arXiv subjects

Jin Zhou

Publications and source records attributed to Jin Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning

LLMs often underperform on complex reasoning tasks when relying on a single generation-and-selection pipeline. Inference-time ensemble methods can improve performance by sampling diverse reasoning paths or aggregating multiple candidate answers, but they typically treat candidates independently and provide no formal guarantees that ensembling improves reasoning quality. We propose a novel method, Aligned Delegation for Multi-Agent LLM Reasoning (ALIGN), which formulates LLM reasoning as an aligned delegation game. In ALIGN, a principal delegates a task to multiple agents that generate candidate solutions under designed incentives, and then selects among their outputs to produce a final answer. This formulation induces structured interaction among agents while preserving alignment between agent and principal objectives. We establish theoretical guarantees showing that, under a fair comparison with equal access to candidate solutions, ALIGN provably improves expected performance over single-agent generation. Our analysis accommodates correlated candidate answers and relaxes independence assumptions that are commonly used in prior work. Empirical results across a broad range of LLM reasoning benchmarks consistently demonstrate that ALIGN outperforms strong single-agent and ensemble baselines.

cs.LG↗

arXiv2026

DiEC: Diffusion Embedded Clustering

Deep clustering methods typically rely on a single, well-defined representation for clustering. In contrast, pretrained diffusion models provide abundant and diverse multi-scale representations across network layers and noise timesteps. However, a key challenge is how to efficiently identify the most clustering-friendly representation in the layer*timestep space. To address this issue, we propose Diffusion Embedded Clustering (DiEC), an unsupervised framework that performs clustering by leveraging optimal intermediate representations from pretrained diffusion models. DiEC systematically evaluates the clusterability of representations along the trajectory of network depth and noise timesteps. Meanwhile, an unsupervised search strategy is designed for recognizing the Clustering-optimal Layer (COL) and Clustering-optimal Timestep (COT) in the layer*timestep space of pretrained diffusion models, aiming to promote clustering performance and reduce computational overhead. DiEC is fine-tuned primarily with a structure-preserving DEC-style KL-divergence objective at the fixed COL + COT, together with a random-timestep diffusion denoising objective to maintain the generative capability of the pretrained model. Without relying on augmentation-based consistency constraints or contrastive learning, DiEC achieves excellent clustering performance across multiple benchmark datasets.

cs.LG↗

arXiv2025

SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing

Neural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model high-level semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.

cs.GR↗

arXiv2025

StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

In the field of sketch generation, raster-format trained models often produce non-stroke artifacts, while vector-format trained models typically lack a holistic understanding of sketches, leading to compromised recognizability. Moreover, existing methods struggle to extract common features from similar elements (e.g., eyes of animals) appearing at varying positions across sketches. To address these challenges, we propose StrokeFusion, a two-stage framework for vector sketch generation. It contains a dual-modal sketch feature learning network that maps strokes into a high-quality latent space. This network decomposes sketches into normalized strokes and jointly encodes stroke sequences with Unsigned Distance Function (UDF) maps, representing sketches as sets of stroke feature vectors. Building upon this representation, our framework exploits a stroke-level latent diffusion model that simultaneously adjusts stroke position, scale, and trajectory during generation. This enables high-fidelity sketch generation while supporting stroke interpolation editing. Extensive experiments on the QuickDraw dataset demonstrate that our framework outperforms state-of-the-art techniques, validating its effectiveness in preserving structural integrity and semantic features. Code and models will be made publicly available upon publication.

cs.GR↗

arXiv2025

StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement

Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures. The code is publicly available at %\href{https://github.com/Teagrus/StructLayoutFormer} {https://github.com/Teagrus/StructLayoutFormer}.

cs.GR↗

arXiv2025

Realization of large magnetocaloric effect in the Kagome antiferromagnet Gd3BWO9 for Sub-Kelvin cryogenic refrigeration

Rare-earth (RE) based frustrated magnets have attracted great attention as excellent candidates for magnetic refrigeration at sub-Kelvin temperatures, while the experimental identification on systems exhibiting both large volumetric cooling capacity and reduced working temperatures far below 1 K remain to be a challenge. Here, through the ultra-low temperature magnetism and thermodynamic characterizations, we unveil the large magnetocaloric effect (MCE) realized at sub-Kelvin temperatures in the frustrated Kagome antiferromagnet Gd3BWO9 with TN~1.0 K. The isothermal magnetization curves indicate the existence of field (B) induced anisotropic magnetic phase diagrams, where four distinct magnetic phases for B // c-axis and five magnetic phases for B // ab-plane are identified at T< TN. The analysis of magnetic entropy S(B, T) data and direct adiabatic demagnetization tests reveal a remarkable cooling performance at sub-Kelvin temperatures featured by a large volumetric entropy density 502.2 mJ/K/cm3 and a low attainable minimal temperature Tmin~168 mK from the initial cooling condition of 2 K and 6 T, surpassing most of Gd-based refrigerants previously documented in temperature ranges of 0.25-4 K. The realized Tmin~168 mK far below TN ~ 1.0 K in Gd3BWO9 is related to the combined effects of magnetic frustration and criticality-enhanced MCE, which together leave a substantial magnetic entropy at reduced temperatures by enhancing spin fluctuations.

