Search

Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion policies trained with analytic gradients from a differentiable simulator can be successfully transferred to the real world. Typically, simulators that offer informative gradients lack the physical accuracy needed for sim-to-real transfer, and vice-versa. A key factor in our success is a smooth contact model that combines informative gradients with physical accuracy, ensuring effective transfer of learned behaviors. To the best of our knowledge, this is the first time a real quadrupedal robot is able to locomote after training exclusively in a differentiable simulation., Comment: Presented at the CoRL 2024 Workshop 'Differentiable Optimization Everywhere'

Two-dimensional (2D) kagome lattice metals are interesting because they display flat electronic bands, Dirac points, Van Hove singularities, and can have interplay between charge density wave (CDW), magnetic order, and superconductivity. In kagome lattice antiferromagnet FeGe, a short-range CDW order was found deep within an antiferromagnetically ordered state, interacting with the magnetic order. Surprisingly, post-growth annealing of FeGe at 560$^{\circ}$C can suppress the CDW order while annealing at 320$^{\circ}$C induces a long-range CDW order, with the ability to cycle between the states repeatedly by annealing. Here we perform transport, neutron scattering, scanning transmission electron microscopy (STEM), and muon spin rotation ($\mu$SR) experiments to unveil the microscopic mechanism of the annealing process and its impact on magneto-transport, CDW, and magnetic properties of FeGe. We find that 560$^{\circ}$C annealing creates germanium vacancies uniformly distributed throughout the FeGe kagome lattice, which prevent the formation of Ge-Ge dimers necessary for the CDW order. Upon annealing at 320$^{\circ}$C, the system segregates into stoichiometric FeGe regions with long-range CDW order and regions with stacking faults that act as nucleation sites for the CDW. The presence or absence of CDW order greatly affects the anomalous Hall effect, incommensurate magnetic order, and spin-lattice coupling in FeGe, thus placing FeGe as the only known kagome lattice material with a tunable CDW and magnetic order, potentially useful for sensing and information transmission.

First-order Policy Gradient (FoPG) algorithms such as Backpropagation through Time and Analytical Policy Gradients leverage local simulation physics to accelerate policy search, significantly improving sample efficiency in robot control compared to standard model-free reinforcement learning. However, FoPG algorithms can exhibit poor learning dynamics in contact-rich tasks like locomotion. Previous approaches address this issue by alleviating contact dynamics via algorithmic or simulation innovations. In contrast, we propose guiding the policy search by learning a residual over a simple baseline policy. For quadruped locomotion, we find that the role of residual policy learning in FoPG-based training (FoPG RPL) is primarily to improve asymptotic rewards, compared to improving sample efficiency for model-free RL. Additionally, we provide insights on applying FoPG's to pixel-based local navigation, training a point-mass robot to convergence within seconds. Finally, we showcase the versatility of FoPG RPL by using it to train locomotion and perceptive navigation end-to-end on a quadruped in minutes.

Robot soccer, in its full complexity, poses an unsolved research challenge. Current solutions heavily rely on engineered heuristic strategies, which lack robustness and adaptability. Deep reinforcement learning has gained significant traction in various complex robotics tasks such as locomotion, manipulation, and competitive games (e.g., AlphaZero, OpenAI Five), making it a promising solution to the robot soccer problem. This paper introduces MARLadona. A decentralized multi-agent reinforcement learning (MARL) training pipeline capable of producing agents with sophisticated team play behavior, bridging the shortcomings of heuristic methods. Further, we created an open-source multi-agent soccer environment based on Isaac Gym. Utilizing our MARL framework and a modified a global entity encoder as our core architecture, our approach achieves a 66.8% win rate against HELIOS agent, which employs a state-of-the-art heuristic strategy. Furthermore, we provided an in-depth analysis of the policy behavior and interpreted the agent's intention using the critic network., Comment: Fixed redundant "-" in the title

