arXiv subjects

Yufei Zhang

Publications and source records attributed to Yufei Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research. Our codes are available at https://github.com/jinsong8/RecInter.

cs.CL↗

arXiv2025

OneRec Technical Report

Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from the AI community in recommendation scenarios. To address these issues, we propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $\times$ and have identified the scaling laws for recommendations within certain boundaries. Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework. Lastly, through infrastructure optimizations, we have achieved 23.7% and 28.8% Model FLOPs Utilization (MFU) on flagship GPUs during training and inference, respectively, aligning closely with the LLM community. This architecture significantly reduces communication and storage overhead, resulting in operating expense that is only 10.6% of traditional recommendation pipelines. Deployed in Kuaishou/Kuaishou Lite APP, it handles 25% of total queries per second, enhancing overall App Stay Time by 0.54% and 1.24%, respectively. Additionally, we have observed significant increases in metrics such as 7-day Lifetime, which is a crucial indicator of recommendation experience. We also provide practical lessons and insights derived from developing, optimizing, and maintaining a production-scale recommendation system with significant real-world impact.

cs.IR↗

arXiv2025

Convergence Rates of Time Discretization in Extended Mean Field Control

Piecewise constant control approximation provides a practical framework for designing numerical schemes of continuous-time control problems. We analyze the accuracy of such approximations for extended mean field control (MFC) problems, where the dynamics and costs depend on the joint distribution of states and controls. For linear-convex extended MFC problems, we show that the optimal control is $1/2$-Hölder continuous in time. Using this regularity, we prove that the optimal cost of the continuous-time problem can be approximated by piecewise constant controls with order $1/2$, while the optimal control itself can be approximated with order $1/4$. For general extended MFC problems, we further show that, under sufficient regularity of the value functions, the value functions converge with an improved first-order rate, matching the best-known rate for classical control problems without mean field interaction, and consistent with the numerical observations for MFC of Cucker-Smale models.

math.OC↗

arXiv2025

The Balmer spectrum of pseudo-coherent complexes over a discrete valuation ring

We study the derived category of pseudo-coherent complexes over a noetherian commutative ring, building on prior work by Matsui-Takahashi. Our main theorem is a computation of the Balmer spectrum of this category in the case of a discrete valuation ring. We prove that it coincides with the spectral space associated to a bounded distributive lattice of asymptotic equivalence classes of monotonic sequences of natural numbers. The proof of this theorem involves an extensive study of generation behaviour in the derived category of pseudo-coherent complexes. We find that different types of generation are related to different asymptotic boundedness conditions on the growth of torsion in homology. Consequently, we introduce certain distributive lattices of (equivalence classes of) monotonic sequences where the partial orders are defined by different notions of asymptotic boundedness. These lattices, and the spectral spaces corresponding to them via Stone duality, may be of independent interest. The complexity of these spectral spaces shows that, even in the simplest nontrivial case, the spectrum of pseudo-coherent complexes is vastly more complicated than the spectrum of perfect complexes. From a broader perspective, these results demonstrate that the spectrum of a rigid tensor-triangulated category can expand tremendously when we pass to a (non-rigid) tensor-triangulated category which contains it.

math.AC↗

arXiv2025

Mirror Descent for Stochastic Control Problems with Measure-valued Controls

This paper studies the convergence of the mirror descent algorithm for finite horizon stochastic control problems with measure-valued control processes. The control objective involves a convex regularisation function, denoted as $h$, with regularisation strength determined by the weight $τ\ge 0$. The setting covers regularised relaxed control problems. Under suitable conditions, we establish the relative smoothness and convexity of the control objective with respect to the Bregman divergence of $h$, and prove linear convergence of the algorithm for $τ=0$ and exponential convergence for $τ>0$. The results apply to common regularisers including relative entropy, $χ^2$-divergence, and entropic Wasserstein costs. This validates recent reinforcement learning heuristics that adding regularisation accelerates the convergence of gradient methods. The proof exploits careful regularity estimates of backward stochastic differential equations in the bounded mean oscillation norm.

