Search

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 Wien\"obst 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., Comment: To appear in Proceedings of NeurIPS 24

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods against a wide range of image editing techniques, including image regeneration, global editing, local editing, and image-to-video generation. Through extensive evaluations of eleven representative watermarking methods against prevalent editing techniques, we demonstrate that most methods fail to detect watermarks after such edits. To address this limitation, we propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques while maintaining high image quality. Our approach involves two key innovations: (1) we analyze the frequency characteristics of image editing and identify that blurring distortions exhibit similar frequency properties, which allows us to use them as surrogate attacks during training to bolster watermark robustness; (2) we leverage a large-scale pretrained diffusion model SDXL-Turbo, adapting it for the watermarking task to achieve more imperceptible and robust watermark embedding. Experimental results show that our method achieves outstanding watermarking performance under various image editing techniques, outperforming existing methods in both image quality and robustness. Code is available at https://github.com/Shilin-LU/VINE.

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., Comment: Conference on Robot Learning (CoRL) 2024

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., Comment: Work in Progress. Code: https://github.com/thunlp/LLMxMapReduce

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.

We use Fisher information theory to forecast the bounds on the finite-size effects of astrophysical compact objects with next-generation gravitational wave detectors, including the ground-based Cosmic Explorer (CE) and Einstein Telescope (ET), as well as the space-based Laser Infrared Space Antenna (LISA). Exploiting the worldline effective field theory (EFT) formalism, we first characterize three types of quadrupole finite-size effects: the spin-induced quadrupole moments, the conservative tidal deformations, and the tidal heating. We then derive the corresponding contributions to the gravitational waveform phases for binary compact objects in aligned-spin quasi-circular orbits. We separately estimate the constraints on these finite-size effects for black holes using the power spectral densities (PSDs) of the CE+ET detector network and LISA observations. For the CE+ET network, we find that the bounds on the mass-weighted spin-independent dissipation number $H_0$ are of the order $O(1)$, while the bounds on the mass-weighted tidal Love number $\tilde{\Lambda}$ are of the order $O(10)$. For high-spin binary black holes with dimensionless spin $\chi \simeq 0.8$, the bounds on the symmetric spin-induced quadrupole moment $\kappa_s$ are of the order $O(10^{-1})$. LISA observations of supermassive black hole mergers offer slightly tighter constraints on all three finite-size parameters. Additionally, we perform a Fisher analysis for a binary neutron star merger within the CE+ET network. The bounds on the tidal parameter $H_0$ and on $\tilde \Lambda$ are around two orders of magnitude better than the current LIGO-Virgo-KAGRA (LVK) bounds., Comment: 25 pages; 2 figures; 2 tables; 1 appendix

Generating physically feasible dynamics in a data-driven context is challenging, especially when adhering to physical priors expressed in specific equations or formulas. Existing methodologies often overlook the integration of physical priors, resulting in violation of basic physical laws and suboptimal performance. In this paper, we introduce a novel framework that seamlessly incorporates physical priors into diffusion-based generative models to address this limitation. Our approach leverages two categories of priors: 1) distributional priors, such as roto-translational invariance, and 2) physical feasibility priors, including energy and momentum conservation laws and PDE constraints. By embedding these priors into the generative process, our method can efficiently generate physically realistic dynamics, encompassing trajectories and flows. Empirical evaluations demonstrate that our method produces high-quality dynamics across a diverse array of physical phenomena with remarkable robustness, underscoring its potential to advance data-driven studies in AI4Physics. Our contributions signify a substantial advancement in the field of generative modeling, offering a robust solution to generate accurate and physically consistent dynamics.

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.

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., Comment: 28 pages, 2 tables, 1 appendix, version 2

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., Comment: 14pages,8 figures

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.

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.

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 $|\Delta E_H/\Delta E_{\infty}|\lesssim 3\cdot 10^{-3}$. 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., Comment: 30+18 pages, 7 figures

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.

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., Comment: Project page: https://flexidreamer.github.io

Given a graph $G,$ a subset of vertices is called a maximum dissociation set of $G$ if it induces a subgraph with vertex degree at most 1, and the subset has maximum cardinality. The cardinality of a maximum dissociation set is called the dissociation number of $G$. The adjacency matrix and the degree diagonal matrix of $G$ are denoted by $A(G)$ and $D(G),$ respectively. In 2017, Nikiforov proposed the $A_\alpha$-matrix: $A_\alpha(G)=\alpha D(G)+(1-\alpha)A(G),$ where $\alpha\in[0,1].$ The largest eigenvalue of this novel matrix is called the $A_\alpha$-index of $G.$ In this paper, we firstly determine the connected graph (resp. bipartite graph, tree) having the largest $A_\alpha$-index over all connected graphs (resp. bipartite graphs, trees) with fixed order and dissociation number. Secondly, we describe the structure of all the $n$-vertex graphs having the minimum $A_\alpha$-index with dissociation number $\tau$, where $\tau\geqslant\lceil\frac{2}{3}n\rceil.$ Finally, we identify all the connected $n$-vertex graphs with dissociation number $\tau\in\{2,\lceil\frac{2}{3}n\rceil,n-1,n-2\}$ having the minimum $A_\alpha$-index., Comment: 16 pages; 6 figures

Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways; meanwhile offering valuable insights into other systems incorporating SE(3)-invariance.