In magnetically ordered insulators, elementary quasiparticles manifest as spin waves - collective motions of localized magnetic moments propagating through the lattice - observed via inelastic neutron scattering. In effective spin-1/2 systems where geometric frustrations suppress static magnetic order, spin excitation continua can emerge, either from degenerate classical spin ground states or from entangled quantum spins characterized by emergent gauge fields and deconfined fractionalized excitations. Comparing the spin Hamiltonian with theoretical models can unveil the microscopic origins of these zero-field spin excitation continua. Here, we use neutron scattering to study spin excitations of the two-dimensional (2D) triangular-lattice effective spin-1/2 antiferromagnet CeMgAl11O19. Analyzing the spin waves in the field-polarized ferromagnetic state, we find that the spin Hamiltonian is close to an exactly solvable 2D triangular-lattice XXZ model, where degenerate 120$^\circ$ ordered ground states - umbrella states - develop in the zero temperature limit. We then find that the observed zero-field spin excitation continuum matches the calculated ensemble of spin waves from the umbrella state manifold, and thus conclude that CeMgAl11O19 is the first example of an exactly solvable spin liquid on a triangular lattice where the spin excitation continuum arises from the ground state degeneracy., Comment: 11 pages, 5 figures

The model by Hu and Cai [Phys. Rev. Lett., Vol. 111(13) (2013)1 ] describes the self-organization of vascular networks for transport of fluids from source to sinks. Diameters, and thereby conductances, of vessel segments evolve so as to minimize a cost functional E. The cost is the trade-off between the power required for pumping the fluid and the energy consumption for vessel maintenance. The model has been used to show emergence of cyclic structures in the presence of locally fluctuating demand, i.e. non-constant net flow at sink nodes. Under rapid and sufficiently large fluctuations, the dynamics exhibits bistability of tree-like and cyclic network structures. We compare these solutions in terms of the cost functional E. Close to the saddle-node bifurcation giving rise to the cyclic solutions, we find a parameter regime where the tree-like solution rather than the cyclic solution is cost-optimal. Further increase of fluctuation amplitude then leads to an additional transition at which the cyclic solution becomes optimal. The findings hold both in a small system of one source and two sinks and in an empirical vascular network with hundreds of sinks. In the small system, we further analyze the case of slower fluctuations, i.e., on the same time scale as network adaptation. We find that the noisy dynamics settles around the cyclic structures even when these structures are not cost-optimal.

Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.

The OpenMP API offers both task-based and data-parallel concepts to scientific computing. While it provides descriptive and prescriptive annotations, it is in many places deliberately unspecific how to implement its annotations. As the predominant OpenMP implementations share design rationales, they introduce "quasi-standards how certain annotations behave. By means of a task-based astrophysical simulation code, we highlight situations where this "quasi-standard" reference behaviour introduces performance flaws. Therefore, we propose prescriptive clauses to constrain the OpenMP implementations. Simulated task traces uncover the clauses' potential, while a discussion of their realization highlights that they would manifest in rather incremental changes to any OpenMP runtime supporting task priorities.

The use of steganography to transmit secret data is becoming increasingly common in security products and malware today. Despite being extremely popular, PDF files are not often the focus of steganography research, as most applications utilize digital image, audio, and video files as their cover data. However, the PDF file format is promising for usage in medium-capacity steganography applications. In this paper, we present a novel PDF steganography algorithm based upon least-significant bit insertion into the real-valued operands of PDF stream operators. Where prior research has only considered a small subset of these operators, we take an extensive look at all the possible operators defined in the Adobe PDF standard to evaluate their usability in our steganography algorithm. We also provide a case study which embeds malware into a given cover PDF document.

The emergence of differentiable simulators enabling analytic gradient computation has motivated a new wave of learning algorithms that hold the potential to significantly increase sample efficiency over traditional Reinforcement Learning (RL) methods. While recent research has demonstrated performance gains in scenarios with comparatively smooth dynamics and, thus, smooth optimization landscapes, research on leveraging differentiable simulators for contact-rich scenarios, such as legged locomotion, is scarce. This may be attributed to the discontinuous nature of contact, which introduces several challenges to optimizing with analytic gradients. The purpose of this paper is to determine if analytic gradients can be beneficial even in the face of contact. Our investigation focuses on the effects of different soft and hard contact models on the learning process, examining optimization challenges through the lens of contact simulation. We demonstrate the viability of employing analytic gradients to learn physically plausible locomotion skills with a quadrupedal robot using Short-Horizon Actor-Critic (SHAC), a learning algorithm leveraging analytic gradients, and draw a comparison to a state-of-the-art RL algorithm, Proximal Policy Optimization (PPO), to understand the benefits of analytic gradients.

