arXiv subjects

Yuan Cao

Publications and source records attributed to Yuan Cao.

At least 55 records · Page 3Linked to original sources

arXiv2026

UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a framework that shifts the learning focus from mimicking high-level trajectories to mastering interaction physics via ground-truth environmental feedback. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and significantly outweighs inverse inference. UI-Oceanus leverages this insight by converting low-cost autonomous exploration, which is verified directly by system execution, into high-density generative supervision to construct a robust internal world model. Experimental evaluations across a series of models demonstrate the decisive superiority of our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results confirm that grounding agents in forward predictive modeling offers a superior pathway to scalable GUI automation with robust cross-domain adaptability and compositional generalization.

cs.LG↗

arXiv2026

Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs

Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details, financial data, and medical records. As a result, there is a growing emphasis on developing privacy-preserving training algorithms for neural networks that maintain good performance while preserving privacy. In this paper, we investigate the generalization and privacy performances of the differentially private gradient descent (DP-GD) algorithm, which is a private variant of the gradient descent (GD) by incorporating additional noise into the gradients during each iteration. Moreover, we identify a concrete learning task where DP-GD can achieve superior generalization performance compared to GD in training two-layer Huberized ReLU convolutional neural networks (CNNs). Specifically, we demonstrate that, under mild conditions, a small signal-to-noise ratio can result in GD producing training models with poor test accuracy, whereas DP-GD can yield training models with good test accuracy and privacy guarantees if the signal-to-noise ratio is not too small. This indicates that DP-GD has the potential to enhance model performance while ensuring privacy protection in certain learning tasks. Numerical simulations are further conducted to support our theoretical results.

stat.ML↗

arXiv2026

From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection

Personality detection aims to measure an individual's corresponding personality traits through their social media posts. The advancements in Large Language Models (LLMs) offer novel perspectives for personality detection tasks. Existing approaches enhance personality trait analysis by leveraging LLMs to extract semantic information from textual posts as prompts, followed by training classifiers for categorization. However, accurately classifying personality traits remains challenging due to the inherent complexity of human personality and subtle inter-trait distinctions. Moreover, prompt-based methods often exhibit excessive dependency on expert-crafted knowledge without autonomous pattern-learning capacity. To address these limitations, we view personality detection as a ranking task rather than a classification and propose a corresponding reinforcement learning training paradigm. First, we employ supervised fine-tuning (SFT) to establish personality trait ranking capabilities while enforcing standardized output formats, creating a robust initialization. Subsequently, we introduce Group Relative Policy Optimization (GRPO) with a specialized ranking-based reward function. Unlike verification tasks with definitive solutions, personality assessment involves subjective interpretations and blurred boundaries between trait categories. Our reward function explicitly addresses this challenge by training LLMs to learn optimal answer rankings. Comprehensive experiments have demonstrated that our method achieves state-of-the-art performance across multiple personality detection benchmarks.

cs.CL↗

arXiv2026

A scalable near-visible integrated photon-pair source for satellite quantum science

Quantum state distribution over vast distances is essential for global-scale quantum networks and fundamental test of quantum physics at space scale. While satellite platforms have demonstrated thousand-kilometer entanglement distribution, quantum key distribution and quantum teleportation with ground, future constellations and deep-space missions demand photon sources that are robust, compact, and power-efficient. Integrated photonics offers a scalable solution, yet a critical spectral gap persists. Although telecom-band integrated photon-pair sources are well established, near-visible photons offer distinct advantages for satellite-to-ground links by mitigating diffraction loss and maximizing the collection efficiency of optical telescopes. Scalable integrated sources in this regime have remained elusive due to the fundamental challenge of achieving anomalous dispersion in materials transparent at visible wavelengths. Here we bridge this gap by demonstrating an integrated near-visible photon-pair source based on a wide-bandgap, ultralow-loss, silicon nitride (Si$_3$N$_4$) microresonator. By engineering the dispersion of higher-order waveguide modes, we overcome the intrinsic normal dispersion limit to achieve efficient phase matching. The device exhibits a spectral brightness of 4.87$\times$10$^7$ pairs/s/mW$^2$/GHz and a narrow photon linewidth of 357 MHz. We report high-purity heralded single-photon generation with a heralding rate up to 2.3 MHz and a second-order correlation function as low as 0.0041. Furthermore, we observe energy-time entanglement with 98.4% interference visibility, violating the CHSH limit even at flux exceeding 40.6 million pairs/s. Combined with the proven radiation hardness of Si$_3$N$_4$, this source constitutes a flight-ready hardware foundation for daylight quantum communications and protocols requiring on-orbit multiphoton interference.

