arXiv subjects

Hao Liu

Publications and source records attributed to Hao Liu.

At least 217 records · Page 12Linked to original sources

arXiv2025

Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition

Foundation models (FMs), such as GPT-4 and AlphaFold, are reshaping the landscape of scientific research. Beyond accelerating tasks such as hypothesis generation, experimental design, and result interpretation, they prompt a more fundamental question: Are FMs merely enhancing existing scientific methodologies, or are they redefining the way science is conducted? In this paper, we argue that FMs are catalyzing a transition toward a new scientific paradigm. We introduce a three-stage framework to describe this evolution: (1) Meta-Scientific Integration, where FMs enhance workflows within traditional paradigms; (2) Hybrid Human-AI Co-Creation, where FMs become active collaborators in problem formulation, reasoning, and discovery; and (3) Autonomous Scientific Discovery, where FMs operate as independent agents capable of generating new scientific knowledge with minimal human intervention. Through this lens, we review current applications and emerging capabilities of FMs across existing scientific paradigms. We further identify risks and future directions for FM-enabled scientific discovery. This position paper aims to support the scientific community in understanding the transformative role of FMs and to foster reflection on the future of scientific discovery. Our project is available at https://github.com/usail-hkust/Awesome-Foundation-Models-for-Scientific-Discovery.

cs.LG↗

arXiv2025

SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior

In this paper, we study the content-aware layout generation problem, which aims to automatically generate layouts that are harmonious with a given background image. Existing methods usually deal with this task with a single-step reasoning framework. The lack of a feedback-based self-correction mechanism leads to their failure rates significantly increasing when faced with complex element layout planning. To address this challenge, we introduce SEGA, a novel Stepwise Evolution Paradigm for Content-Aware Layout Generation. Inspired by the systematic mode of human thinking, SEGA employs a hierarchical reasoning framework with a coarse-to-fine strategy: first, a coarse-level module roughly estimates the layout planning results; then, another refining module performs fine-level reasoning regarding the coarse planning results. Furthermore, we incorporate layout design principles as prior knowledge into the model to enhance its layout planning ability. Besides, we present GenPoster-100K that is a new large-scale poster dataset with rich meta-information annotation. The experiments demonstrate the effectiveness of our approach by achieving the state-of-the-art results on multiple benchmark datasets. Our project page is at: https://brucew91.github.io/SEGA.github.io/

cs.CV↗

arXiv2025

Outraged AI: Large language models prioritise emotion over cost in fairness enforcement

Emotions guide human decisions, but whether large language models (LLMs) use emotion similarly remains unknown. We tested this using altruistic third-party punishment, where an observer incurs a personal cost to enforce fairness, a hallmark of human morality and often driven by negative emotion. In a large-scale comparison of 4,068 LLM agents with 1,159 adults across 796,100 decisions, LLMs used emotion to guide punishment, sometimes even more strongly than humans did: Unfairness elicited stronger negative emotion that led to more punishment; punishing unfairness produced more positive emotion than accepting; and critically, prompting self-reports of emotion causally increased punishment. However, mechanisms diverged: LLMs prioritized emotion over cost, enforcing norms in an almost all-or-none manner with reduced cost sensitivity, whereas humans balanced fairness and cost. Notably, reasoning models (o3-mini, DeepSeek-R1) were more cost-sensitive and closer to human behavior than foundation models (GPT-3.5, DeepSeek-V3), yet remained heavily emotion-driven. These findings provide the first causal evidence of emotion-guided moral decisions in LLMs and reveal deficits in cost calibration and nuanced fairness judgements, reminiscent of early-stage human responses. We propose that LLMs progress along a trajectory paralleling human development; future models should integrate emotion with context-sensitive reasoning to achieve human-like emotional intelligence.

