arXiv subjects

Jinze Wu

Publications and source records attributed to Jinze Wu.

18 recordsLinked to original sources

arXiv2026

Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing

Knowledge Tracing (KT) aims to assess students' dynamic knowledge states from their learning histories. While most existing KT methods focus on single-domain learning with notable success, real-world learning scenarios often involve multiple domains simultaneously, introducing two critical factors: 1) Cognitive load, arising from managing learning across domains in both temporal and knowledge dimensions. 2) Knowledge transfer, where knowledge states in one domain influence related states both within and across domains. In this paper, we focus on exploring these factors to improve students' knowledge state assessment in multi-domain learning scenarios and propose a novel method incorporating cognitive Load and knowledge Transfer for Multi-domain Knowledge Tracing (LT-MKT). Specifically, to bridge isolated domains, LT-MKT first integrates textual information from questions and their associated concepts to construct a Multi-domain Hierarchical Graph, leveraging the advanced representational capabilities of large language models (LLMs). Then, cross-domain features in both the temporal and knowledge dimensions are explicitly modeled to capture the effects of cognitive load. Additionally, a knowledge transfer module is designed to model the propagation of knowledge states within and across domains. By jointly modeling these factors, LT-MKT enables more accurate prediction of students' future performance. Finally, extensive experiments on real-world datasets demonstrate that our method achieves state-of-the-art performance.

cs.AI↗

arXiv2026

XDen-1K: A Density Field Dataset of Real-World Objects

A deep understanding of the physical world is essential for robotic manipulation and physically realistic simulation. While current methods, including VLM-based and other learning-based approaches, have shown promise in physical property inference, their evaluation is often hindered by the lack of physically grounded reference data. To address this gap, we introduce XDen-1K, the first large-scale multimodal dataset that provides physically grounded density field for real-world objects. XDen-1K comprises 1,000 real-world objects spanning 137 categories, with comprehensive data for each object, including a high-resolution, carefully curated 3D geometric model with part-level annotations and paired real-world biplanar X-ray scans. In addition, XDen-1K includes high-fidelity volumetric density field reconstructed from sparse biplanar X-ray views via a novel optimization framework. XDen-1K also provides a benchmark for density estimation and enables X-ray-conditioned volumetric segmentation. Experiments further demonstrate that the center-of-mass prior derived by XDen-1K can improve robotic manipulation performance. By providing real-world X-ray scans and physics-consistent density field, XDen-1K establishes a foundation for advancing physical property inference and embodied AI.

cs.CV↗

arXiv2025

Learning Natural and Robust Hexapod Locomotion over Complex Terrains via Motion Priors based on Deep Reinforcement Learning

Multi-legged robots offer enhanced stability to navigate complex terrains with their multiple legs interacting with the environment. However, how to effectively coordinate the multiple legs in a larger action exploration space to generate natural and robust movements is a key issue. In this paper, we introduce a motion prior-based approach, successfully applying deep reinforcement learning algorithms to a real hexapod robot. We generate a dataset of optimized motion priors, and train an adversarial discriminator based on the priors to guide the hexapod robot to learn natural gaits. The learned policy is then successfully transferred to a real hexapod robot, and demonstrate natural gait patterns and remarkable robustness without visual information in complex terrains. This is the first time that a reinforcement learning controller has been used to achieve complex terrain walking on a real hexapod robot.

cs.RO↗

arXiv2025

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities. In this paper, we propose \textbf{CogMath}, which comprehensively assesses LLMs' mathematical abilities through the lens of human cognition. Specifically, inspired by psychological theories, CogMath formalizes human reasoning process into 3 stages: \emph{problem comprehension}, \emph{problem solving}, and \emph{solution summarization}. Within these stages, we investigate perspectives such as numerical calculation, knowledge, and counterfactuals, and design a total of 9 fine-grained evaluation dimensions. In each dimension, we develop an ``\emph{Inquiry}-\emph{Judge}-\emph{Reference}'' multi-agent system to generate inquiries that assess LLMs' mastery from this dimension. An LLM is considered to truly master a problem only when excelling in all inquiries from the 9 dimensions. By applying CogMath on three benchmarks, we reveal that the mathematical capabilities of 7 mainstream LLMs are overestimated by 30\%-40\%. Moreover, we locate their strengths and weaknesses across specific stages/dimensions, offering in-depth insights to further enhance their reasoning abilities.