quant-ph↗

arXiv2026

Forbidden second harmonics in centrosymmetric bilayer crystals

Optical spectroscopy based on second-order nonlinearity is a critical technique for characterizing two-dimensional (2D) crystals as well as bioimaging and quantum optics. It is generally believed that second-harmonic generation (SHG) in centrosymmetric crystals, such as graphene and other bilayer 2D crystals, is negligible without externally breaking the inversion symmetry. Here, we show that with a new homodyne detection technique, we can apparently circumvent this symmetry-imposed constraint and observe robust SHG in pristine centrosymmetric crystals, without any symmetry-breaking field. With its exceptional sensitivity, we resolve polarization-resolved SHG in bilayer hexagonal boron nitride (h-BN), bilayer 2H-WSe$_2$, and remarkably, Bernal-stacked bilayer graphene, allowing us to unambiguously identify the crystallographic orientation in these crystals via SHG for the first time. We also demonstrate that the new technique can be used to non-invasively detect uniaxial strain and optical geometric phase in these crystals. The observed SHG in our experiments is attributed to second-order nonlinearity in the quadrupole channel, which is controlled by the presence of the $C_2$ symmetry instead of the inversion symmetry. Our new technique expands the capability of nonlinear optical spectroscopy to encompass a large class of centrosymmetric materials that could never be measured before, and can be used for quantum sensing of moiré materials and twisted epitaxial films.

cond-mat.mes-hall↗

arXiv2026

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety

Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models through reasoning over detailed ``code-like'' safety rules, the effectiveness of this approach in open-source LLMs, which typically lack advanced reasoning capabilities, is understudied. In this work, we systematically evaluate the impact of explicitly specifying extensive safety codes versus demonstrating them through illustrative cases. We find that referencing explicit codes inconsistently improves harmlessness and systematically degrades helpfulness, whereas training on case-augmented simple codes yields more robust and generalized safety behaviors. By guiding LLMs with case-augmented reasoning instead of extensive code-like safety rules, we avoid rigid adherence to narrowly enumerated rules and enable broader adaptability. Building on these insights, we propose CADA, a case-augmented deliberative alignment method for LLMs utilizing reinforcement learning on self-generated safety reasoning chains. CADA effectively enhances harmlessness, improves robustness against attacks, and reduces over-refusal while preserving utility across diverse benchmarks, offering a practical alternative to rule-only DA for improving safety while maintaining helpfulness.

cs.AI↗

arXiv2025

From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents

While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has been largely overlooked. Our motivating study reveals that inefficient UI representation creates a critical performance bottleneck. However, UI representation optimization, formulated as the task of automatically generating programs that transform UI representations, faces two unique challenges. First, the lack of Boolean oracles, which traditional program synthesis uses to decisively validate semantic correctness, poses a fundamental challenge to co-optimization of token efficiency and completeness. Second, the need to process large, complex UI trees as input while generating long, compositional transformation programs, making the search space vast and error-prone. Toward addressing the preceding limitations, we present UIFormer, the first automated optimization framework that synthesizes UI transformation programs by conducting constraint-based optimization with structured decomposition of the complex synthesis task. First, UIFormer restricts the program space using a domain-specific language (DSL) that captures UI-specific operations. Second, UIFormer conducts LLM-based iterative refinement with correctness and efficiency rewards, providing guidance for achieving the efficiency-completeness co-optimization. UIFormer operates as a lightweight plugin that applies transformation programs for seamless integration with existing LLM agents, requiring minimal modifications to their core logic. Evaluations across three UI navigation benchmarks spanning Android and Web platforms with five LLMs demonstrate that UIFormer achieves 48.7% to 55.8% token reduction with minimal runtime overhead while maintaining or improving agent performance. Real-world industry deployment at WeChat further validates the practical impact of UIFormer.