cs.CL↗

arXiv2025

RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness of these detection methods is still underexplored. Existing Graph Neural Network (GNN)-based methods cannot be directly applied due to the issues of limited control over social agents, the black-box nature of bot detectors, and the heterogeneity of bots. To address these challenges, this paper proposes the first adversarial multi-agent Reinforcement learning framework for social Bot control attacks (RoBCtrl) targeting GNN-based social bot detectors. Specifically, we use a diffusion model to generate high-fidelity bot accounts by reconstructing existing account data with minor modifications, thereby evading detection on social platforms. To the best of our knowledge, this is the first application of diffusion models to mimic the behavior of evolving social bots effectively. We then employ a Multi-Agent Reinforcement Learning (MARL) method to simulate bots adversarial behavior. We categorize social accounts based on their influence and budget. Different agents are then employed to control bot accounts across various categories, optimizing the attachment strategy through reinforcement learning. Additionally, a hierarchical state abstraction based on structural entropy is designed to accelerate the reinforcement learning. Extensive experiments on social bot detection datasets demonstrate that our framework can effectively undermine the performance of GNN-based detectors.

cs.LG↗

arXiv2025

On the existence of self-similar solutions to the steady Navier-Stokes equations in high dimensions

We prove that the steady incompressible Navier-Stokes equations with any given $(-3)$-homogeneous, locally Lipschitz external force on $\mathbb{R}^n\setminus\{0\}$, $4\leq n\leq 16$, have at least one $(-1)$-homogeneous solution which is scale-invariant and regular away from the origin. The global uniqueness of the self-similar solution is obtained as long as the external force is small. The key observation is to exploit a nice relation between the radial component of the velocity and the total head pressure under the self-similarity assumption. It plays an essential role in establishing the energy estimates. If the external force has only the nonnegative radial component, we can prove the existence of $(-1)$-homogeneous solutions for all $n\geq 4$. The regularity of the solution follows from integral estimates of the positive part of the total head pressure, which is due to the maximum principle and a ``dimension-reduction" effect arising from the self-similarity.

math.AP↗

arXiv2025

DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi

On-demand ride-hailing services like DiDi, Uber, and Lyft have transformed urban transportation, offering unmatched convenience and flexibility. In this paper, we introduce DiMA, an LLM-powered ride-hailing assistant deployed in DiDi Chuxing. Its goal is to provide seamless ride-hailing services and beyond through a natural and efficient conversational interface under dynamic and complex spatiotemporal urban contexts. To achieve this, we propose a spatiotemporal-aware order planning module that leverages external tools for precise spatiotemporal reasoning and progressive order planning. Additionally, we develop a cost-effective dialogue system that integrates multi-type dialog repliers with cost-aware LLM configurations to handle diverse conversation goals and trade-off response quality and latency. Furthermore, we introduce a continual fine-tuning scheme that utilizes real-world interactions and simulated dialogues to align the assistant's behavior with human preferred decision-making processes. Since its deployment in the DiDi application, DiMA has demonstrated exceptional performance, achieving 93% accuracy in order planning and 92% in response generation during real-world interactions. Offline experiments further validate DiMA capabilities, showing improvements of up to 70.23% in order planning and 321.27% in response generation compared to three state-of-the-art agent frameworks, while reducing latency by $0.72\times$ to $5.47\times$. These results establish DiMA as an effective, efficient, and intelligent mobile assistant for ride-hailing services. Our project is released at https://github.com/usail-hkust/DiMA and we also release the MCP service (https://mcp.didichuxing.com/api) to foster the ride-hailing research community.