math.OC↗

arXiv2025

Diffusion-based 3D Hand Motion Recovery with Intuitive Physics

While 3D hand reconstruction from monocular images has made significant progress, generating accurate and temporally coherent motion estimates from videos remains challenging, particularly during hand-object interactions. In this paper, we present a novel 3D hand motion recovery framework that enhances image-based reconstructions through a diffusion-based and physics-augmented motion refinement model. Our model captures the distribution of refined motion estimates conditioned on initial ones, generating improved sequences through an iterative denoising process. Instead of relying on scarce annotated video data, we train our model only using motion capture data without images. We identify valuable intuitive physics knowledge during hand-object interactions, including key motion states and their associated motion constraints. We effectively integrate these physical insights into our diffusion model to improve its performance. Extensive experiments demonstrate that our approach significantly improves various frame-wise reconstruction methods, achieving state-of-the-art (SOTA) performance on existing benchmarks.

cs.CV↗

arXiv2025

Conformal Phase Transition in Supersymmetric QCD

We construct a four-dimensional supersymmetric QCD in conformal window with a marginally relevant deformation which triggers the spontaneous breaking of (approximate) scale invariance and the subsequent confinement, generating a mass gap, at an energy scale hierarchically smaller than the Planck scale without fine-tuning. We analyze the finite temperature system and show that the phase transition associated with the breaking of conformal invariance is of the strong first order. When such a phase transition takes place at a temperature of the Universe around the electroweak scale, it generates a stochastic gravitational wave (GW) background probed by future space-based interferometers, while a conformal phase transition in a dark sector at $\mathcal{O}(1)$ GeV generates GWs to explain the reported pulsar timing array signal.

hep-ph↗

arXiv2025

FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding

Semantic querying in complex 3D scenes through free-form language presents a significant challenge. Existing 3D scene understanding methods use large-scale training data and CLIP to align text queries with 3D semantic features. However, their reliance on predefined vocabulary priors from training data hinders free-form semantic querying. Besides, recent advanced methods rely on LLMs for scene understanding but lack comprehensive 3D scene-level information and often overlook the potential inconsistencies in LLM-generated outputs. In our paper, we propose FreeQ-Graph, which enables Free-form Querying with a semantic consistent scene Graph for 3D scene understanding. The core idea is to encode free-form queries from a complete and accurate 3D scene graph without predefined vocabularies, and to align them with 3D consistent semantic labels, which accomplished through three key steps. We initiate by constructing a complete and accurate 3D scene graph that maps free-form objects and their relations through LLM and LVLM guidance, entirely free from training data or predefined priors. Most importantly, we align graph nodes with accurate semantic labels by leveraging 3D semantic aligned features from merged superpoints, enhancing 3D semantic consistency. To enable free-form semantic querying, we then design an LLM-based reasoning algorithm that combines scene-level and object-level information to intricate reasoning. We conducted extensive experiments on 3D semantic grounding, segmentation, and complex querying tasks, while also validating the accuracy of graph generation. Experiments on 6 datasets show that our model excels in both complex free-form semantic queries and intricate relational reasoning.

cs.CV↗

arXiv2025

Analytic Continual Test-Time Adaptation for Multi-Modality Corruption

Test-Time Adaptation (TTA) enables pre-trained models to bridge the gap between source and target datasets using unlabeled test data, addressing domain shifts caused by corruptions like weather changes, noise, or sensor malfunctions in test time. Multi-Modal Continual Test-Time Adaptation (MM-CTTA), as an extension of standard TTA, further allows models to handle multi-modal inputs and adapt to continuously evolving target domains. However, MM-CTTA faces critical challenges such as catastrophic forgetting and reliability bias, which are rarely addressed effectively under multi-modal corruption scenarios. In this paper, we propose a novel approach, Multi-modality Dynamic Analytic Adapter (MDAA), to tackle MM-CTTA tasks. MDAA introduces analytic learning,a closed-form training technique,through Analytic Classifiers (ACs) to mitigate catastrophic forgetting. Furthermore, we design the Dynamic Late Fusion Mechanism (DLFM) to dynamically select and integrate reliable information from different modalities. Extensive experiments show that MDAA achieves state-of-the-art performance across the proposed tasks.

