Searcharxiv⌕ Search

arXiv subjects

Wenjun Sun

Publications and source records attributed to Wenjun Sun.

13 recordsLinked to original sources
arXiv2026

Benchmarking Patent Drafting from Inventor-Style Disclosures

While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of real-world patent drafting: generating a complete and legally coherent patent application directly from early-stage invention materials. Prior work predominantly assumes later-stage, highly structured, or already legalistic inputs. However, real patenting workflows begin with informal, de-legalized disclosures authored by inventors. To bridge the gap, we introduce Dis2Pat, a disclosure-to-patent dataset that reflects realistic patenting workflows by requiring the generation of complete patent applications directly from inventor-style, de-legalized disclosures. Given the inherent difficulty of long-form, legally constrained patent drafting and the strong privacy requirements, we further propose a strong baseline named Patent-MAF. It is a multi-agent framework for locally deployable patent drafting. Benchmark results reveal that current LLMs exhibit limitations in patent drafting, while Patent-MAF provides a strong baseline that consistently outperforms evaluated open-source models and remains competitive with large closed-source models.

cs.CL↗
arXiv2026

When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation

Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.

cs.CL↗
arXiv2026

Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot

The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training data and reliable evaluation benchmarks. Collecting data in the physical world poses prohibitive costs and scalability challenges, and prevailing simulation benchmarks frequently suffer from fragmentation, narrow scope, or insufficient fidelity to enable effective sim-to-real transfer. To address these challenges, we introduce Genie Sim 3.0, a unified simulation platform for robotic manipulation. We present Genie Sim Generator, a large language model (LLM)-powered tool that constructs high-fidelity scenes from natural language instructions. Its principal strength resides in rapid and multi-dimensional generalization, facilitating the synthesis of diverse environments to support scalable data collection and robust policy evaluation. We introduce the first benchmark that pioneers the application of LLM for automated evaluation. It leverages LLM to mass-generate evaluation scenarios and employs Vision-Language Model (VLM) to establish an automated assessment pipeline. We also release an open-source dataset comprising more than 10,000 hours of synthetic data across over 200 tasks. Through systematic experimentation, we validate the robust zero-shot sim-to-real transfer capability of our open-source dataset, demonstrating that synthetic data can server as an effective substitute for real-world data under controlled conditions for scalable policy training. For code and dataset details, please refer to: https://github.com/AgibotTech/genie_sim.

cs.RO↗
arXiv2025

Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure traceability by embedding imperceptible watermarks into training images, which remain detectable in outputs even after fine-tuning. However, current methods lack a unified evaluation framework. To address this, this paper establishes a general threat model and introduces a comprehensive evaluation framework encompassing Universality, Transmissibility, and Robustness. Experiments show that existing methods perform well in universality and transmissibility, and exhibit some robustness against common image processing operations, yet still fall short under real-world threat scenarios. To reveal these vulnerabilities, the paper further proposes a practical watermark removal method that fully eliminates dataset watermarks without affecting fine-tuning, highlighting a key challenge for future research.

cs.CV↗
arXiv2025

Reasoning for Hierarchical Text Classification: The Case of Patents

Hierarchical text classification (HTC) assigns documents to multiple levels of a pre-defined taxonomy. Automated patent subject classification represents one of the hardest HTC scenarios because of domain knowledge difficulty and a huge number of labels. Prior approaches only output a flat label set, which offers little insight into the reason behind predictions. Therefore, we propose Reasoning for Hierarchical Classification (RHC), a novel framework that reformulates HTC as a step-by-step reasoning task to sequentially deduce hierarchical labels. RHC trains large language models (LLMs) in two stages: a cold-start stage that aligns outputs with chain-of-thought (CoT) reasoning format and a reinforcement learning (RL) stage to enhance multi-step reasoning ability. RHC demonstrates four advantages in our experiments. (1) Effectiveness: RHC surpasses previous baselines and outperforms the supervised fine-tuning counterparts by approximately 3% in accuracy and macro F1. (2) Explainability: RHC produces natural-language justifications before prediction to facilitate human inspection. (3) Scalability: RHC scales favorably with model size with larger gains compared to standard fine-tuning. (4) Applicability: Beyond patents, we further demonstrate that RHC achieves state-of-the-art performance on other widely used HTC benchmarks, which highlights its broad applicability.