cs.SE↗

arXiv2025

Towards Understanding Transformers in Learning Random Walks

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of transformers has not been well understood in theory. In this paper, we study the capability and interpretability of transformers in learning a family of classic statistical models, namely random walks on circles. We theoretically demonstrate that, after training with gradient descent, a one-layer transformer model can achieve optimal accuracy in predicting random walks. Importantly, our analysis reveals that the trained model is interpretable: the trained softmax attention serves as a token selector, focusing on the direct parent state; subsequently, the value matrix executes a one-step probability transition to predict the location of the next state based on this parent state. We also show that certain edge cases not covered by our theory are indeed failure cases, demonstrating that our theoretical conditions are tight. By investigating these success and failure cases, it is revealed that gradient descent with small initialization may fail or struggle to converge to a good solution in certain simple tasks even beyond random walks. Experiments are conducted to support our theoretical findings.

cs.LG↗

arXiv2025

Memory-Assisted Nonlocal Interferometer Towards Long-Baseline Telescopes

Quantum networks and remote quantum entanglement serve as vital future quantum communication resources with broad applicability. A key direction lies in extending the baseline of optical interferometers to enhance angular resolution in interferometric imaging. Here, by measuring a simulated thermal light field, we report the demonstration of a memory-assisted nonlocal interferometer achieving a fiber-link baseline up to 20 km while simultaneously showing its capability to compensate for a geometric delay equivalent to 1.5 km. This result demonstrates potential for enhancing the angular resolution of interferometric imaging in the optical band with delocalized single-photon entanglement, and paves the way for future application of quantum memories in astronomical observation.

quant-ph↗

arXiv2025

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical work primarily analyzes its full-batch version, which differs fundamentally from the stochastic variant used in practice. Unlike SGD, stochastic Adam does not converge to its full-batch counterpart even with infinitesimal learning rates. We present the first theoretical characterization of how batch size affects Adam's generalization, analyzing two-layer over-parameterized CNNs on image data. Our results reveal that while both Adam and AdamW with proper weight decay $λ$ converge to poor test error solutions, their mini-batch variants can achieve near-zero test error. We further prove Adam has a strictly smaller effective weight decay bound than AdamW, theoretically explaining why Adam requires more sensitive $λ$ tuning. Extensive experiments validate our findings, demonstrating the critical role of batch size and weight decay in Adam's generalization performance.

cs.LG↗

arXiv2025

AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?

Large language models (LLMs) have demonstrated remarkable capability in function-level code generation tasks. Unlike isolated functions, real-world applications demand reasoning over the entire software system: developers must orchestrate how different components interact, maintain consistency across states over time, and ensure the application behaves correctly within the lifecycle and framework constraints. Yet, no existing benchmark adequately evaluates whether LLMs can bridge this gap and construct entire software systems from scratch. To address this gap, we propose APPFORGE, a benchmark consisting of 101 software development problems drawn from real-world Android apps. Given a natural language specification detailing the app functionality, a language model is tasked with implementing the functionality into an Android app from scratch. Developing an Android app from scratch requires understanding and coordinating app states, lifecycle management, and asynchronous operations, calling for LLMs to generate context-aware, robust, and maintainable code. To construct APPFORGE, we design a multi-agent system to automatically summarize the main functionalities from app documents and navigate the app to synthesize test cases validating the functional correctness of app implementation. Following rigorous manual verification by Android development experts, APPFORGE incorporates the test cases within an automated evaluation framework that enables reproducible assessment without human intervention, making it easily adoptable for future research. Our evaluation on 12 flagship LLMs show that all evaluated models achieve low effectiveness, with the best-performing model (GPT-5) developing only 18.8% functionally correct applications, highlighting fundamental limitations in current models' ability to handle complex, multi-component software engineering challenges.