cs.LG↗

arXiv2025

Constraining neutrino mass with the CSST galaxy clusters

With the advent of next-generation surveys, constraints on cosmological parameters are anticipated to become more stringent, particularly for the total neutrino mass. This study forecasts such constraints utilizing galaxy clusters from the Chinese Space Station Telescope (CSST). Employing Fisher matrix techniques, we derive the constraint $σ(M_ν)$ from cluster number counts, cluster power spectrum, and their combination. The investigation covers both the standard cosmological model with massive neutrinos $νΛ$CDM and the inclusion of dynamic dark energy in the $νw_0 w_a$CDM model, revealing a minor impact of dark energy on neutrino mass constraints. We examine the largest source of systematic arising from the mass-observable relation uncertainties and find that, with perfect knowledge of the scaling relation parameters, CSST clusters have the potential to enhance precision, tightening constraints to $\sim0.03$ eV. We also study the effects of the maximum redshift $z_{max}$ and other uncertainties, including those in redshift, halo mass function, and bias. Furthermore, we emphasize the significance of accounting for the growth-induced scale-dependent bias (GISDB) effect, which we find can tighten the final constraint by a factor of $1.2$ - $2.2$.

astro-ph.CO↗

arXiv2025

A numerical investigation of sweep effects on turbulent flow over iced wings

This study employs an improved delayed detached eddy simulation (AMD-IDDES) method to investigate the flow characteristics of an iced swept wing. The AMD-IDDES approach incorporates an anisotropic minimum-dissipation (AMD) model into the traditional IDDES framework to better account for local flow anisotropy and energy dissipation characteristics. The method is validated against the traditional IDDES approach, and the results show that AMD-IDDES more accurately captures the evolution of vortices and separated shear layers. Compared with an iced straight wing, a swept wing exhibits distinct aerodynamic behavior driven mainly by the sweep angle. The sweep angle induces strong spanwise flow, which reshapes the separation region and transforms the flow from two-dimensional to three-dimensional. This spanwise motion significantly alters vortex development and enhances the complexity of the unsteady flow. The shear layer separation, initiated by a Kelvin-Helmholtz instability, dominates the unsteady aerodynamic response. Although wingtip effects remain secondary, their interaction with the leading-edge vortex still contributes to lowering the dominant frequency. Overall, this study highlights that the aerodynamic forces of an iced swept wing are primarily governed by sweep-induced spanwise flow and associated shear layer dynamics, with minimal influence from the root and tip regions.

physics.flu-dyn↗

arXiv2025

Time-Frequency Transfer over Optical Fiber

Optical time-frequency transfer establishes the metrological linkage in large-scale clock networks, which facilitates various applications. Fiber-based transfer benefits from the abundant deployment of fiber infrastructures to achieve this advantage. In this Review, we provide an overview of the advances in optical two-way time-frequency transfer, which began with characterizing the time-frequency transfer stability. Then, we discuss the system configuration, key modules, main challenges, and mainstream transfer methods. Finally, the Review concludes with an outlook on further applications toward global-scale high-precision clock networks.

physics.optics↗

arXiv2025

Bridging Vision and Language: Optimal Transport-Driven Radiology Report Generation via LLMs

Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively capture the relationship between X-ray images and their corresponding texts, thus resulting in poor clinical practicability. To address these challenges, we propose Optimal Transport-Driven Radiology Report Generation (OTDRG), a novel framework that leverages Optimal Transport (OT) to align image features with disease labels extracted from reports, effectively bridging the cross-modal gap. The core component of OTDRG is Alignment \& Fine-Tuning, where OT utilizes results from the encoding of label features and image visual features to minimize cross-modal distances, then integrating image and text features for LLMs fine-tuning. Additionally, we design a novel disease prediction module to predict disease labels contained in X-ray images during validation and testing. Evaluated on the MIMIC-CXR and IU X-Ray datasets, OTDRG achieves state-of-the-art performance in both natural language generation (NLG) and clinical efficacy (CE) metrics, delivering reports that are not only linguistically coherent but also clinically accurate.

