arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 613 records · Page 34Linked to original sources

arXiv2025

Modeling Insider Filing Delays in Financial Markets with an Interpretable XGBoost Framework

Timely disclosure of insider transactions is a cornerstone of market transparency, yet delays in filing remain widespread and challenging to monitor at scale. This study introduces a comprehensive insider filing delay dataset spanning more than four million Form 4 transactions from 2002 to 2025, enriched with annotations on insider roles, governance attributes, and firm-level indicators. Building on these data, we present a hybrid framework that integrates a state-space encoder with an XGBoost classifier to capture temporal trading patterns while retaining interpretability essential for regulatory auditing. The framework consistently outperforms statistical models, deep sequence learners, and large language model baselines, achieving balanced gains in precision, recall, and F1-score. Feature ablation analyses highlight the predictive importance of insider history, spatiotemporal factors, and governance signals, shedding light on the behavioral drivers of both minor oversights and systematic violations. Beyond accuracy, the dataset and framework establish a reproducible benchmark for studying disclosure compliance, offering regulators and researchers transparent tools to strengthen market integrity.

cs.CE↗

arXiv2025

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Estimating the uncertainty of responses from Large Language Models (LLMs) remains a critical challenge. While recent Bayesian methods have demonstrated effectiveness in quantifying uncertainty through low-rank weight updates, they typically require complex fine-tuning or post-training procedures. In this paper, we propose Training-Free Bayesianization (TFB), a simple yet theoretically grounded framework that efficiently transforms trained low-rank adapters into Bayesian ones without additional training. TFB systematically searches for the maximally acceptable level of variance in the weight posterior, constrained within a family of low-rank isotropic Gaussian distributions. Our theoretical analysis shows that under mild conditions, this search process is equivalent to KL-regularized variational optimization, a generalized form of variational inference. Through comprehensive experiments, we show that TFB achieves superior uncertainty estimation and generalization compared to existing methods while eliminating the need for complex Bayesianization training procedures. Code will be available at https://github.com/Wang-ML-Lab/bayesian-peft.

stat.ML↗

arXiv2025

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.

cs.LG↗

arXiv2025

Generating Moving 3D Soundscapes with Latent Diffusion Models

Spatial audio has become central to immersive applications such as VR/AR, cinema, and music. Existing generative audio models are largely limited to mono or stereo formats and cannot capture the full 3D localization cues available in first-order Ambisonics (FOA). Recent FOA models extend text-to-audio generation but remain restricted to static sources. In this work, we introduce SonicMotion, the first end-to-end latent diffusion framework capable of generating FOA audio with explicit control over moving sound sources. SonicMotion is implemented in two variations: 1) a descriptive model conditioned on natural language prompts, and 2) a parametric model conditioned on both text and spatial trajectory parameters for higher precision. To support training and evaluation, we construct a new dataset of over one million simulated FOA caption pairs that include both static and dynamic sources with annotated azimuth, elevation, and motion attributes. Experiments show that SonicMotion achieves state-of-the-art semantic alignment and perceptual quality comparable to leading text-to-audio systems, while uniquely attaining low spatial localization error.

cs.SD↗

arXiv2025

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy to estimate advantage, which may cause the policy to fall into local optimum and increase computational cost. To address these issues, we propose PVPO, an efficient reinforcement learning method enhanced by an advantage reference anchor and data pre-sampling. Specifically, we use the reference model to rollout in advance and employ the calculated reward score as a reference anchor. Our approach effectively corrects the cumulative bias introduced by intra-group comparisons and significantly reduces reliance on the number of rollouts during training. Meanwhile, the reference model can assess sample difficulty during data pre-sampling, enabling effective selection of high-gain data to improve training efficiency. Moreover, PVPO is orthogonal to other advanced critic-free RL algorithms, making it compatible with and complementary to these methods. Experiments conducted on nine datasets across two domains demonstrate that PVPO achieves State-Of-The-Art (SOTA) performance. Our approach not only demonstrates robust generalization across multiple tasks, but also exhibits scalable performance across models of varying scales.

