arXiv subjects

Zihan Zhou

Publications and source records attributed to Zihan Zhou.

At least 109 records · Page 6Linked to original sources

arXiv2024

Research on the Proximity Relationships of Psychosomatic Disease Knowledge Graph Modules Extracted by Large Language Models

As social changes accelerate, the incidence of psychosomatic disorders has significantly increased, becoming a major challenge in global health issues. This necessitates an innovative knowledge system and analytical methods to aid in diagnosis and treatment. Here, we establish the ontology model and entity types, using the BERT model and LoRA-tuned LLM for named entity recognition, constructing the knowledge graph with 9668 triples. Next, by analyzing the network distances between disease, symptom, and drug modules, it was found that closer network distances among diseases can predict greater similarities in their clinical manifestations, treatment approaches, and psychological mechanisms, and closer distances between symptoms indicate that they are more likely to co-occur. Lastly, by comparing the proximity d and proximity z score, it was shown that symptom-disease pairs in primary diagnostic relationships have a stronger association and are of higher referential value than those in diagnostic relationships. The research results revealed the potential connections between diseases, co-occurring symptoms, and similarities in treatment strategies, providing new perspectives for the diagnosis and treatment of psychosomatic disorders and valuable information for future mental health research and practice.

cs.AI↗

arXiv2024

From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach

In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods which rely on task-specific data representations and/or algorithms. Specifically, on the input side, we simply treat the 2D CAD drawing as a raster image, regardless of its original format, and encode the image with a standard ViT model. We show that such an encoding scheme achieves competitive performance against existing methods that operate on vector-graphics inputs, while imposing substantially fewer restrictions on the 2D drawings. On the output side, our method auto-regressively predicts a general-purpose language describing 3D parametric models in text form. Compared to other sequence modeling methods for CAD which use domain-specific sequence representations with fixed-size slots, our text-based representation is more flexible, and can be easily extended to arbitrary geometric entities and semantic or functional properties. Experimental results on a large-scale dataset of cabinet models demonstrate the effectiveness of our method.

cs.CV↗

arXiv2024

Records from the S-Matrix Marathon: Gravitational Physics from Scattering Amplitudes

These lecture notes explain how classical gravitational physics emerges from scattering amplitudes. We emphasize the role of different kinematic regimes in probing various aspects of bound and unbound problems, as illustrated by the Hydrogen atom example. Classical predictions of General Relativity, such as the Shapiro time delay and perihelion precession, emerge from these considerations. We also explain a number of recent approaches to probing black hole physics from the perspective of amplitudes, including applications of worldline effective field theory in astrophysics, predictions of gravitational waveforms, and the hierarchical three-body problem. These notes are based on a series of lectures held during the S-Matrix Marathon workshop at the Institute for Advanced Study on 11--22 March 2024.

hep-th↗

arXiv2024

Investigating tidal heating in neutron stars via gravitational Raman scattering

We present a scattering amplitude formalism to study the tidal heating effects of nonspinning neutron stars incorporating both worldline effective field theory and relativistic stellar perturbation theory. In neutron stars, tidal heating arises from fluid viscosity due to various scattering processes in the interior. It also serves as a channel for the exchange of energy and angular momentum between the neutron star and its environment. In the interior of the neutron star, we first derive two master perturbation equations that capture fluid perturbations accurate to linear order in frequency. Remarkably, these equations receive no contribution from bulk viscosity due to a peculiar adiabatic incompressibility which arises in stellar fluid for non-barotropic perturbations. In the exterior, the metric perturbations reduce to the Regge-Wheeler (RW) equation which we solve using the analytical Mano-Suzuki-Takasugi (MST) method. We compute the amplitude for gravitational waves scattering off a neutron star, also known as gravitational Raman scattering. From the amplitude, we obtain expressions for the electric quadrupolar static Love number and the leading dissipation number to all orders in compactness. We then compute the leading dissipation number for various realistic equation-of-state(s) and estimate the change in the number of gravitational wave cycles due to tidal heating during inspiral in the LIGO-Virgo-KAGRA (LVK) band.