cs.CV↗

arXiv2025

Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models

Large language models (LLMs) have mastered abundant simple and explicit commonsense knowledge through pre-training, enabling them to achieve human-like performance in simple commonsense reasoning. Nevertheless, LLMs struggle to reason with complex and implicit commonsense knowledge that is derived from simple ones (such as understanding the long-term effects of certain events), an aspect humans tend to focus on more. Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure. To fill this gap and align with real-world concerns, we propose a benchmark Com$^2$ focusing on complex commonsense reasoning. We first incorporate causal event graphs to serve as structured complex commonsense. Then we adopt causal theory~(e.g., intervention) to modify the causal event graphs and obtain different scenarios that meet human concerns. Finally, an LLM is employed to synthesize examples with slow thinking, which is guided by the logical relationships in the modified causal graphs. Furthermore, we use detective stories to construct a more challenging subset. Experiments show that LLMs struggle in reasoning depth and breadth, while post-training and slow thinking can alleviate this. The code and data are available at https://github.com/Waste-Wood/Com2.

cs.CL↗

arXiv2025

Hi-LSplat: Hierarchical 3D Language Gaussian Splatting

Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a unified 3D representation, leading to view inconsistencies. Additionally, inherent open-vocabulary challenges cause inconsistencies in object and relational descriptions, impeding hierarchical semantic understanding. In this paper, we propose Hi-LSplat, a view-consistent Hierarchical Language Gaussian Splatting work for 3D open-vocabulary querying. To achieve view-consistent 3D hierarchical semantics, we first lift 2D features to 3D features by constructing a 3D hierarchical semantic tree with layered instance clustering, which addresses the view inconsistency issue caused by 2D semantic features. Besides, we introduce instance-wise and part-wise contrastive losses to capture all-sided hierarchical semantic representations. Notably, we construct two hierarchical semantic datasets to better assess the model's ability to distinguish different semantic levels. Extensive experiments highlight our method's superiority in 3D open-vocabulary segmentation and localization. Its strong performance on hierarchical semantic datasets underscores its ability to capture complex hierarchical semantics within 3D scenes.

cs.CV↗

arXiv2025

A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces

We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent method. We establish the global well-posedness of the gradient flow and demonstrate its exponential convergence to the optimal policy. Moreover, we prove the flow is stable with respect to gradient evaluation, offering insights into the performance of a natural policy gradient flow with log-linear policy parameterisation. To overcome challenges stemming from the lack of the convexity of the objective function and the discontinuity arising from the entropy regulariser, we leverage the performance difference lemma and the duality relationship between the gradient and mirror descent flows. Our analysis provides a theoretical foundation for developing various discrete policy gradient algorithms.

math.OC↗

arXiv2025

Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games

Multi-agent reinforcement learning, despite its popularity and empirical success, faces significant scalability challenges in large-population dynamic games. Graphon mean field games (GMFGs) offer a principled framework for approximating such games while capturing heterogeneity among players. In this paper, we propose and analyze a policy optimization framework for continuous-time, finite-horizon linear-quadratic GMFGs. Exploiting the structural properties of GMFGs, we design an efficient policy parameterization in which each player's policy is represented as an affine function of their private state, with a shared slope function and player-specific intercepts. We develop a bilevel optimization algorithm that alternates between policy gradient updates for best-response computation under a fixed population distribution, and distribution updates using the resulting policies. We prove linear convergence of the policy gradient steps to best-response policies and establish global convergence of the overall algorithm to the Nash equilibrium. The analysis relies on novel landscape characterizations over infinite-dimensional policy spaces. Numerical experiments demonstrate the convergence and robustness of the proposed algorithm under varying graphon structures, noise levels, and action frequencies.

math.OC↗

arXiv2025

Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo

Designing efficient learning algorithms with complexity guarantees for Markov decision processes (MDPs) with large or continuous state and action spaces remains a fundamental challenge. We address this challenge for entropy-regularized MDPs with Polish state and action spaces, assuming access to a generative model of the environment. We propose a novel family of multilevel Monte Carlo (MLMC) algorithms that integrate fixed-point iteration with MLMC techniques and a generic stochastic approximation of the Bellman operator. We quantify the precise impact of the chosen approximate Bellman operator on the accuracy of the resulting MLMC estimator. Leveraging this error analysis, we show that using a biased plain MC estimate for the Bellman operator results in quasi-polynomial sample complexity, whereas an unbiased randomized multilevel approximation of the Bellman operator achieves polynomial sample complexity in expectation. Notably, these complexity bounds are independent of the dimensions or cardinalities of the state and action spaces, distinguishing our approach from existing algorithms whose complexities scale with the sizes of these spaces. We validate these theoretical performance guarantees through numerical experiments.

cs.LG↗