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.

Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores., Comment: Work in Progress

Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level robot actions, effectively bridging the interface between high-level planning and low-level robot control. However, the challenge remains that even with syntactically correct plans, robots can still fail to achieve their intended goals due to imperfect plans or unexpected environmental issues. To overcome this, Vision Language Models (VLMs) have shown remarkable success in tasks such as visual question answering. Leveraging the capabilities of VLMs, we present a novel framework called Robotic Replanning with Perception and Language Models (RePLan) that enables online replanning capabilities for long-horizon tasks. This framework utilizes the physical grounding provided by a VLM's understanding of the world's state to adapt robot actions when the initial plan fails to achieve the desired goal. We developed a Reasoning and Control (RC) benchmark with eight long-horizon tasks to test our approach. We find that RePLan enables a robot to successfully adapt to unforeseen obstacles while accomplishing open-ended, long-horizon goals, where baseline models cannot, and can be readily applied to real robots. Find more information at https://replan-lm.github.io/replan.github.io/

Purpose: This study aims to develop a high-resolution whole-brain multi-parametric quantitative MRI approach for simultaneous mapping of myelin-water fraction (MWF), T1, T2, and proton-density (PD), all within a clinically feasible scan time. Methods: We developed 3D ViSTa-MRF, which combined Visualization of Short Transverse relaxation time component (ViSTa) technique with MR Fingerprinting (MRF), to achieve high-fidelity whole-brain MWF and T1/T2/PD mapping on a clinical 3T scanner. To achieve fast acquisition and memory-efficient reconstruction, the ViSTa-MRF sequence leverages an optimized 3D tiny-golden-angle-shuffling spiral-projection acquisition and joint spatial-temporal subspace reconstruction with optimized preconditioning algorithm. With the proposed ViSTa-MRF approach, high-fidelity direct MWF mapping was achieved without a need for multi-compartment fitting that could introduce bias and/or noise from additional assumptions or priors. Results: The in-vivo results demonstrate the effectiveness of the proposed acquisition and reconstruction framework to provide fast multi-parametric mapping with high SNR and good quality. The in-vivo results of 1mm- and 0.66mm-iso datasets indicate that the MWF values measured by the proposed method are consistent with standard ViSTa results that are 30x slower with lower SNR. Furthermore, we applied the proposed method to enable 5-minute whole-brain 1mm-iso assessment of MWF and T1/T2/PD mappings for infant brain development and for post-mortem brain samples. Conclusions: In this work, we have developed a 3D ViSTa-MRF technique that enables the acquisition of whole-brain MWF, quantitative T1, T2, and PD maps at 1mm and 0.66mm isotropic resolution in 5 and 15 minutes, respectively. This advancement allows for quantitative investigations of myelination changes in the brain., Comment: 38 pages, 12 figures and 1 table

$B_1^+$ and $B_0$ field-inhomogeneities can significantly reduce accuracy and robustness of MRF's quantitative parameter estimates. Additional $B_1^+$ and $B_0$ calibration scans can mitigate this but add scan time and cannot be applied retrospectively to previously collected data. Here, we proposed a calibration-free sequence-adaptive deep-learning framework, to estimate and correct for $B_1^+$ and $B_0$ effects of any MRF sequence. We demonstrate its capability on arbitrary MRF sequences at 3T, where no training data were previously obtained. Such approach can be applied to any previously-acquired and future MRF-scans. The flexibility in directly applying this framework to other quantitative sequences is also highlighted., Comment: 12 pages, 5 figures, submitted to International Society for Magnetic Resonance in Medicine 31th Scientific Meeting, 2024

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., Comment: 18 pages, 3 figs; the helicity reversing amplitude is considered in the new version

Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps. Till now, it remains unclear how to effectively accelerate this procedure explicitly in SE(3)-invariant space, which greatly hinders its wide application in the real world. In this paper, we systematically study the diffusion mechanism in SE(3)-invariant space via the lens of approximate errors induced by existing methods. Thereby, we develop more precise approximate in SE(3) in the context of projected differential equations. Theoretical analysis is further provided as well as empirical proof relating hyper-parameters with such errors. Altogether, we propose a novel acceleration scheme for generating molecular conformations in SE(3)-invariant space. Experimentally, our scheme can generate high-quality conformations with 50x--100x speedup compared to existing methods., Comment: We are currently developing a new manuscript that significantly expands upon and integrates the research presented here. The forthcoming paper includes broader analyses and more comprehensive findings, rendering the current version obsolete. We believe this decision will contribute to a clearer and more consolidated presentation of our research findings