cs.CL↗
arXiv2024

Randomized Radial Basis Function Neural Network for Solving Multiscale Elliptic Equations

To overcome these obstacles and improve computational accuracy and efficiency, this paper presents the Randomized Radial Basis Function Neural Network (RRNN), an innovative approach explicitly crafted for solving multiscale elliptic equations. The RRNN method commences by decomposing the computational domain into non-overlapping subdomains. Within each subdomain, the solution to the localized subproblem is approximated by a randomized radial basis function neural network with a Gaussian kernel. This network is distinguished by the random assignment of width and center coefficients for its activation functions, thereby rendering the training process focused solely on determining the weight coefficients of the output layer. For each subproblem, similar to the Petrov-Galerkin finite element method, a linear system will be formulated on the foundation of a weak formulation. Subsequently, a selection of collocation points is stochastically sampled at the boundaries of the subdomain, ensuring satisfying $C^0$ and $C^1$ continuity and boundary conditions to couple these localized solutions. The network is ultimately trained using the least squares method to ascertain the output layer weights. To validate the RRNN method's effectiveness, an extensive array of numerical experiments has been executed and the results demonstrate that the proposed method can improve the accuracy and efficiency well.

math.NA↗
arXiv2024

Macroscopic auxiliary asymptotic preserving neural networks for the linear radiative transfer equations

We develop a Macroscopic Auxiliary Asymptotic-Preserving Neural Network (MA-APNN) method to solve the time-dependent linear radiative transfer equations (LRTEs), which have a multi-scale nature and high dimensionality. To achieve this, we utilize the Physics-Informed Neural Networks (PINNs) framework and design a new adaptive exponentially weighted Asymptotic-Preserving (AP) loss function, which incorporates the macroscopic auxiliary equation that is derived from the original transfer equation directly and explicitly contains the information of the diffusion limit equation. Thus, as the scale parameter tends to zero, the loss function gradually transitions from the transport state to the diffusion limit state. In addition, the initial data, boundary conditions, and conservation laws serve as the regularization terms for the loss. We present several numerical examples to demonstrate the effectiveness of MA-APNNs.

math.NA↗
arXiv2023

Spatial second-order positive and asymptotic preserving filtered $P_N$ schemes for nonlinear radiative transfer equations

A spatial second-order scheme for the nonlinear radiative transfer equations is introduced in this paper. The discretization scheme is based on the filtered spherical harmonics ($FP_N$) method for the angular variable and the unified gas kinetic scheme (UGKS) framework for the spatial and temporal variables respectively. In order to keep the scheme positive and second-order accuracy, firstly, we use the implicit Monte Carlo linearization method [6] in the construction of the UGKS numerical boundary fluxes. Then, by carefully analyzing the constructed second-order fluxes involved in the macro-micro decomposition, which is induced by the $FP_N$ angular discretization, we establish the sufficient conditions that guarantee the positivity of the radiative energy density and material temperature. Finally, we employ linear scaling limiters for the angular variable in the $P_N$ reconstruction and for the spatial variable in the piecewise linear slopes reconstruction respectively, which are shown to be realizable and reasonable to enforce the sufficient conditions holding. Thus, the desired scheme, called the $PPFP_N$-based UGKS, is obtained. Furthermore, in the regime $\epsilon\ll 1$ and the regime $\epsilon=O(1)$, a simplified spatial second-order scheme, called the $PPFP_N$-based SUGKS, is presented, which possesses all the properties of the non-simplified one. Inheriting the merit of UGKS, the proposed schemes are asymptotic preserving. By employing the $FP_N$ method for the angular variable, the proposed schemes are almost free of ray effects. To our best knowledge, this is the first time that spatial second-order, positive, asymptotic preserving and almost free of ray effects schemes are constructed for the nonlinear radiative transfer equations without operator splitting. Various numerical experiments are included to validate the properties of the proposed schemes.

math.NA↗
arXiv2022

A model-data asymptotic-preserving neural network method based on micro-macro decomposition for gray radiative transfer equations