cs.SE↗

arXiv2025

Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization

Portfolio optimization aims at constructing a realistic portfolio with significant out-of-sample performance, which is typically measured by the out-of-sample Sharpe ratio. However, due to in-sample optimism, it is inappropriate to use the in-sample estimated covariance to evaluate the out-of-sample Sharpe, especially in the high dimensional settings. In this paper, we propose a novel method to estimate the out-of-sample Sharpe ratio using only in-sample data, based on random matrix theory. Furthermore, portfolio managers can use the estimated out-of-sample Sharpe as a criterion to decide the best tuning for constructing their portfolios. Specifically, we consider the classical framework of Markowits mean-variance portfolio optimization {under} high dimensional regime of $p/n \to c \in (0,\infty)$, where $p$ is the portfolio dimension and $n$ is the number of samples or time points. We propose to correct the sample covariance by a regularization matrix and provide a consistent estimator of its Sharpe ratio. The new estimator works well under either of the following conditions: (1) bounded covariance spectrum, (2) arbitrary number of diverging spikes when $c < 1$, and (3) fixed number of diverging spikes with weak requirement on their diverging speed when $c \ge 1$. We can also extend the results to construct global minimum variance portfolio and correct out-of-sample efficient frontier. We demonstrate the effectiveness of our approach through comprehensive simulations and real data experiments. Our results highlight the potential of this methodology as a useful tool for portfolio optimization in high dimensional settings.

math.ST↗

arXiv2025

Transformers Simulate MLE for Sequence Generation in Bayesian Networks

Transformers have achieved significant success in various fields, notably excelling in tasks involving sequential data like natural language processing. Despite these achievements, the theoretical understanding of transformers' capabilities remains limited. In this paper, we investigate the theoretical capabilities of transformers to autoregressively generate sequences in Bayesian networks based on in-context maximum likelihood estimation (MLE). Specifically, we consider a setting where a context is formed by a set of independent sequences generated according to a Bayesian network. We demonstrate that there exists a simple transformer model that can (i) estimate the conditional probabilities of the Bayesian network according to the context, and (ii) autoregressively generate a new sample according to the Bayesian network with estimated conditional probabilities. We further demonstrate in extensive experiments that such a transformer does not only exist in theory, but can also be effectively obtained through training. Our analysis highlights the potential of transformers to learn complex probabilistic models and contributes to a better understanding of large language models as a powerful class of sequence generators.

stat.ML↗

arXiv2025

Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation

Session-based Recommendation (SBR) aims to predict the next item a user will likely engage with, using their interaction sequence within an anonymous session. Existing SBR models often focus only on single-session information, ignoring inter-session relationships and valuable cross-session insights. Some methods try to include inter-session data but struggle with noise and irrelevant information, reducing performance. Additionally, most models rely on item ID co-occurrence and overlook rich semantic details, limiting their ability to capture fine-grained item features. To address these challenges, we propose a novel hierarchical intent-guided optimization approach with pluggable LLM-driven semantic learning for session-based recommendations, called HIPHOP. First, we introduce a pluggable embedding module based on large language models (LLMs) to generate high-quality semantic representations, enhancing item embeddings. Second, HIPHOP utilizes graph neural networks (GNNs) to model item transition relationships and incorporates a dynamic multi-intent capturing module to address users' diverse interests within a session. Additionally, we design a hierarchical inter-session similarity learning module, guided by user intent, to capture global and local session relationships, effectively exploring users' long-term and short-term interests. To mitigate noise, an intent-guided denoising strategy is applied during inter-session learning. Finally, we enhance the model's discriminative capability by using contrastive learning to optimize session representations. Experiments on multiple datasets show that HIPHOP significantly outperforms existing methods, demonstrating its effectiveness in improving recommendation quality. Our code is available: https://github.com/hjx159/HIPHOP.

cs.IR↗

arXiv2025

Leveraging Multimodal Data and Side Users for Diffusion Cross-Domain Recommendation