This paper considers the best policy identification (BPI) problem in online Constrained Markov Decision Processes (CMDPs). We are interested in algorithms that are model-free, have low regret, and identify an approximately optimal policy with a high probability. Existing model-free algorithms for online CMDPs with sublinear regret and constraint violation do not provide any convergence guarantee to an optimal policy and provide only average performance guarantees when a policy is uniformly sampled at random from all previously used policies. In this paper, we develop a new algorithm, named Pruning-Refinement-Identification (PRI), based on a fundamental structural property of CMDPs proved before, which we call limited stochasticity. The property says for a CMDP with $N$ constraints, there exists an optimal policy with at most $N$ stochastic decisions. The proposed algorithm first identifies at which step and in which state a stochastic decision has to be taken and then fine-tunes the distributions of these stochastic decisions. PRI achieves trio objectives: (i) PRI is a model-free algorithm; and (ii) it outputs an approximately optimal policy with a high probability at the end of learning; and (iii) PRI guarantees $\tilde{\mathcal{O}}(H\sqrt{K})$ regret and constraint violation, which significantly improves the best existing regret bound $\tilde{\mathcal{O}}(H^4 \sqrt{SA}K^{\frac{4}{5}})$ under a model-free algorithm, where $H$ is the length of each episode, $S$ is the number of states, $A$ is the number of actions, and the total number of episodes during learning is $2K+\tilde{\cal O}(K^{0.25}).$ We further present a matching lower via an example that shows under any online learning algorithm, there exists a well-separated CMDP instance such that either the regret or violation has to be $\Omega(H\sqrt{K}),$ which matches the upper bound by a polylogarithmic factor.

In various applications, such as robotic navigation and remote visual assistance, expanding the field of view (FOV) of the camera proves beneficial for enhancing environmental perception. Unlike image outpainting techniques aimed solely at generating aesthetically pleasing visuals, these applications demand an extended view that faithfully represents the scene. To achieve this, we formulate a new problem of faithful FOV extrapolation that utilizes a set of pre-captured images as prior knowledge of the scene. To address this problem, we present a simple yet effective solution called NeRF-Enhanced Outpainting (NEO) that uses extended-FOV images generated through NeRF to train a scene-specific image outpainting model. To assess the performance of NEO, we conduct comprehensive evaluations on three photorealistic datasets and one real-world dataset. Extensive experiments on the benchmark datasets showcase the robustness and potential of our method in addressing this challenge. We believe our work lays a strong foundation for future exploration within the research community.

Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule. Generating molecular conformation via diffusion requires learning to reverse a noising process. Diffusion on inter-atomic distances instead of conformation preserves SE(3)-equivalence and shows superior performance compared to alternative techniques, whereas related generative modelings are predominantly based upon heuristical assumptions. In response to this, we propose a novel molecular conformation generation approach driven by the observation that the disintegration of a molecule can be viewed as casting increasing force fields to its composing atoms, such that the distribution of the change of inter-atomic distance shifts from Gaussian to Maxwell-Boltzmann distribution. The corresponding generative modeling ensures a feasible inter-atomic distance geometry and exhibits time reversibility. Experimental results on molecular datasets demonstrate the advantages of the proposed shifting distribution compared to the state-of-the-art., Comment: 18 pages, 7 figures

In this paper, we develop a new method to automatically convert 2D line drawings from three orthographic views into 3D CAD models. Existing methods for this problem reconstruct 3D models by back-projecting the 2D observations into 3D space while maintaining explicit correspondence between the input and output. Such methods are sensitive to errors and noises in the input, thus often fail in practice where the input drawings created by human designers are imperfect. To overcome this difficulty, we leverage the attention mechanism in a Transformer-based sequence generation model to learn flexible mappings between the input and output. Further, we design shape programs which are suitable for generating the objects of interest to boost the reconstruction accuracy and facilitate CAD modeling applications. Experiments on a new benchmark dataset show that our method significantly outperforms existing ones when the inputs are noisy or incomplete., Comment: To Appear in ICCV 2023. The first three authors contributed equally to this work. The project page is at https://manycore-research.github.io/PlankAssembly