Motion planning is an essential part of autonomous mobile platforms. A good pipeline should be modular enough to handle different vehicles, environments, and perception modules. The planning process has to cope with all the different modalities and has to have a modular and flexible design. But most importantly, it has to be safe and robust. In this paper, we want to present our motion planning pipeline with particle swarm optimization (PSO) at its core. This solution is independent of the vehicle type and has a clear and simple-to-implement interface for perception modules. Moreover, the approach stands out for being easily adaptable to new scenarios. Parallel calculation allows for fast planning cycles. Following the principles of PSO, the trajectory planer first generates a swarm of initial trajectories that are optimized afterward. We present the underlying control space and inner workings. Finally, the application to real-world automated driving is shown in the evaluation with a deeper look at the modeling of the cost function. The approach is used in our automated shuttles that have already driven more than 3.500 km safely and entirely autonomously in sub-urban everyday traffic.

The discovery of the charge density wave order (CDW) within a magnetically ordered phase in the kagome lattice FeGe has provided a promising platform to investigate intertwined degrees of freedom in kagome lattices. Recently, a method based on post-annealing has been suggested to manipulate the CDW order in kagome FeGe towards either long-range or suppressed orders. Here, we provide a comprehensive comparison of the experimentally measured electronic structures of FeGe crystals that have undergone different post-annealing procedures and demonstrate the remarkable effectiveness on tuning the CDW gap without strong perturbation on the underlying electronic structure. Moreover, we observe an additional low temperature transition that only appears in crystals with a long-range CDW order, which we associate with a lattice-spin coupled order. Our work indicates a likely strong sensitivity of the CDW order to disorder in FeGe, and provides evidence for strong coupling between the electronic, lattice, and spin degrees of freedom in this kagome magnet.

Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired transformation invariances and suffer from motion artifacts. For instance, a quadruped may exhibit different gaits when commanded to move forward or backward, even though it is symmetrical about its torso. This issue becomes further pronounced in high-dimensional or complex environments, where DRL methods are prone to local optima and fail to explore regions of the state space equally. Past methods on encouraging symmetry for robotic tasks have studied this topic mainly in a single-task setting, where symmetry usually refers to symmetry in the motion, such as the gait patterns. In this paper, we revisit this topic for goal-conditioned tasks in robotics, where symmetry lies mainly in task execution and not necessarily in the learned motions themselves. In particular, we investigate two approaches to incorporate symmetry invariance into DRL -- data augmentation and mirror loss function. We provide a theoretical foundation for using augmented samples in an on-policy setting. Based on this, we show that the corresponding approach achieves faster convergence and improves the learned behaviors in various challenging robotic tasks, from climbing boxes with a quadruped to dexterous manipulation., Comment: M. Mittal and N. Rudin contributed equally. Accepted for ICRA 2024

The reduction in sea ice cover with Arctic warming facilitates the transit of ships through routes that are remarkably shorter than the traditional shipping routes. Automatic Identification System (AIS), ideally designed to avoid vessel collisions, transmits on vessel navigation information (currently 27 types of messages) such as name, position or speed, is a powerful data source to monitor the progress of Arctic shipping as the ice cover decreases. Based on the analysis of an online platform collecting shipping AIS data, we quantified the spatial distribution of shipping through the Arctic Ocean, its intensity and the temporal evolution, in relation to the area released by the sea ice area. Shipping through the Arctic Ocean is distributed spatially following a heavy-tailed distribution, implying heavy traffic through a limited Arctic area, with an exponent that depends on the vessel category. Fishing is the category with the largest spatial spread, with the width of shipping routes correlated with the proximal sea ice area. The time evolution of these routes is characterized by increasing extended periods of shipping activity through the year. AIS data offers valuable information on the activity of the international fleet worldwide. In the context of the new international agreements, it is a valuable source to monitor shipping, fishing and the potential impact in marine life among other aspects. Here we have focused on the Arctic shipping in recent years, which is rapidly growing, particularly around the Northeastern and Northwest Passage coastal routes, providing an opportunity for the design of shorter shipping routes and reduced greenhouse gas emissions from transport of goods, but at a risk of impacts on the Arctic ecosystem.

