneously resonate with the ions. The ion acceleration from ultra-low-frequency waves leads to velocity distributions unstable to the growth of whistler waves, which in turn resonate with the electrons to complete cross-scale energy transfer. These observations, consistent with numerical simulations in the occurrence of phase-bunched ion and electron distributions, also highlight the importance of anomalous resonance, a nonlinear modification of the classical cyclotron resonance, in the cross-scale wave coupling and energy transfer processes.

physics.space-ph↗
arXiv2024

Identification of coupled Landau and anomalous resonances in space plasmas

Wave-particle resonance, a ubiquitous process in the plasma universe, occurs when resonant particles observe a constant wave phase to enable sustained energy transfer. Here, we present spacecraft observations of simultaneous Landau and anomalous resonances between oblique whistler waves and the same group of protons, which are evidenced, respectively, by phase-space rings in parallel-velocity spectra and phase-bunched distributions in gyro-phase spectra. Our results indicate the coupling between Landau and anomalous resonances via the overlapping of the resonance islands.

physics.space-ph↗