cs.CL↗

arXiv2025

An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigation

The rise of Internet of Vehicles (IoV) technologies is transforming traffic management from isolated control to a collective, multi-vehicle process. At the heart of this shift is multi-vehicle dynamic navigation, which requires simultaneously routing large fleets under evolving traffic conditions. Existing path search algorithms and reinforcement learning methods struggle to scale to city-wide networks, often failing to capture the nonlinear, stochastic, and coupled dynamics of urban traffic. To address these challenges, we propose CityNav, a hierarchical, LLM-powered framework for large-scale multi-vehicle navigation. CityNav integrates a global traffic allocation agent, which coordinates strategic traffic flow distribution across regions, with local navigation agents that generate locally adaptive routes aligned with global directives. To enable effective cooperation, we introduce a cooperative reasoning optimization mechanism, in which agents are jointly trained with a dual-reward structure: individual rewards promote per-vehicle efficiency, while shared rewards encourage network-wide coordination and congestion reduction. Extensive experiments on four real-world road networks of varying scales (up to 1.6 million roads and 430,000 intersections) and traffic datasets demonstrate that CityNav consistently outperforms nine classical path search and RL-based baselines in city-scale travel efficiency and congestion mitigation. Our results highlight the potential of LLMs to enable scalable, adaptive, and cooperative city-wide traffic navigation, providing a foundation for intelligent, large-scale vehicle routing in complex urban environments. Our project is available at https://github.com/usail-hkust/CityNav.

cs.AI↗

arXiv2025

Baseline-Aware Dependence fitting for DAmping Timescales (BADDAT): A Nearly Unbiased Approach to Constraining Optical Variability Dependence on Physical Properties of Active Galactic Nuclei

Active galactic nuclei (AGNs) exhibit stochastic optical variability, commonly characterized by a damped random walk. The damping timescale is of particular interest because it is related to fundamental properties of the central black hole, such as its mass and accretion rate. However, the systematic underestimation of damping timescales caused by limited observational baselines makes it difficult to exhaustively utilize all available data. Many previous efforts have relied on strict selection criteria to avoid biased measurements, and such criteria inevitably constrain the range of AGN physical parameter space and therefore hinder robust inference of the underlying dependencies of damping timescale on AGN properties. In contrast, we introduce a novel forward modeling approach, Baseline-Aware Dependence fitting for DAmping Timescales (BADDAT), which explicitly accounts for these biases and leverages the information contained in underestimated timescale measurements. Rather than attempting to correct individual timescale measurements, BADDAT robustly constrains the population-level dependence of damping timescale on AGN physical properties. We demonstrate its effectiveness using mock light curves and show that it successfully reconciles previous inconsistent results based on two independent AGN samples. Our BADDAT method will have broad applications in AGN variability studies during the era of time-domain astronomy.

astro-ph.GA↗

arXiv2025

A new variability pattern in GRS 1915+105 with NICER and Insight-HXMT observations

We explore the timing and spectral properties of GRS 1915+105 based on X-ray observations of NICER and Insight-HXMT during the long outburst from 2017 to 2021. We find a new class of variability in the rising stage of the outburst that differs from the formerly reported patterns of light curves. This new variability pattern, which we name class $ψ$, is characterized by several periodic mini pulses superposed on another longer periodic pulse. The periods are around $\sim$130 seconds and $\sim$10 seconds for the main pulses and mini pulses respectively based on the analysis of power spectrum density (PSD) and step-wise filter correlation (SFC), where the SFC method has an advantage in finding the superimposed periodic components. The mini pulses become weak or disappear when the luminosity increases and the light curves change into the classical class $κ$. The class $ψ$ shows a softer spectrum with lower count rates compared to the class $κ$ during the main pulse. The new class $ψ$ shows peculiar timing and spectral properties compared to those of classic class $κ$, which can help us to explore the class transition mechanism in GRS 1915+105.