We generalise the geometric analysis of square fishnet integrals in two dimensions to the case of hexagonal fishnets with three-point vertices. Our results support the conjecture that fishnet Feynman integrals in two dimensions, together with their associated geometry, are completely fixed by their Yangian and permutation symmetries. As a new feature for the hexagonal fishnets, the star-triangle identity introduces an ambiguity in the graph representation of a given Feynman integral. This translates into a map between different geometric interpretations attached to a graph. We demonstrate explicitly how these fishnet integrals can be understood as Calabi-Yau varieties, whose Picard-Fuchs ideals are generated by the Yangian over the conformal algebra. In analogy to elliptic curves, which represent the simplest examples of fishnet integrals with four-point vertices, we find that the simplest examples of three-point fishnets correspond to Picard curves with natural generalisations at higher loop orders., Comment: 51 pages, v2: section 3.5 improved, typos corrected

In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across various domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot., Comment: Video: https://youtu.be/Ec6ar8BVJh4

Understanding the magnetoresistance (MR) of a magnetic material forms the basis for uncovering the orbital mechanisms and charge-spin interactions in the system. Although the parent state of iron-based high-temperature superconductors, including $BaFe_2As_2$, exhibits unusual electron transport properties resulting from spin and charge correlations, there is still valuable insight to be gained by understanding the in-plane MR effect due to twin domains in the orthorhombic antiferromagnetic (AF) ordered state. Here, we study the in-plane magnetoresistance anisotropy in detwinned $BaFe_2As_2$ and compare the results to the non-magnetic Ni-doped sample. We find that in the antiferromagnetically ordered state, $BaFe_2As_2$ exhibits anisotropic MR that becomes large at low temperatures and high fields. Both transverse and longitudinal MRs are highly anisotropic and dependent on the field and current orientations. These results cannot be fully explained by calculations considering only the anisotropic Fermi surface. Instead, the spin orientation of the ordered moment also affects the MR effect, suggesting the presence of a large charge-spin interaction in $BaFe_2As_2$ that is not present in the Ni-doped material.

The exponential of an operator or matrix is widely used in quantum theory, but it sometimes can be a challenge to evaluate. For non-commutative operators ${\bf X}$ and ${\bf Y}$, according to the Campbell-Baker-Hausdorff-Dynkin theorem, ${\rm e}^{{\bf X}+{\bf Y}}$ is not equivalent to ${\rm e}^{\bf X}{\rm e}^{\bf Y}$, but is instead given by the well-known infinite series formula. For a Lie algebra of a basis of three operators $\{{\bf X,Y,Z}\}$, such that $[{\bf X}, {\bf Y}] = \kappa{\bf Z}$ for scalar $\kappa$ and cyclic permutations, here it is proven that ${\rm e}^{a{\bf X}+b{\bf Y}}$ is equivalent to ${\rm e}^{p{\bf Z}}{\rm e}^{q{\bf X}}{\rm e}^{-p{\bf Z}}$ for scalar $p$ and $q$. Extensions for ${\rm e}^{a{\bf X}+b{\bf Y}+c{\bf Z}}$ are also provided. This method is useful for the dynamics of atomic and molecular nuclear and electronic spins in constant and oscillatory transverse magnetic and electric fields., Comment: 6 pages,0 figures