gr-qc↗

arXiv2024

Sample Efficient Bayesian Learning of Causal Graphs from Interventions

Causal discovery is a fundamental problem with applications spanning various areas in science and engineering. It is well understood that solely using observational data, one can only orient the causal graph up to its Markov equivalence class, necessitating interventional data to learn the complete causal graph. Most works in the literature design causal discovery policies with perfect interventions, i.e., they have access to infinite interventional samples. This study considers a Bayesian approach for learning causal graphs with limited interventional samples, mirroring real-world scenarios where such samples are usually costly to obtain. By leveraging the recent result of Wienöbst et al. (2023) on uniform DAG sampling in polynomial time, we can efficiently enumerate all the cut configurations and their corresponding interventional distributions of a target set, and further track their posteriors. Given any number of interventional samples, our proposed algorithm randomly intervenes on a set of target vertices that cut all the edges in the graph and returns a causal graph according to the posterior of each target set. When the number of interventional samples is large enough, we show theoretically that our proposed algorithm will return the true causal graph with high probability. We compare our algorithm against various baseline methods on simulated datasets, demonstrating its superior accuracy measured by the structural Hamming distance between the learned DAG and the ground truth. Additionally, we present a case study showing how this algorithm could be modified to answer more general causal questions without learning the whole graph. As an example, we illustrate that our method can be used to estimate the causal effect of a variable that cannot be intervened.

cs.LG↗

arXiv2024

SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation

Robot learning has proven to be a general and effective technique for programming manipulators. Imitation learning is able to teach robots solely from human demonstrations but is bottlenecked by the capabilities of the demonstrations. Reinforcement learning uses exploration to discover better behaviors; however, the space of possible improvements can be too large to start from scratch. And for both techniques, the learning difficulty increases proportional to the length of the manipulation task. Accounting for this, we propose SPIRE, a system that first uses Task and Motion Planning (TAMP) to decompose tasks into smaller learning subproblems and second combines imitation and reinforcement learning to maximize their strengths. We develop novel strategies to train learning agents when deployed in the context of a planning system. We evaluate SPIRE on a suite of long-horizon and contact-rich robot manipulation problems. We find that SPIRE outperforms prior approaches that integrate imitation learning, reinforcement learning, and planning by 35% to 50% in average task performance, is 6 times more data efficient in the number of human demonstrations needed to train proficient agents, and learns to complete tasks nearly twice as efficiently. View https://sites.google.com/view/spire-corl-2024 for more details.

cs.RO↗

arXiv2024

MicroDreamer: Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction

Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and the limitation of optimization confined to latent space. This paper introduces score-based iterative reconstruction (SIR), an efficient and general algorithm mimicking a differentiable 3D reconstruction process to reduce the NFEs and enable optimization in pixel space. Given a single set of images sampled from a multi-view score-based diffusion model, SIR repeatedly optimizes 3D parameters, unlike the single-step optimization in SDS. With other improvements in training, we present an efficient approach called MicroDreamer that generally applies to various 3D representations and 3D generation tasks. In particular, MicroDreamer is 5-20 times faster than SDS in generating neural radiance field while retaining a comparable performance and takes about 20 seconds to create meshes from 3D Gaussian splatting on a single A100 GPU, halving the time of the fastest optimization-based baseline DreamGaussian with significantly superior performance compared to the measurement standard deviation. Our code is available at https://github.com/ML-GSAI/MicroDreamer.

cs.CV↗

arXiv2024

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information when splitting the document, which can lead the model to produce incomplete or incorrect answers based on the segmented texts. Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict. We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experimental results demonstrate that LLM$\times$MapReduce can outperform representative open-source and commercial long-context LLMs, and is applicable to several different models.

cs.CL↗

arXiv2024

A Mathematical Theory of Hyper-simplex Fractal Network for Blockchain: Part I

Blockchain technology holds promise for Web 3.0, but scalability remains a critical challenge. Here, we present a mathematical theory for a novel blockchain network topology based on fractal N-dimensional simplexes. This Hyper-simplex fractal network folds one-dimensional data blocks into geometric shapes, reflecting both underlying and overlaying network connectivities. Our approach offers near-infinite scalability, accommodating trillions of nodes while maintaining efficiency. We derive the mathematical foundations for generating and describing these network topologies, proving key properties such as node count, connectivity patterns, and fractal dimension. The resulting structure facilitates a hierarchical consensus mechanism and enables deterministic address mapping for rapid routing. This theoretical framework lays the groundwork for next-generation blockchain architectures, potentially revolutionizing large-scale decentralized systems. The Part I work was conducted between March and September 2024.