cs.AI↗

arXiv2025

From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation

Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation methods focus primarily on textual quality, but they often overlook educational objectives. Moreover, these methods address only single-dimensional, simple question generation, failing to meet complex, multifaceted educational requirements. To address these challenges, we constructed and annotated EduMath, a dataset of 16k mathematical questions with multi-dimensional educational objectives. Based on this dataset, we developed EQGEVAL, which incorporates three evaluation dimensions and is designed to assess the ability of models to generate educational questions. Drawing inspiration from teachers' problem design processes, we propose the Educational Question Planning with self-Reflection (EQPR) method for educational mathematical question generation, following a "plan-evaluate-optimize" approach. Specifically, by combining planning algorithm based on Monte Carlo Tree Search with the generative capabilities of Large Language Models, we continuously optimize questions through iterative feedback. This self-optimization mechanism ensures that the generated questions both fit the educational context and strategically achieve specific basic educational objectives. Through extensive experiments based on EQGEVAL, we have demonstrated that EQPR achieves significant improvements in generating questions that meet multi-dimensional educational objectives.

cs.CL↗

arXiv2024

End-to-End Graph Flattening Method for Large Language Models

In recent years, the breakthrough of Large Language Models (LLMs) offers new ideas for achieving universal methods on graph data. The common practice of converting graphs into natural language for LLMs, which refers to graph flattening, exhibits good generalizability and interpretability. However, the poor organization of the textual format results in poor performance in long-distance scenario understanding. Inspired by human cognitive reasoning habits, we propose a novel method for graph flattening to fit LLMs, termed as End-to-End DAG-Path prompting (EEDP). Experiments on real-world datasets show that EEDP enhances the reasoning performance of LLMs in long-distance scenarios while maintaining excellent performance in short-distance scenarios, demonstrating good robustness in the face of distance variations.

cs.CL↗

arXiv2024

Gapless superconductivity in the low-frequency electrodynamic response of two-dimensional granular In/InO$_x$ composites

We measured the full complex ac conductance of two-dimensional granular In/InO$_x$ composites using the mutual inductance technique to explore the transition from a "failed-superconductor-turned anomalous metal" to a robust superconductor. In this system, room-temperature annealing was adopted to tune the InO$_x$-mediated coupling between In grains, allowing for the observation of both a "true" superconductor-to-insulator transition and the emergence of an intervening anomalous metallic state. In this paper, we show that further annealing increases the inter-grain coupling, which eliminates the anomalous metallic phase, but at the same time prevent the emergence of strong Bose-dominated insulating phase. The complex ac conductance revealed a $T\to0$ saturating dissipative response in a finite magnetic field, coexisting with a robust superfluid density. The anomalous power-law spectra for the dissipative response appear to indicate quantum critical behavior proximate to a quantum superconductor to anomalous-metal transition as probed in the kilo-Hertz range, and point to signatures of gapless superconductivity in our granular superconducting system.

cond-mat.supr-con↗

arXiv2024

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process

Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning. However, existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning. In this paper, inspired by dual-process theory, we propose a Dual-Reasoning Geometry Solver (DualGeoSolver) to simulate the dual-reasoning process of humans for GPS. Specifically, we construct two systems in DualGeoSolver, namely Knowledge System and Inference System. Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System. Inference System conducts an explicit reasoning process, which specifies the goal in each reasoning step and applies the knowledge to generate program tokens for resolving it. The two systems carry out the above process iteratively, which behaves more in line with human cognition. We conduct extensive experiments on two benchmark datasets, GeoQA and GeoQA+. The results demonstrate the superiority of DualGeoSolver in both solving accuracy and robustness from explicitly modeling human reasoning process and knowledge application.

cs.AI↗

arXiv2024

Unified Uncertainty Estimation for Cognitive Diagnosis Models

Cognitive diagnosis models have been widely used in different areas, especially intelligent education, to measure users' proficiency levels on knowledge concepts, based on which users can get personalized instructions. As the measurement is not always reliable due to the weak links of the models and data, the uncertainty of measurement also offers important information for decisions. However, the research on the uncertainty estimation lags behind that on advanced model structures for cognitive diagnosis. Existing approaches have limited efficiency and leave an academic blank for sophisticated models which have interaction function parameters (e.g., deep learning-based models). To address these problems, we propose a unified uncertainty estimation approach for a wide range of cognitive diagnosis models. Specifically, based on the idea of estimating the posterior distributions of cognitive diagnosis model parameters, we first provide a unified objective function for mini-batch based optimization that can be more efficiently applied to a wide range of models and large datasets. Then, we modify the reparameterization approach in order to adapt to parameters defined on different domains. Furthermore, we decompose the uncertainty of diagnostic parameters into data aspect and model aspect, which better explains the source of uncertainty. Extensive experiments demonstrate that our method is effective and can provide useful insights into the uncertainty of cognitive diagnosis.