cond-mat.str-el↗

arXiv2025

Two-Stage Least Squares Instrumental Variable Estimation for Semiparametric Accelerated Failure Time Models with Right-Censored Data

Instrumental variable (IV) analysis is widely used in fields such as economics and epidemiology to address unobserved confounding and measurement error when estimating the causal effects of intermediate covariates on outcomes. However, extending the commonly used two-stage least squares (TSLS) approach to survival settings is nontrivial due to censoring. This paper introduces a novel extension of TSLS to the semiparametric accelerated failure time (AFT) model with right-censored data, supported by rigorous theoretical justification. Specifically, we propose an iterative reweighted generalized estimating equation (GEE) approach that incorporates Leurgans' synthetic variable method, establish the asymptotic properties of the resulting estimator, and derive a consistent variance estimator, enabling valid causal inference. Simulation studies are conducted to evaluate the finite-sample performance of the proposed method across different scenarios. The results show that it outperforms the naive unweighted GEE method, a parametric IV approach, and a one-stage estimator without IV. The proposed method is also highly scalable to large datasets, achieving a 300- to 1500-fold speedup relative to a Bayesian parametric IV approach in both simulations and the real-data example. We further illustrate the utility of the proposed method through a real-data application using the UK Biobank data.

stat.ME↗

arXiv2025

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation

Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-audio generation, including multimodal data scarcity, modality imbalance and limited audio quality in existing methods, we propose HunyuanVideo-Foley, an end-to-end text-video-to-audio framework that synthesizes high-fidelity audio precisely aligned with visual dynamics and semantic context. Our approach incorporates three core innovations: (1) a scalable data pipeline curating 100k-hour multimodal datasets through automated annotation; (2) a representation alignment strategy using self-supervised audio features to guide latent diffusion training, efficiently improving audio quality and generation stability; (3) a novel multimodal diffusion transformer resolving modal competition, containing dual-stream audio-video fusion through joint attention, and textual semantic injection via cross-attention. Comprehensive evaluations demonstrate that HunyuanVideo-Foley achieves new state-of-the-art performance across audio fidelity, visual-semantic alignment, temporal alignment and distribution matching. The demo page is available at: https://szczesnys.github.io/hunyuanvideo-foley/.

eess.AS↗

arXiv2025

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require understanding diagrams with complex physical structures and quantitative analysis based on multi-modal information. To address this, we develop a new framework, named Multi-Modal Scientific Reasoning with Physics Perception and Simulation (MAPS) based on an MLLM. MAPS decomposes expert-level multi-modal reasoning task into physical diagram understanding via a Physical Perception Model (PPM) and reasoning with physical knowledge via a simulator. The PPM module is obtained by fine-tuning a visual language model using carefully designed synthetic data with paired physical diagrams and corresponding simulation language descriptions. At the inference stage, MAPS integrates the simulation language description of the input diagram provided by PPM and results obtained through a Chain-of-Simulation process with MLLM to derive the underlying rationale and the final answer. Validated using our collected college-level circuit analysis problems, MAPS significantly improves reasoning accuracy of MLLM and outperforms all existing models. The results confirm MAPS offers a promising direction for enhancing multi-modal scientific reasoning ability of MLLMs. We will release our code, model and dataset used for our experiments upon publishing of this paper.

cs.AI↗

arXiv2025

Efficient Implementation of a Semiparametric Joint Model for Multivariate Longitudinal Biomarkers and Competing Risks Time-to-Event Data