cs.NI↗

arXiv2024

BE-RAN: Blockchain-enabled Open RAN for 6G with DID and Privacy-Preserving Communication

As 6G networks evolve towards a synergistic system of Communication, Sensing, and Computing, Radio Access Networks become more distributed, necessitating robust end-to-end authentication. We propose Blockchain-enabled Radio Access Networks, a novel decentralized RAN architecture enhancing security, privacy, and efficiency in authentication processes. BE-RAN leverages distributed ledger technology to establish trust, offering user-centric identity management, enabling mutual authentication, and facilitating on-demand point-to-point inter-network elements and UE-UE communication with accountable logging and billing service add-on for public network users, all without relying on centralized authorities. We envision a thoroughly decentralized RAN model and propose a privacy-preserving P2P communication approach that complements existing security measures while supporting the CSC paradigm. Results demonstrate BE-RAN significantly reduces communication and computation overheads, enhances privacy through decentralized identity management, and facilitates CSC integration, advancing towards more efficient and secure 6G networks.

cs.CR↗

arXiv2024

Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications

Safe reinforcement learning tasks are a challenging domain despite being very common in the real world. The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. To address this issue, we first describe the problem with a stronger Uniformly Constrained MDP (UCMDP) model where we impose constraints on all reachable states; we then propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic, as a solution to the Lagrangian dual of a UCMDP. We benchmark Objective Suppression in two multi-constraint safety domains, including an autonomous driving domain where any incorrect behavior can lead to disastrous consequences. On the driving domain, we evaluate on open source and proprietary data and evaluate transfer to a real autonomous fleet. Empirically, we demonstrate that our proposed method, when combined with existing safe RL algorithms, can match the task reward achieved by baselines with significantly fewer constraint violations.

cs.LG↗

arXiv2024

From Time-inconsistency to Time-consistency for Optimal Stopping Problems

For optimal stopping problems with time-inconsistent preference, we measure the inherent level of time-inconsistency by taking the time needed to turn the naive strategies into the sophisticated ones. In particular, when in a repeated experiment the naive agent can observe her actual sequence of actions which are inconsistent with what she has planned at the initial time, she then chooses her immediate action based on the observations on her later actual behavior. The procedure is repeated until her actual sequence of actions are consistent with her plan at any time. We show that for the preference value of cumulative prospect theory, in which the time-inconsistency is due to the probability distortion, the higher the degree of probability distortion, the more severe the level of time-inconsistency, and the more time required to turn the naive strategies into the sophisticated ones.

econ.GN↗

arXiv2024

Decide: Knowledge-Based Version Incompatibility Detection in Deep Learning Stacks

Version incompatibility issues are prevalent when reusing or reproducing deep learning (DL) models and applications. Compared with official API documentation, which is often incomplete or out-of-date, Stack Overflow (SO) discussions possess a wealth of version knowledge that has not been explored by previous approaches. To bridge this gap, we present Decide, a web-based visualization of a knowledge graph that contains 2,376 version knowledge extracted from SO discussions. As an interactive tool, Decide allows users to easily check whether two libraries are compatible and explore compatibility knowledge of certain DL stack components with or without the version specified. A video demonstrating the usage of Decide is available at https://youtu.be/wqPxF2ZaZo0.

cs.SE↗

arXiv2024

Black Hole Perturbation Theory Meets CFT$_2$: Kerr Compton Amplitudes from Nekrasov-Shatashvili Functions

We present a novel study of Kerr Compton amplitudes in a partial wave basis in terms of the Nekrasov-Shatashvili (NS) function of the confluent Heun equation (CHE). Remarkably, NS-functions enjoy analytic properties and symmetries that are naturally inherited by the Compton amplitudes. Based on this, we characterize the analytic dependence of the Compton phase-shift in the Kerr spin parameter and provide a direct comparison to the standard post-Minkowskian (PM) perturbative approach within General Relativity (GR). We also analyze the universal large frequency behavior of the relevant characteristic exponent of the CHE -- also known as the renormalized angular momentum -- and find agreement with numerical computations. Moreover, we discuss the analytic continuation in the harmonics quantum number $\ell$ of the partial wave, and show that the limit to the physical integer values commutes with the PM expansion of the observables. Finally, we obtain the contributions to the tree level, point-particle, gravitational Compton amplitude in a covariant basis through $O(a_{\text{BH}}^8)$, without the need to take the super-extremal limit for Kerr spin.