cs.CY↗

arXiv2024

Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits

Multi-legged robots offer enhanced stability in complex terrains, yet autonomously learning natural and robust motions in such environments remains challenging. Drawing inspiration from animals' progressive learning patterns, from simple to complex tasks, we introduce a universal two-stage learning framework with two-step reward setting based on self-acquired experience, which efficiently enables legged robots to incrementally learn natural and robust movements. In the first stage, robots learn through gait-related rewards to track velocity on flat terrain, acquiring natural, robust movements and generating effective motion experience data. In the second stage, mirroring animal learning from existing experiences, robots learn to navigate challenging terrains with natural and robust movements using adversarial imitation learning. To demonstrate our method's efficacy, we trained both quadruped robots and a hexapod robot, and the policy were successfully transferred to a physical quadruped robot GO1, which exhibited natural gait patterns and remarkable robustness in various terrains.

cs.RO↗

arXiv2023

Distributed Finite-Time Cooperative Localization for Three-Dimensional Sensor Networks

This paper addresses the distributed localization problem for a network of sensors placed in a three-dimensional space, in which sensors are able to perform range measurements, i.e., measure the relative distance between them, and exchange information on a network structure. First, we derive a necessary and sufficient condition for node localizability using barycentric coordinates. Then, building on this theoretical result, we design a distributed localizability verification algorithm, in which we propose and employ a novel distributed finite-time algorithm for sum consensus. Finally, we develop a distributed localization algorithm based on conjugate gradient method, and we derive a theoretical guarantee on its performance, which ensures finite-time convergence to the exact position for all localizable nodes. The efficiency of our algorithm compared to the existing ones from the state-of-the-art literature is further demonstrated through numerical simulations.

eess.SY↗

arXiv2023

Learning Multiple Gaits within Latent Space for Quadruped Robots

Learning multiple gaits is non-trivial for legged robots, especially when encountering different terrains and velocity commands. In this work, we present an end-to-end training framework for learning multiple gaits for quadruped robots, tailored to the needs of robust locomotion, agile locomotion, and user's commands. A latent space is constructed concurrently by a gait encoder and a gait generator, which helps the agent to reuse multiple gait skills to achieve adaptive gait behaviors. To learn natural behaviors for multiple gaits, we design gait-dependent rewards that are constructed explicitly from gait parameters and implicitly from conditional adversarial motion priors (CAMP). We demonstrate such multiple gaits control on a quadruped robot Go1 with only proprioceptive sensors.

cs.RO↗

arXiv2023

A Novel Approach for Auto-Formulation of Optimization Problems

In the Natural Language for Optimization (NL4Opt) NeurIPS 2022 competition, competitors focus on improving the accessibility and usability of optimization solvers, with the aim of subtask 1: recognizing the semantic entities that correspond to the components of the optimization problem; subtask 2: generating formulations for the optimization problem. In this paper, we present the solution of our team. First, we treat subtask 1 as a named entity recognition (NER) problem with the solution pipeline including pre-processing methods, adversarial training, post-processing methods and ensemble learning. Besides, we treat subtask 2 as a generation problem with the solution pipeline including specially designed prompts, adversarial training, post-processing methods and ensemble learning. Our proposed methods have achieved the F1-score of 0.931 in subtask 1 and the accuracy of 0.867 in subtask 2, which won the fourth and third places respectively in this competition. Our code is available at https://github.com/bigdata-ustc/nl4opt.

cs.CL↗

arXiv2022

Cooperative Guidance Strategy for Active Defense Spacecraft with Imperfect Information via Deep Reinforcement Learning