Joint modeling has become increasingly popular for characterizing the association between one or more longitudinal biomarkers and competing risks time-to-event outcomes. However, semiparametric multivariate joint modeling for large-scale data encounter substantial statistical and computational challenges, primarily due to the high dimensionality of random effects and the complexity of estimating nonparametric baseline hazards. These challenges often lead to prolonged computation time and excessive memory usage, limiting the utility of joint modeling for biobank-scale datasets. In this article, we introduce an efficient implementation of a semiparametric multivariate joint model, supported by a normal approximation and customized linear scan algorithms within an expectation-maximization (EM) framework. Our method significantly reduces computation time and memory consumption, enabling the analysis of data from thousands of subjects. The scalability and estimation accuracy of our approach are demonstrated through two simulation studies. We also present an application to the Primary Biliary Cirrhosis (PBC) dataset involving five longitudinal biomarkers as an illustrative example. A user-friendly R package, \texttt{FastJM}, has been developed for the shared random effects joint model with efficient implementation. The package is publicly available on the Comprehensive R Archive Network: https://CRAN.R-project.org/package=FastJM.

stat.ME↗

arXiv2025

HunyuanVideo: A Systematic Framework For Large Video Generative Models

Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at https://github.com/Tencent/HunyuanVideo.

cs.CV↗

arXiv2025

Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning

Recent innovations in autonomous drones have facilitated time-optimal flight in single-drone configurations, and enhanced maneuverability in multi-drone systems by applying optimal control and learning-based methods. However, few studies have achieved time-optimal motion planning for multi-drone systems, particularly during highly agile maneuvers or in dynamic scenarios. This paper presents a decentralized policy network using multi-agent reinforcement learning for time-optimal multi-drone flight. To strike a balance between flight efficiency and collision avoidance, we introduce a soft collision-free mechanism inspired by optimization-based methods. By customizing PPO in a centralized training, decentralized execution (CTDE) fashion, we unlock higher efficiency and stability in training while ensuring lightweight implementation. Extensive simulations show that, despite slight performance trade-offs compared to single-drone systems, our multi-drone approach maintains near-time-optimal performance with a low collision rate. Real-world experiments validate our method, with two quadrotors using the same network as in simulation achieving a maximum speed of 13.65 m/s and a maximum body rate of 13.4 rad/s in a 5.5 m * 5.5 m * 2.0 m space across various tracks, relying entirely on onboard computation.

cs.RO↗

arXiv2025

A Semiparametric Bayesian Method for Instrumental Variable Analysis with Partly Interval-Censored Time-to-Event Outcome

This paper develops a semiparametric Bayesian instrumental variable analysis method for estimating the causal effect of an endogenous variable when dealing with unobserved confounders and measurement errors with partly interval-censored time-to-event data, where event times are observed exactly for some subjects but left-censored, right-censored, or interval-censored for others. Our method is based on a two-stage Dirichlet process mixture instrumental variable (DPMIV) model which simultaneously models the first-stage random error term for the exposure variable and the second-stage random error term for the time-to-event outcome using a bivariate Gaussian mixture of the Dirichlet process (DPM) model. The DPM model can be broadly understood as a mixture model with an unspecified number of Gaussian components, which relaxes the normal error assumptions and allows the number of mixture components to be determined by the data. We develop an MCMC algorithm for the DPMIV model tailored for partly interval-censored data and conduct extensive simulations to assess the performance of our DPMIV method in comparison with some competing methods. Our simulations revealed that our proposed method is robust under different error distributions and can have superior performance over its parametric counterpart under various scenarios. We further demonstrate the effectiveness of our approach on an UK Biobank data to investigate the causal effect of systolic blood pressure on time-to-development of cardiovascular disease from the onset of diabetes mellitus.

stat.ME↗

arXiv2024

Structure and magnetic properties of a family of two-leg spin ladder compounds Ba2RE2Ge4O13 (RE = Pr, Nd, and Gd-Ho) with strong rung interaction

Compared to the intensive investigation on the 3d transition-metal (TM)-based spin ladder compounds, less attention has been paid to the ones constructed by the rare-earth (RE) ions. Herein, we report a family of RE-based spin ladder compounds Ba2RE2Ge4O13 (RE = Pr, Nd, Gd-Ho) crystallized into the monoclinic structure with the space group C2/c. The RE ions are arranged on a two-leg spin ladder motif along the b-axis, where the rung and leg exchange interactions are bridged via the RE-O-RE pathways and RE-O-Ge-O-RE routes, respectively. Moreover, the much shorter rung distance in the RE2O12 dimer units than the leg distance suggests Ba2RE2Ge4O13 to be a strong-rung spin ladder system. All the synthesized Ba2RE2Ge4O13 (RE = Pr, Nd, Gd-Ho) compounds exhibit the dominant antiferromagnetic (AFM) interactions and absence of magnetic order down to 1.8 K. Among the family members, Ba2Dy2Ge4O13 can be described by Jeff = 1/2 Kramers doublet states, the low temperature specific heat indicates the coexistence of spin dimerized state with broad maximum at ~ 2.4 K and long-range AFM order with TN = 0.81 K. This family of Ba2RE2Ge4O13 compounds thereby provides a rare platform to investigate the novel spin ladder physics constructed by 4f electrons.