hep-th↗

arXiv2024

Light-induced fictitious magnetic fields for quantum storage in cold atomic ensembles

In this work, we have demonstrated that optically generated fictitious magnetic fields can be utilized to extend the lifetime of quantum memories in cold atomic ensembles. All the degrees of freedom of an AC Stark shift such as polarization, spatial profile, and temporal waveform can be readily controlled in a precise manner. Temporal fluctuations over several experimental cycles, and spatial inhomogeneities along a cold atomic gas have been compensated by an optical beam. The advantage of the use of fictitious magnetic fields for quantum storage stems from the speed and spatial precision that these fields can be synthesized. Our simple and versatile technique can find widespread application in coherent pulse and single-photon storage in any atomic species.

quant-ph↗

arXiv2024

BeerReview: A Blockchain-enabled Peer Review Platform

In an era of increasing concerns over intellectual property rights, traditional peer review systems face challenges including plagiarism, malicious attacks, and unauthorized data access. BeerReview, a blockchain-enabled peer review platform, offers a robust solution, enabling experts and scholars to participate actively in the review process without concerns about plagiarism or security threats. Following the completion of its alpha testing, BeerReview demonstrates the potential for expanded deployment. This platform offers improved convenience and more robust intellectual property protection within the peer review process with open source initiative.

cs.DC↗

arXiv2024

FlexiDreamer: Single Image-to-3D Generation with FlexiCubes

3D content generation has wide applications in various fields. One of its dominant paradigms is by sparse-view reconstruction using multi-view images generated by diffusion models. However, since directly reconstructing triangle meshes from multi-view images is challenging, most methodologies opt to an implicit representation (such as NeRF) during the sparse-view reconstruction and acquire the target mesh by a post-processing extraction. However, the implicit representation takes extensive time to train and the post-extraction also leads to undesirable visual artifacts. In this paper, we propose FlexiDreamer, a novel framework that directly reconstructs high-quality meshes from multi-view generated images. We utilize an advanced gradient-based mesh optimization, namely FlexiCubes, for multi-view mesh reconstruction, which enables us to generate 3D meshes in an end-to-end manner. To address the reconstruction artifacts owing to the inconsistencies from generated images, we design a hybrid positional encoding scheme to improve the reconstruction geometry and an orientation-aware texture mapping to mitigate surface ghosting. To further enhance the results, we respectively incorporate eikonal and smooth regularizations to reduce geometric holes and surface noise. Our approach can generate high-fidelity 3D meshes in the single image-to-3D downstream task with approximately 1 minute, significantly outperforming previous methods.

cs.CV↗

arXiv2024

Bring the Heat: Tidal Heating Constraints for Black Holes and Exotic Compact Objects from the LIGO-Virgo-KAGRA Data

We present the first constraints on tidal heating for the binary systems detected in the LIGO-Virgo-KAGRA (LVK) gravitational wave data. Tidal heating, also known as tidal dissipation, characterizes the viscous nature of an astrophysical body and provides a channel for exchanging energy and angular momentum with the tidal environment. Using the worldline effective field theory formalism, we introduce a physically motivated and easily interpretable parametrization of tidal heating valid for an arbitrary compact astrophysical object. We then derive the imprints of the spin-independent and linear-in-spin tidal heating effects of generic binary components on the waveform phases and amplitudes of quasi-circular orbits. Notably, the mass-weighted spin-independent tidal heating coefficient derived in this work, $\mathcal{H}_0$, is the dissipative analog of the tidal Love number. We constrain the tidal heating coefficients using the public LVK O1-O3 data. Our parameter estimation study includes two separate analyses: the first treats the catalog of binary events as binary black holes (BBH), while the second makes no assumption about the nature of the binary constituents and can therefore be interpreted as constraints for exotic compact objects. In the former case, we combine the posterior distributions of the individual BBH events and obtain a joint constraint of $-13 < \mathcal{H}_0 < 20$ at the $90\%$ credible interval for the BBH population. This translates into a bound on the fraction of the emitted gravitational wave energy lost due to tidal heating (or gained due to radiation enhancement effects) at $|ΔE_H/ΔE_{\infty}|\lesssim 3\cdot 10^{-3}$. Our work provides the first robust framework for deriving and measuring tidal heating effects in merging binary systems, demonstrating its potential as a powerful probe of the nature of binary constituents and tests of new physics.

gr-qc↗