cs.LG↗

arXiv2025

FedCoSR: Personalized Federated Learning with Contrastive Shareable Representations for Label Heterogeneity in Non-IID Data

Heterogeneity arising from label distribution skew and data scarcity can cause inaccuracy and unfairness in intelligent communication applications that heavily rely on distributed computing. To deal with it, this paper proposes a novel personalized federated learning algorithm, named Federated Contrastive Shareable Representations (FedCoSR), to facilitate knowledge sharing among clients while maintaining data privacy. Specifically, the parameters of local models' shallow layers and typical local representations are both considered as shareable information for the server and are aggregated globally. To address performance degradation caused by label distribution skew among clients, contrastive learning is adopted between local and global representations to enrich local knowledge. Additionally, to ensure fairness for clients with scarce data, FedCoSR introduces adaptive local aggregation to coordinate the global model involvement in each client. Our simulations demonstrate FedCoSR's effectiveness in mitigating label heterogeneity by achieving accuracy and fairness improvements over existing methods on datasets with varying degrees of label heterogeneity.

cs.LG↗

arXiv2025

High-throughput screening of spin Hall conductivity in 2D materials

Two-dimensional (2D) materials with large spin Hall effect (SHE) have attracted significant attention due to their potential applications in next-generation spintronic devices. In this work, we perform high-throughput (HTP) calculations to obtain the spin Hall conductivity (SHC) of 4486 non-magnetic compounds in the \texttt{2Dmatpedia} database and identify six materials with SHC exceeding $500\,(\hbar/e)\,(\mathrm{S/cm})$, surpassing those of previously known materials. Detailed analysis reveals that the significant SHC can be attributed to spin-orbit coupling (SOC)-induced gap openings at Dirac-like band crossings. Additionally, the presence of mirror symmetry further enhances the SHC. Beyond the high-SHC materials, 57 topological insulators with quantized SHCs have also been identified. Our work enables rapid screening and paves the way for experimental validation, potentially accelerating the discovery of novel 2D materials optimized for spintronics applications.

cond-mat.mtrl-sci↗

arXiv2025

Enhancing CTR Prediction with De-correlated Expert Networks

Modeling feature interactions is essential for accurate click-through rate (CTR) prediction in advertising systems. Recent studies have adopted the Mixture-of-Experts (MoE) approach to improve performance by ensembling multiple feature interaction experts. These studies employ various strategies, such as learning independent embedding tables for each expert or utilizing heterogeneous expert architectures, to differentiate the experts, which we refer to expert de-correlation. However, it remains unclear whether these strategies effectively achieve de-correlated experts. To address this, we propose a De-Correlated MoE (D-MoE) framework, which introduces a Cross-Expert De-Correlation loss to minimize expert correlations.Additionally, we propose a novel metric, termed Cross-Expert Correlation, to quantitatively evaluate the expert de-correlation degree. Based on this metric, we identify a key finding for MoE framework design: different de-correlation strategies are mutually compatible, and progressively employing them leads to reduced correlation and enhanced performance. Extensive experiments have been conducted to validate the effectiveness of D-MoE and the de-correlation principle. Moreover, online A/B testing on Tencent's advertising platforms demonstrates that D-MoE achieves a significant 1.19% Gross Merchandise Volume (GMV) lift compared to the Multi-Embedding MoE baseline.

cs.IR↗

arXiv2025

Hopscotch: Discovering and Skipping Redundancies in Language Models

Modern causal language models stack many attention blocks to improve performance, but not all blocks are necessary for every task. We propose Hopscotch, a simple yet effective method that identifies and skips attention blocks with least contributions to a task and adapts to preserve output quality. Hopscotch jointly optimizes which blocks to skip and how to scale the outputs of the remaining layers. By introducing lightweight, trainable scaling parameters to attention and MLP blocks, it mitigates distribution shifts in hidden states caused by removing attention blocks. Hopscotch does not modify model weights or require access to pretraining or instruction-tuning data, and is compatible with existing model compression techniques. When applied to $\texttt{Llama-3.1-8B}$ and $\texttt{Qwen2.5-7B}$, Hopscotch achieves less than a 2% drop in performance even after skipping four attention blocks.