astro-ph.HE↗

arXiv2025

How Microplastics cross the Buoyancy Barrier: A multi-scale Study

Microplastics (MPs), though less dense than water, are frequently recovered from sediments in aqueous environments, indicating they can cross the buoyancy barrier. We quantify eco-corona mediated MP-sediment attraction and MP transport from the nanoscale to the macroscale, linking all scales to a coherent mechanism explaining how MP overcome buoyancy and settle in sediments through interaction with suspended sediment. Colloidal probe atomic force microscopy (CP-AFM) detected attractive forces (0.15 - 17 mN/m) enabling heteroaggregation. Microscale tests confirmed aggregation and on larger scales sediment retention more than doubled with an eco-corona. Simulations showed that environmental shear force ($4 \cdot 10^{-4} mN/m$) cannot disrupt aggregates. In sedimentation columns, biofilm-covered MPs settled twice as often as plain MPs in bentonite suspensions. MP retention increased by 32 %. These results demonstrate that eco-corona/biofilm-mediated heteroaggregation is a robust pathway for MP sinking, accumulation, and retention in sediment beds. By identifying physical interaction thresholds and aggregation stability, we provide mechanistic insight into MP fate, highlight probable accumulation hotspots, and offer an evidence base for improved risk assessment and environmental modelling.

cond-mat.soft↗

arXiv2025

Semantic Exploration and Dense Mapping of Complex Environments using Ground Robot with Panoramic LiDAR-Camera Fusion

This paper presents a system for autonomous semantic exploration and dense semantic target mapping of a complex unknown environment using a ground robot equipped with a LiDAR-panoramic camera suite. Existing approaches often struggle to balance collecting high-quality observations from multiple view angles and avoiding unnecessary repetitive traversal. To fill this gap, we propose a complete system combining mapping and planning. We first redefine the task as completing both geometric coverage and semantic viewpoint observation. We then manage semantic and geometric viewpoints separately and propose a novel Priority-driven Decoupled Local Sampler to generate local viewpoint sets. This enables explicit multi-view semantic inspection and voxel coverage without unnecessary repetition. Building on this, we develop a hierarchical planner to ensure efficient global coverage. In addition, we propose a Safe Aggressive Exploration State Machine, which allows aggressive exploration behavior while ensuring the robot's safety. Our system includes a plug-and-play semantic target mapping module that integrates seamlessly with state-of-the-art SLAM algorithms for pointcloud-level dense semantic target mapping. We validate our approach through extensive experiments in both realistic simulations and complex real-world environments. Simulation results show that our planner achieves faster exploration and shorter travel distances while guaranteeing a specified number of multi-view inspections. Real-world experiments further confirm the system's effectiveness in achieving accurate dense semantic object mapping of unstructured environments.

cs.RO↗

arXiv2025

Self-Questioning Language Models

Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic (e.g., algebra word problems) and asking the model to generate its own questions. To do this, we propose Self-Questioning Language Models (SQLM): an asymmetric self-play framework where a proposer is given the topic and generates a question for a solver, who tries to answer it. Both the proposer and solver are trained via reinforcement learning. The proposer receives a reward if the problem is not too easy or too difficult, and the solver receives a reward based on majority voting, a proxy for correctness in the absence of ground-truth answers. For coding, the proposer can instead generate unit tests which are used for verification. We study this asymmetric self-play framework on three benchmarks: three-digit multiplication, algebra problems from the OMEGA benchmark, and programming problems from Codeforces. By continually generating more interesting problems and attempting to solve them, language models can improve on downstream benchmarks without access to any curated training datasets.

cs.LG↗

arXiv2025

UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting

Recent advancements in deep learning have led to the development of Foundation Models (FMs) for weather forecasting, yet their ability to predict extreme weather events remains limited. Existing approaches either focus on general weather conditions or specialize in specific-type extremes, neglecting the real-world atmospheric patterns of diversified extreme events. In this work, we identify two key characteristics of extreme events: (1) the spectral disparity against normal weather regimes, and (2) the hierarchical drivers and geographic blending of diverse extremes. Along this line, we propose UniExtreme, a universal extreme weather forecasting foundation model that integrates (1) an Adaptive Frequency Modulation (AFM) module that captures region-wise spectral differences between normal and extreme weather, through learnable Beta-distribution filters and multi-granularity spectral aggregation, and (2) an Event Prior Augmentation (EPA) module which incorporates region-specific extreme event priors to resolve hierarchical extreme diversity and composite extreme schema, via a dual-level memory fusion network. Extensive experiments demonstrate that UniExtreme outperforms state-of-the-art baselines in both extreme and general weather forecasting, showcasing superior adaptability across diverse extreme scenarios.