cond-mat.str-el↗

arXiv2024

Understanding and Alleviating Memory Consumption in RLHF for LLMs

Fine-tuning with Reinforcement Learning with Human Feedback (RLHF) is essential for aligning large language models (LLMs). However, RLHF often encounters significant memory challenges. This study is the first to examine memory usage in the RLHF context, exploring various memory management strategies and unveiling the reasons behind excessive memory consumption. Additionally, we introduce a simple yet effective approach that substantially reduces the memory required for RLHF fine-tuning.

cs.LG↗

arXiv2024

Gate-Aware Online Planning for Two-Player Autonomous Drone Racing

The flying speed of autonomous quadrotors has increased significantly over the past 5 years, particularly in the field of autonomous drone racing. However, most research primarily focuses on the aggressive flight of a single quadrotor, simplifying the racing gate traversal problem to a waypoint passing problem that neglects the orientations of the racing gates. In this paper, we propose a systematic method called Pairwise Model Predictive Control (PMPC) that can guide two quadrotors online to navigate racing gates with minimal time and without collisions. The flight task is initially simplified as a point-mass model waypoint passing problem to provide analytical time optimal reference through an efficient two-step velocity search method. Subsequently, we utilize the spatial configuration of the racing track to compute the optimal heading at each gate, maximizing the visibility of subsequent gates for the quadrotors. To address varying gate orientations, we introduce a novel Magnetic Induction Line-based spatial curve to guide the quadrotors through racing gates of different orientations. Furthermore, we formulate a nonlinear optimization problem that uses the point-mass trajectory as initial values and references to enhance solving efficiency, enabling the method to run onboard at a frequency of 200 Hz. The feasibility of the proposed method is validated through both simulation and real-world experiments. In real-world tests, the two quadrotors achieved a top speed of 6.1 m/s on a 7-waypoint racing track within a compact flying arena of 5 m * 4 m * 2 m.

cs.RO↗

arXiv2024

Imitation Learning-Based Online Time-Optimal Control with Multiple-Waypoint Constraints for Quadrotors

Over the past decade, there has been a remarkable surge in utilizing quadrotors for various purposes due to their simple structure and aggressive maneuverability, such as search and rescue, delivery and autonomous drone racing, etc. One of the key challenges preventing quadrotors from being widely used in these scenarios is online waypoint-constrained time-optimal trajectory generation and control technique. This letter proposes an imitation learning-based online solution to efficiently navigate the quadrotor through multiple waypoints with time-optimal performance. The neural networks (WN&CNets) are trained to learn the control law from the dataset generated by the time-consuming CPC algorithm and then deployed to generate the optimal control commands online to guide the quadrotors. To address the challenge of limited training data and the hover maneuver at the final waypoint, we propose a transition phase strategy that utilizes MINCO trajectories to help the quadrotor 'jump over' the stop-and-go maneuver when switching waypoints. Our method is demonstrated in both simulation and real-world experiments, achieving a maximum speed of 5.6m/s while navigating through 7 waypoints in a confined space of 5.5m*5.5m*2.0m. The results show that with a slight loss in optimality, the WN&CNets significantly reduce the processing time and enable online optimal control for multiple-waypoint constrained flight tasks.

cs.RO↗

arXiv2024

Ba6RE2Ti4O17 (RE= Nd, Sm,Gd, Dy-Yb): A family of Rare-earth based layered triangular lattice magnets

Rare-earth-based triangular-lattice magnets provide the fertile ground to explore the exotic quantum magnetic state. Herein, we report a new family of RE-based triangular-lattice magnets Ba6RE2Ti4O17(RE= rare earth ions) crystallized into the hexagonal structure with space group of P63 mmc, where magnetic rare earth ions form an ideal triangular lattice within the ab-plane and stack in an AA -type fashion along the c-axis. The low-temperature magnetic susceptibility results reveal all the serial compounds have the dominant antiferromagnetic interactions and an absence of magnetic ordering down to 1.8 K. The magnetization and electron spin resonance results indicate distinct magnetic anisotropy for the compounds with different RE ions. Moreover, Ba6Nd2Ti4O17 single crystal is successfully grown and it exhibits strong Ising like anisotropy with magnetic easy-axis perpendicular to the triangle-lattice plane, being a candidate to explore quantum spin liquid state with dominant Ising-type interaction.

cond-mat.mtrl-sci↗