Cross-domain recommendation (CDR) aims to address the persistent cold-start problem in Recommender Systems. Current CDR research concentrates on transferring cold-start users' information from the auxiliary domain to the target domain. However, these systems face two main issues: the underutilization of multimodal data, which hinders effective cross-domain alignment, and the neglect of side users who interact solely within the target domain, leading to inadequate learning of the target domain's vector space distribution. To address these issues, we propose a model leveraging Multimodal data and Side users for diffusion Cross-domain recommendation (MuSiC). We first employ a multimodal large language model to extract item multimodal features and leverage a large language model to uncover user features using prompt learning without fine-tuning. Secondly, we propose the cross-domain diffusion module to learn the generation of feature vectors in the target domain. This approach involves learning feature distribution from side users and understanding the patterns in cross-domain transformation through overlapping users. Subsequently, the trained diffusion module is used to generate feature vectors for cold-start users in the target domain, enabling the completion of cross-domain recommendation tasks. Finally, our experimental evaluation of the Amazon dataset confirms that MuSiC achieves state-of-the-art performance, significantly outperforming all selected baselines. Our code is available: https://anonymous.4open.science/r/MuSiC-310A/.

cs.IR↗

arXiv2025

TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation

With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, trajectory similarity computation plays a critical role in a wide range of real-world applications. However, existing learning-based methods face three challenges: First, they ignore the semantic gap between GPS and grid features in trajectories, making it difficult to obtain meaningful trajectory embeddings. Second, the noise inherent in the trajectories, as well as the noise introduced during grid discretization, obscures the true motion patterns of the trajectories. Third, existing methods focus solely on point-wise and pair-wise losses, without utilizing the global ranking information obtained by sorting all trajectories according to their similarity to a given trajectory. To address the aforementioned challenges, we propose a novel trajectory similarity computation framework, named TrajDiff. Specifically, the semantic alignment module relies on cross-attention and an attention score mask mechanism with adaptive fusion, effectively eliminating semantic discrepancies between data at two scales and generating a unified representation. Additionally, the DDBM-based Noise-robust Pre-Training introduces the transfer patterns between any two trajectories into the model training process, enhancing the model's noise robustness. Finally, the overall ranking-aware regularization shifts the model's focus from a local to a global perspective, enabling it to capture the holistic ordering information among trajectories. Extensive experiments on three publicly available datasets show that TrajDiff consistently outperforms state-of-the-art baselines. In particular, it achieves an average HR@1 gain of 33.38% across all three evaluation metrics and datasets.

cs.LG↗

arXiv2025

Ultrabright Entanglement Based Quantum Key Distribution over a 404 km Optical Fiber

Entangled photons are crucial resources for quantum information processing. Here, we present an ultrabright polarization-entangled photon source based on a periodically poled lithium niobate waveguide designed for practical quantum communication networks. Using a 780 nm pump laser, the source achieves a pair generation rate of 2.4 $\times 10^{10}$ pairs/s/mW. Remarkably, the entangled photons are bright enough to be detected by a power meter, reaching a power of 17.9 nW under a pump power of 3.2 mW. We demonstrate the practicality of the source by conducting quantum key distribution experiments over long-distance fiber links. Wavelength-division multiplexing was employed to enhance the key generation, and nonlocal dispersion compensation was implemented to ensure precise timing coincidence measurements across a broad spectral range. By utilizing nine pairs of wavelength channels, the system achieved the applicable secure key rates of up to 440.80 bits/s over 200 km with a 62 dB loss and extended the maximum secure key generation distance to 404 km. These results demonstrate the potential of wavelength-multiplexed polarization-entangled photon sources for high-speed, long-distance quantum communication, positioning them as key components for future large-scale quantum networks.

quant-ph↗

arXiv2025

Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding

Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks, enabling efficient deployment on resource-constrained devices. However, existing pruning methods often rely on local heuristics or weight-based criteria that fail to capture global structural dependencies within the network, leading to suboptimal pruning decisions and degraded model performance. To address these limitations, we propose a novel structure-aware automatic channel pruning (SACP) framework that utilizes graph convolutional networks (GCNs) to model the network topology and learn the global importance of each channel. By encoding structural relationships within the network, our approach implements topology-aware pruning and this pruning is fully automated, reducing the need for human intervention. We restrict the pruning rate combinations to a specific space, where the number of combinations can be dynamically adjusted, and use a search-based approach to determine the optimal pruning rate combinations. Extensive experiments on benchmark datasets (CIFAR-10, ImageNet) with various models (ResNet, VGG16) demonstrate that SACP outperforms state-of-the-art pruning methods on compression efficiency and competitive on accuracy retention.

cs.AI↗