cs.CL↗

arXiv2025

Igniting VLMs toward the Embodied Space

While foundation models show remarkable progress in language and vision, existing vision-language models (VLMs) still have limited spatial and embodiment understanding. Transferring VLMs to embodied domains reveals fundamental mismatches between modalities, pretraining distributions, and training objectives, leaving action comprehension and generation as a central bottleneck on the path to AGI. We introduce WALL-OSS, an end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision-language understanding, (2) strong language-action association, and (3) robust manipulation capability. Our approach employs a tightly coupled architecture and multi-strategies training curriculum that enables Unified Cross-Level CoT-seamlessly unifying instruction reasoning, subgoal decomposition, and fine-grained action synthesis within a single differentiable framework. Our results show that WALL-OSS attains high success on complex long-horizon manipulations, demonstrates strong instruction-following capabilities, complex understanding and reasoning, and outperforms strong baselines, thereby providing a reliable and scalable path from VLMs to embodied foundation models.

cs.RO↗

arXiv2025

Redefining Website Fingerprinting Attacks With Multiagent LLMs

Website Fingerprinting (WFP) uses deep learning models to classify encrypted network traffic to infer visited websites. While historically effective, prior methods fail to generalize to modern web environments. Single-page applications (SPAs) eliminate the paradigm of websites as sets of discrete pages, undermining page-based classification, and traffic from scripted browsers lacks the behavioral richness seen in real user sessions. Our study reveals that users exhibit highly diverse behaviors even on the same website, producing traffic patterns that vary significantly across individuals. This behavioral entropy makes WFP a harder problem than previously assumed and highlights the need for larger, more diverse, and representative datasets to achieve robust performance. To address this, we propose a new paradigm: we drop session-boundaries in favor of contiguous traffic segments and develop a scalable data generation pipeline using large language models (LLM) agents. These multi-agent systems coordinate decision-making and browser interaction to simulate realistic, persona-driven browsing behavior at 3--5x lower cost than human collection. We evaluate nine state-of-the-art WFP models on traffic from 20 modern websites browsed by 30 real users, and compare training performance across human, scripted, and LLM-generated datasets. All models achieve under 10\% accuracy when trained on scripted traffic and tested on human data. In contrast, LLM-generated traffic boosts accuracy into the 80\% range, demonstrating strong generalization to real-world traces. Our findings indicate that for modern WFP, model performance is increasingly bottlenecked by data quality, and that scalable, semantically grounded synthetic traffic is essential for capturing the complexity of real user behavior.

cs.CR↗

arXiv2025

MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind

Large Language Model (LLM) agents have demonstrated impressive capabilities in social deduction games (SDGs) like Werewolf, where strategic reasoning and social deception are essential. However, current approaches remain limited to textual information, ignoring crucial multimodal cues such as facial expressions and tone of voice that humans naturally use to communicate. Moreover, existing SDG agents primarily focus on inferring other players' identities without modeling how others perceive themselves or fellow players. To address these limitations, we use One Night Ultimate Werewolf (ONUW) as a testbed and present MultiMind, the first framework integrating multimodal information into SDG agents. MultiMind processes facial expressions and vocal tones alongside verbal content, while employing a Theory of Mind (ToM) model to represent each player's suspicion levels toward others. By combining this ToM model with Monte Carlo Tree Search (MCTS), our agent identifies communication strategies that minimize suspicion directed at itself. Through comprehensive evaluation in both agent-versus-agent simulations and studies with human players, we demonstrate MultiMind's superior performance in gameplay. Our work presents a significant advancement toward LLM agents capable of human-like social reasoning across multimodal domains.

cs.AI↗

arXiv2025

Global Hopf bifurcation and connected components in a delayed predator-prey model