We propose a model-data asymptotic-preserving neural network(MD-APNN) method to solve the nonlinear gray radiative transfer equations(GRTEs). The system is challenging to be simulated with both the traditional numerical schemes and the vanilla physics-informed neural networks(PINNs) due to the multiscale characteristics. Under the framework of PINNs, we employ a micro-macro decomposition technique to construct a new asymptotic-preserving(AP) loss function, which includes the residual of the governing equations in the micro-macro coupled form, the initial and boundary conditions with additional diffusion limit information, the conservation laws, and a few labeled data. A convergence analysis is performed for the proposed method, and a number of numerical examples are presented to illustrate the efficiency of MD-APNNs, and particularly, the importance of the AP property in the neural networks for the diffusion dominating problems. The numerical results indicate that MD-APNNs lead to a better performance than APNNs or pure data-driven networks in the simulation of the nonlinear non-stationary GRTEs.

math.NA↗
arXiv2021

High-order gas-kinetic scheme for radiation hydrodynamics in equilibrium-diffusion limit

In this paper, a high-order gas-kinetic scheme is developed for the equation of radiation hydrodynamics in equilibrium-diffusion limit which describes the interaction between matter and radiation. To recover RHE, the Bhatnagar-Gross-Krook (BGK) model with modified equilibrium state is considered. In the equilibrium-diffusion limit, the time scales of radiation diffusion and hydrodynamic part are different, and it will make the time step very small for the fully explicit scheme. An implicit-explicit (IMEX) scheme is applied, in which the hydrodynamic part is treated explicitly and the radiation diffusion is treated implicitly. For the hydrodynamics part, a time dependent gas distribution function can be constructed by the integral solution of modified BGK equation, and the time dependent numerical fluxes can be obtained by taking moments of gas distribution function. For the radiation diffusion term, the nonlinear generalized minimal residual (GMRES) method is used. To achieve the temporal accuracy, a two-stage method is developed, which is an extension of two-stage method for hyperbolic conservation law. For the spatial accuracy, the multidimensional weighted essential non-oscillation (WENO) scheme is used for the spatial reconstruction. A variety of numerical tests are provided for the performance of current scheme, including the order of accuracy and robustness.

math.NA↗
arXiv2020

High order asymptotic preserving discontinuous Galerkin methods for gray radiative transfer equations

In this paper, we will develop a class of high order asymptotic preserving (AP) discontinuous Galerkin (DG) methods for nonlinear time-dependent gray radiative transfer equations (GRTEs). Inspired by the work \cite{Peng2020stability}, in which stability enhanced high order AP DG methods are proposed for linear transport equations, we propose to pernalize the nonlinear GRTEs under the micro-macro decomposition framework by adding a weighted linear diffusive term. In the diffusive limit, a hyperbolic, namely $\Delta t=\mathcal{O}(h)$ where $\Delta t$ and $h$ are the time step and mesh size respectively, instead of parabolic $\Delta t=\mathcal{O}(h^2)$ time step restriction is obtained, which is also free from the photon mean free path. The main new ingredient is that we further employ a Picard iteration with a predictor-corrector procedure, to decouple the resulting global nonlinear system to a linear system with local nonlinear algebraic equations from an outer iterative loop. Our scheme is shown to be asymptotic preserving and asymptotically accurate. Numerical tests for one and two spatial dimensional problems are performed to demonstrate that our scheme is of high order, effective and efficient.

math.NA↗
arXiv2019

Unified gas-kinetic simulation for the system of multiscale radiation hydrodynamics

This paper aims at the simulation of multiple scale physics in the system of radiation hydrodynamics. The system couples the fluid dynamic evolution equations with the radiative heat transfer. The coupled system is solved by the gas-kinetic scheme (GKS) for the compressible viscous and heat conducting flow and the unified gas-kinetic scheme (UGKS) for the non-equilibrium radiative transfer, together with the momentum and energy exchange between these two phases. For the radiative transfer, due to the possible large variation of fluid opacity in different regions, the transport of photons in the flow system is simulated by the multiscale UGKS, which is capable of naturally capturing the transport process from the free streaming to the diffusive propagation.Since both GKS and UGKS are finite volume methods,all unknowns are defined inside each control volume and are discretized consistently for the hydrodynamic and radiative variables. For the coupled system, the scheme has the asymptotical preserving (AP) property, such as recovering the equilibrium diffusion limit for the radiation hydrodynamic equations in the optically thick region, where the cell size is not limited by photon's mean free path. A few test cases, such as radiative shock wave problems, are used to validate the current approach.

physics.comp-ph↗