The high-precision description of black hole scattering in classical general relativity using the post-Minkowskian (PM) expansion requires the evaluation of single-scale Feynman integrals at increasing loop orders. Up to 4PM, the scattering angle and the impulse are expressible in terms of polylogarithmic functions and Calabi-Yau (CY) two-fold periods. As in QFT, periods of higher dimensional CY n-folds are expected at higher PM order. We find at 5PM in the dissipative leading order self-force sector (5PM-1SF) that the only non-polylogarithmic functions are the K3 periods encountered before and the ones of a new hypergeometric CY three-fold. In the 5PM-2SF sector further CY two- and three-fold periods appear. Griffiths transversality of the CY period motives allows to transform the differential equations for the master integrals into $\epsilon$-factorized form and to solve them in terms of a well controlled function space, as we demonstrate in the 5PM-1SF sector., Comment: 11 pages, 2 tables, 2 figures v2: typos corrected, added reference [76], v3: PRD published version; change in title

In previous work, we used new mathematical relations between Gopakumar-Vafa (GV) invariants and rank 0 Donaldson-Thomas (DT) invariants to determine the first few terms in the generating series of Abelian D4-D2-D0 indices for a class of compact one-parameter Calabi-Yau threefolds. This allowed us to obtain striking checks of S-duality, namely the prediction that these series should be vector-valued weakly holomorphic modular forms under $SL(2,\mathbb{Z})$. In this work, we extend this analysis to the case of D4-D2-D0 indices with two units of D4-brane charge, where S-duality instead predicts that the corresponding generating series should be mock modular with a specific shadow. For the degree 10 hypersurface in weighted projective space $\mathbb{P}_{5,2,1,1,1}$, and the degree 8 hypersurface in $\\mathbb{P}_{4,1,1,1,1}$, where GV invariants can be computed to sufficiently high genus, we find that the first few terms indeed match a unique mock modular form with the required properties, which we determine explicitly. Turning the argument around, we obtain new boundary conditions on the holomorphic ambiguity of the topological string amplitude, which in principle allow to determine it completely up to genus 95 and 112, respectively, i.e. almost twice the maximal genus obtainable using gap and ordinary Castelnuovo vanishing conditions., Comment: 34 pages

We use transport measurements to determine the in-plane anisotropy of the upper critical field Hc2 in detwinned superconducting Ba(Fe1-xMx)2As2 (M = Co, Ni) single crystals. In previous measurements on twinned single crystals, the charge carrier doping dependence (x) of the upper critical field anisotropy for fields along the inter-planar (c-axis) and in-plane field directions was found to increase in the overdoped regime. For underdoped samples, which exhibit a spin nematic phase below the tetragonal to orthorhombic structural transition temperature Ts , we find that Hc2 along the a-axis is considerably lower than that along the b-axis. The upper critical field anisotropy disappears in the over-doped regime when the system becomes tetragonal. By combining these results with inelastic neutron scattering studies of spin excitations, and angle-resolved photoemission spectroscopy, we conclude that superconductivity in under-doped iron pnictides is orbital selective - with a dominant contribution from electrons with the dyz orbital character and being intimately associated with spin excitations.

Most of the widely used quantum programming languages and libraries are not designed for the tightly coupled nature of hybrid quantum-classical algorithms, which run on quantum resources that are integrated on-premise with classical HPC infrastructure. We propose a programming model using the API provided by OpenMP to target quantum devices, which provides an easy-to-use and efficient interface for HPC applications to utilize quantum compute resources. We have implemented a variational quantum eigensolver using the programming model, which has been tested using a classical simulator. We are in the process of testing on the quantum resources hosted at the Leibniz Supercomputing Centre (LRZ)., Comment: Poster extended abstract for Supercomputing 2023 (SC23)

We analyse the family of Calabi-Yau varieties attached to four-point fishnet integrals in two dimensions. We find that the Picard-Fuchs operators for fishnet integrals are exterior powers of the Picard-Fuchs operators for ladder integrals. This implies that the periods of the Calabi-Yau varieties for fishnet integrals can be written as determinants of periods for ladder integrals. The representation theory of the geometric monodromy group plays an important role in this context. We then show how the determinant form of the periods immediately leads to the well-known Basso-Dixon formula for four-point fishnet integrals in two dimensions. Notably, the relation to Calabi-Yau geometry implies that the volume is also expressible via a determinant formula of Basso-Dixon type. Finally, we show how the fishnet integrals can be written in terms of iterated integrals naturally attached to the Calabi-Yau varieties., Comment: 42 pages, v2: typos corrected, references updated

Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical constraints during training. While high-fidelity simulations provide significant benefits, they often bypass these essential physical limitations. In this paper, we experiment with the Constrained Markov Decision Process (CMDP) framework instead of the conventional unconstrained RL for robotic applications. We perform a comparative study of different constrained policy optimization algorithms to identify suitable methods for practical implementation. Our robot experiments demonstrate the critical role of incorporating physical constraints, yielding successful sim-to-real transfers, and reducing operational errors on physical systems. The CMDP formulation streamlines the training process by separately handling constraints from rewards. Our findings underscore the potential of constrained RL for the effective development and deployment of learned controllers in robotics.

Spontaneous symmetry breaking-the phenomenon where an infinitesimal perturbation can cause the system to break the underlying symmetry-is a cornerstone concept in the understanding of interacting solid-state systems. In a typical series of temperature-driven phase transitions, higher temperature phases are more symmetric due to the stabilizing effect of entropy that becomes dominant as the temperature is increased. However, the opposite is rare but possible when there are multiple degrees of freedom in the system. Here, we present such an example of a symmetry-ascending phenomenon in a magnetic kagome metal FeGe by utilizing neutron Larmor diffraction and Raman spectroscopy. In the paramagnetic state at 460K, we confirm that the crystal structure is indeed hexagonal kagome lattice. On cooling to TN, the crystal structure changes from hexagonal to monoclinic with in-plane lattice distortions on the order of 10^(-4) and the associated splitting of the double degenerate phonon mode of the pristine kagome lattice. Upon further cooling to TCDW, the kagome lattice shows a small negative thermal expansion, and the crystal structure becomes more symmetric gradually upon further cooling. Increasing the crystalline symmetry upon cooling is unusual, it originates from an extremely weak structural instability that coexists and competes with the CDW and magnetic orders. These observations are against the expectations for a simple model with a single order parameter, hence can only be explained by a Landau free energy expansion that takes into account multiple lattice, charge, and spin degrees of freedom. Thus, the determination of the crystalline lattice symmetry as well as the unusual spin-lattice coupling is a first step towards understanding the rich electronic and magnetic properties of the system and sheds new light on intertwined orders where the lattice degree of freedom is no longer dominant., Comment: 20 pages with 10 figures, replaced with journal version

The ability to reversibly toggle between two distinct states in a non-volatile method is important for information storage applications. Such devices have been realized for phase-change materials, which utilizes local heating methods to toggle between a crystalline and an amorphous state with distinct electrical properties. To expand such kind of switching between two topologically distinct phases requires non-volatile switching between two crystalline phases with distinct symmetries. Here we report the observation of reversible and non-volatile switching between two stable and closely-related crystal structures with remarkably distinct electronic structures in the near room temperature van der Waals ferromagnet Fe$_{5-\delta}$GeTe$_2$. From a combination of characterization techniques we show that the switching is enabled by the ordering and disordering of an Fe site vacancy that results in distinct crystalline symmetries of the two phases that can be controlled by a thermal annealing and quenching method. Furthermore, from symmetry analysis as well as first principle calculations, we provide understanding of the key distinction in the observed electronic structures of the two phases: topological nodal lines compatible with the preserved global inversion symmetry in the site-disordered phase, and flat bands resulting from quantum destructive interference on a bipartite crystaline lattice formed by the presence of the site order as well as the lifting of the topological degeneracy due to the broken inversion symmetry in the site-ordered phase. Our work not only reveals a rich variety of quantum phases emergent in the metallic van der Waals ferromagnets due to the presence of site ordering, but also demonstrates the potential of these highly tunable two-dimensional magnets for memory and spintronics applications.