cs.LG↗

arXiv2025

Data-Driven Discovery and Formulation Refines the Quasi-Steady Model of Flapping-Wing Aerodynamics

Insects control unsteady aerodynamic forces on flapping wings to navigate complex environments. While understanding these forces is vital for biology, physics, and engineering, existing evaluation methods face trade-offs: high-fidelity simulations are computationally or experimentally expensive and lack explanatory power, whereas theoretical models based on quasi-steady assumptions offer insights but exhibit low accuracy. To overcome these limitations and thus enhance the accuracy of quasi-steady aerodynamic models, we applied a data-driven approach involving discovery and formulation of previously overlooked critical mechanisms. Through selection from 5,000 candidate kinematic functions, we identified mathematical expressions for three key additional mechanisms -- the effect of advance ratio, effect of spanwise kinematic velocity, and rotational Wagner effect -- which had been qualitatively recognized but were not formulated. Incorporating these mechanisms considerably reduced the prediction errors of the quasi-steady model using the computational fluid dynamics results as the ground truth, both in hawkmoth forward flight (at high Reynolds numbers) and fruit fly maneuvers (at low Reynolds numbers). The data-driven quasi-steady model enables rapid aerodynamic analysis, serving as a practical tool for understanding evolutionary adaptations in insect flight and developing bio-inspired flying robots.

physics.flu-dyn↗

arXiv2025

TimeMachine: Fine-Grained Facial Age Editing with Identity Preservation

With the advancement of generative models, facial image editing has made significant progress. However, achieving fine-grained age editing while preserving personal identity remains a challenging task. In this paper, we propose TimeMachine, a novel diffusion-based framework that achieves accurate age editing while keeping identity features unchanged. To enable fine-grained age editing, we inject high-precision age information into the multi-cross attention module, which explicitly separates age-related and identity-related features. This design facilitates more accurate disentanglement of age attributes, thereby allowing precise and controllable manipulation of facial aging. Furthermore, we propose an Age Classifier Guidance (ACG) module that predicts age directly in the latent space, instead of performing denoising image reconstruction during training. By employing a lightweight module to incorporate age constraints, this design enhances age editing accuracy by modest increasing training cost. Additionally, to address the lack of large-scale, high-quality facial age datasets, we construct a HFFA dataset (High-quality Fine-grained Facial-Age dataset) which contains one million high-resolution images labeled with identity and facial attributes. Experimental results demonstrate that TimeMachine achieves state-of-the-art performance in fine-grained age editing while preserving identity consistency.

cs.CV↗

arXiv2025

Residual-based Efficient Bidirectional Diffusion Model for Image Dehazing and Haze Generation

Current deep dehazing methods only focus on removing haze from hazy images, lacking the capability to translate between hazy and haze-free images. To address this issue, we propose a residual-based efficient bidirectional diffusion model (RBDM) that can model the conditional distributions for both dehazing and haze generation. Firstly, we devise dual Markov chains that can effectively shift the residuals and facilitate bidirectional smooth transitions between them. Secondly, the RBDM perturbs the hazy and haze-free images at individual timesteps and predicts the noise in the perturbed data to simultaneously learn the conditional distributions. Finally, to enhance performance on relatively small datasets and reduce computational costs, our method introduces a unified score function learned on image patches instead of entire images. Our RBDM successfully implements size-agnostic bidirectional transitions between haze-free and hazy images with only 15 sampling steps. Extensive experiments demonstrate that the proposed method achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2025

Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2025

Light Baryon Spectroscopy at BESIII

The BESIII collaboration has collected large data samples in the center-of-mass energy range from 1.84 to 4.95 GeV. These data provide a low-background environment and suitable phase space for studying the spectroscopy of light baryons. In this article, we review the achievements of baryon spectroscopy studies by the BESIII collaboration. Most of the results are obtained through the partial wave analysis (PWA) method, with spin and parity well determined.

hep-ex↗