In this paper, an adaptive cooperative guidance strategy for the active protection of a target spacecraft trying to evade an interceptor was developed. The target spacecraft performs evasive maneuvers, launching an active defense vehicle to divert the interceptor. Instead of classical strategies, which are based on optimal control or differential game theory, the problem was solved by using the deep reinforcement learning method, and imperfect information was assumed for the interceptor maneuverability. To address the sparse reward problem, a universal reward design method and an increasingly difficult training approach were presented utilizing the shaping technique. Guidance law, reward function, and training approach were demonstrated through the learning process and Monte Carlo simulations. The application of the non-sparse reward function and increasingly difficult training approach accelerated the model convergence, alleviating the overfitting problem. Considering a standard optimal guidance law as a benchmark, the effectiveness, and the advantages, that guarantee the target spacecraft's escape and win rates in a multi-agent game, of the proposed guidance strategy were validated by the simulation results. The trained agent's adaptiveness to the interceptor maneuverability was superior to the optimal guidance law. Moreover, compared to the standard optimal guidance law, the proposed guidance strategy performed better with less prior knowledge.

eess.SY↗

arXiv2021

FedSiam: Towards Adaptive Federated Semi-Supervised Learning

Federated learning (FL) has emerged as an effective technique to co-training machine learning models without actually sharing data and leaking privacy. However, most existing FL methods focus on the supervised setting and ignore the utilization of unlabeled data. Although there are a few existing studies trying to incorporate unlabeled data into FL, they all fail to maintain performance guarantees or generalization ability in various real-world settings. In this paper, we focus on designing a general framework FedSiam to tackle different scenarios of federated semi-supervised learning, including four settings in the labels-at-client scenario and two setting in the labels-at-server scenario. FedSiam is built upon a siamese network into FL with a momentum update to handle the non-IID challenges introduced by unlabeled data. We further propose a new metric to measure the divergence of local model layers within the siamese network. Based on the divergence, FedSiam can automatically select layer-level parameters to be uploaded to the server in an adaptive manner. Experimental results on three datasets under two scenarios with different data distribution settings demonstrate that the proposed FedSiam framework outperforms state-of-the-art baselines.

cs.LG↗

arXiv2021

Imaging the transverse spin density of light via electromagnetically induced transparency

When a light beam is strongly laterally confined, its field vector spins in a plane not perpendicular to the propagation direction, leading to the presence of transverse spin angular momentum, which plays a crucial role in the field of chiral quantum optics. The existing techniques to measure the transverse spin density require complex setups and sophisticated time-consuming procedures. Here, we propose a scheme to measure the transverse spin density of an optical field in real time using a multi-level atomic medium. The susceptibility of the medium is spatially modulated by the transverse spin via electromagnetically induced transparency. The distribution of the transverse spin is then extracted by measuring the distributions of the Stokes parameters of another collimated probe field.

physics.optics↗

arXiv2019

Controllable spin-Hall and related effects of light in an atomic medium via coupling fields

We show the existence of spin-Hall effect of light (SHEL) in an atomic medium which is made anisotropic via electromagnetically induced transparency. The medium is made birefringent by applying an additional linearly polarized coupling light beam. The refractive index and the orientation of the optics axis are controlled by the coupling beam. We show that after transmitting the atomic medium, a linearly polarized probe light beam splits into its two spin components by opposite transverse shifts. With proper choice of parameters and atomic density of about $2.5\times10^{17}\,\mathrm{m}^{-3}$, the shifts are about the order of wavelength and can be larger than the wavelength by increasing the atomic density. We propose a novel measurement scheme based on a balanced homodyne detection (BHD). By properly choosing the polarization, phase, and transverse mode of the local oscillator of the BHD, one can independently measure (i) the SHEL shifts of the two spin components; (ii) the spatial and angular shifts; (iii) the transverse and longitudinal shifts. The measurement can reach the quantum limit of precision by detecting signals at the modulation frequency of the electro-optic modulator used to modulate the input probe beam. The precision is estimated to be at the nanometer level limited by the quantum noise.

physics.optics↗

arXiv2018

Observation of momentum-space chiral edge currents in room-temperature atoms

Chiral edge currents play an important role in characterizing topological matter. In atoms, they have been observed at such a low temperature that the atomic motion can be measured. Here we report the first experimental observation of chiral edge currents in atoms at room temperature. Staggered magnetic fluxes are induced by the spatial phase difference between two standing-wave light fields, which couple atoms to form a momentum-space zigzag superradiance lattice. The chiral edge currents have been measured by comparing the directional superradiant emissions of two timed Dicke states in the lattice. This work paves the way for quantum simulation of topological matter with hot atoms and facilitates the application of topological physics in real devices.

physics.optics↗