We study the dynamics of a delayed predator-prey system with Holling type II functional response, focusing on the interplay between time delay and carrying capacity. Using local and global Hopf bifurcation theory, we establish the existence of sequences of bifurcations as the delay parameter varies, and prove that the connected components of global Hopf branches are nested under suitable conditions. A novel contribution is to show that the classical limit cycle of the non-delayed system belongs to a connected component of the global Hopf bifurcation in Fuller's space. Our analysis combines rigorous functional differential equation theory with continuation methods to characterize the structure and boundedness of bifurcation branches. We further demonstrate that delays can induce oscillatory coexistence at lower carrying capacities than in the corresponding ODE model, yielding counterintuitive biological insights. The results contribute to the broader theory of global bifurcations in delay differential equations while providing new perspectives on nonlinear population dynamics.

math.DS↗

arXiv2025

GreyShot: Zeroshot and Privacy-preserving Recommender System by GM(1,1) Model

Every recommendation engineer needs to face the cold start problem when building his system. During the past decades, most scientists adopted transfer learning and meta learning to solve the problem. Although notable exceptions such as ZeroMat etc. have been invented in recent years, cold-start problem remains a challenging problem for many researchers. In this paper, we build a zeroshot and privacy-preserving recommender system algorithm GreyShot using GM(1,1) model by taking advantage of the Poisson-Pareto property of the online rating data. Our approach relies on no input data and is effective in generating both accurate and fair results. In conclusion, zeroshot problem of recommender systems could be effectively solved by grey system methods such as GM(1,1).

cs.IR↗

arXiv2025

The enhanced X-ray Timing and Polarimetry mission -- eXTP for launch in 2030

In this paper we present the current status of the enhanced X-ray Timing and Polarimetry mission, which has been fully approved for launch in 2030. eXTP is a space science mission designed to study fundamental physics under extreme conditions of matter density, gravity, and magnetism. The mission aims at determining the equation of state of matter at supra-nuclear density, measuring the effects of quantum electro-dynamics, and understanding the dynamics of matter in strong-field gravity. In addition to investigating fundamental physics, the eXTP mission is poised to become a leading observatory for time-domain and multi-messenger astronomy in the 2030's, as well as providing observations of unprecedented quality on a variety of galactic and extragalactic objects. After briefly introducing the history and a summary of the scientific objectives of the eXTP mission, this paper presents a comprehensive overview of: 1) the cutting-edge technology, technical specifications, and anticipated performance of the mission's scientific instruments; 2) the full mission profile, encompassing spacecraft design, operational capabilities, and ground segment infrastructure.

astro-ph.HE↗

arXiv2025

A large language model system for the field of chemical engineering technology

The development of chemical engineering technology is a multi-stage process that encompasses laboratory research, scaling up, and industrial deployment. This process demands interdisciplinary col laboration and typically incurs significant time and economic costs. To tackle these challenges, we have developed a system based on ChemELLM in this work. This system enables users to interact freely with the chem ical engineering model, establishing a new paradigm for AI-driven in novation and accelerating technological advancements in the chemical sector.If you would like to experience our system, please visit our official website at: https://chemindustry.iflytek.com/chat.

physics.chem-ph↗

arXiv2025

Geometry-Dependent Defect Merging Induces Bifurcated Dynamics in Active Networks

Cytoskeletal networks can repair defects to maintain structural integrity. However, the mechanisms and dynamics of defect merging remain poorly understood. Here we report a geometry-tunable merging mechanism in microtubule-motor networks initiated by active crosslinking. We directly generate defects using a light-controlled microtubule-motor system in O-shaped and V-shaped networks, and observe that the defects can self-close. Combining theory and experiment, we find that the V-shaped networks must overcome internal elastic resistance in order to zip up cracks, giving rise to a bifurcation of dynamics dependent on the initial opening angle of the crack: the crack merges below a critical angle and opens up at larger angles. Simulation of a continuum model reproduces the bifurcation dynamics, revealing the importance of overlapping boundary layers where free motors and microtubules can actively crosslink and thereby merge the defects. We also formulate a simple elastic-rod model that can qualitatively predict the critical angle, which is tunable by the network geometry.

cond-mat.soft↗

arXiv2025

Kwai Keye-VL 1.5 Technical Report

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.

cs.CV↗