World Wide Web is speeding up its pace into an intelligent and decentralized ecosystem, as seen in the campaign of Web 3.0 and forthcoming Web 4.0. Marked by the Europe Commission's latest mention of Web 4.0, a race towards strategic Web 4.0 success has started. Web 4.0 is committed to bringing the next technological transition with an open, secure, trustworthy fairness and digital ecosystem for individuals and businesses in private and public sectors. Despite overlapping scopes and objectives of Web 3.0 and Web 4.0 from academic and industrial perspectives, there are distinct and definitive features and gaps for the next generation of WWW. In this review, a brief introduction to WWW development unravels the entangled but consistent requirement of a more vivid web experience, enhancing human-centric experience in both societal and technical aspects. Moreover, the review brings a decentralized intelligence prospect of view on native AI entities for Web 4.0, envisioning sustainable, autonomous and decentralized AI services for the entire Web 4.0 environment, powering a self-sustainable Decentralized Physical and Software Infrastructure for Computing Force Network, Semantic Network, Virtual/Mixed Reality, and Privacy-preserving content presumption. The review aims to reveal that Web 4.0 offers native intelligence with focused thinking on utilizing decentralized physical infrastructure, in addition to sole requirements on decentralization, bridging the gap between Web 4.0 and Web 3.0 advances with the latest future-shaping blockchain-enabled computing and network routing protocols., Comment: 6 pages 2 figures

We present 2SDS (Scene Separation and Data Selection algorithm), a temporal segmentation algorithm used in real-time video stream interpretation. It complements CNN-based models to make use of temporal information in videos. 2SDS can detect the change between scenes in a video stream by com-paring the image difference between two frames. It separates a video into segments (scenes), and by combining itself with a CNN model, 2SDS can select the optimal result for each scene. In this paper, we will be discussing some basic methods and concepts behind 2SDS, as well as presenting some preliminary experiment results regarding 2SDS. During these experiments, 2SDS has achieved an overall accuracy of over 90%., Comment: 5 pages, 4 figures, at IJCAI-ECAI 2022 workshop, First International Workshop on Spatio-Temporal Reasoning and Learning, July 24, 2022, Vienna, Austria

We match scattering amplitudes in point particle effective field theory (EFT) and general relativity to extract low frequency dynamical tidal responses of rotating (Kerr) black holes to all orders in spin. In the conservative sector, we study local worldline couplings that correspond to the time-derivative expansion of the black hole tidal response function. These are dynamical (frequency-dependent) generalizations of the static Love numbers. We identify and extract couplings of three types of subleading local worldline operators: the curvature time derivative terms, the spin - curvature time derivative couplings, and quadrupole - octupole mixing operators that arise due to the violation of spherical symmetry. The first two subleading couplings are non-zero and exhibit a classical renormalization group running; we explicitly present their scheme-independent beta functions. The conservative mixing terms, however, vanish as a consequence of vanishing static Love numbers. In the non-conservative sector, we match the dissipation numbers at next-to-leading and next-to-next-to leading orders in frequency. In passing, we identify terms in the general relativity absorption probabilities that originate from tails and short-scale logarithmic corrections to the lowest order dissipation contributions., Comment: 52 pages, published version in PRD

We propose Structured Exploration with Achievements (SEA), a multi-stage reinforcement learning algorithm designed for achievement-based environments, a particular type of environment with an internal achievement set. SEA first uses offline data to learn a representation of the known achievements with a determinant loss function, then recovers the dependency graph of the learned achievements with a heuristic algorithm, and finally interacts with the environment online to learn policies that master known achievements and explore new ones with a controller built with the recovered dependency graph. We empirically demonstrate that SEA can recover the achievement structure accurately and improve exploration in hard domains such as Crafter that are procedurally generated with high-dimensional observations like images., Comment: published as a conference paper at ICLR 2023

Collusive fraud, in which multiple fraudsters collude to defraud health insurance funds, threatens the operation of the healthcare system. However, existing statistical and machine learning-based methods have limited ability to detect fraud in the scenario of health insurance due to the high similarity of fraudulent behaviors to normal medical visits and the lack of labeled data. To ensure the accuracy of the detection results, expert knowledge needs to be integrated with the fraud detection process. By working closely with health insurance audit experts, we propose FraudAuditor, a three-stage visual analytics approach to collusive fraud detection in health insurance. Specifically, we first allow users to interactively construct a co-visit network to holistically model the visit relationships of different patients. Second, an improved community detection algorithm that considers the strength of fraud likelihood is designed to detect suspicious fraudulent groups. Finally, through our visual interface, users can compare, investigate, and verify suspicious patient behavior with tailored visualizations that support different time scales. We conducted case studies in a real-world healthcare scenario, i.e., to help locate the actual fraud group and exclude the false positive group. The results and expert feedback proved the effectiveness and usability of the approach., Comment: 12 pages, 7 figures

A complex system with cluttered observations may be a coupled mixture of multiple simple sub-systems corresponding to latent entities. Such sub-systems may hold distinct dynamics in the continuous-time domain; therein, complicated interactions between sub-systems also evolve over time. This setting is fairly common in the real world but has been less considered. In this paper, we propose a sequential learning approach under this setting by decoupling a complex system for handling irregularly sampled and cluttered sequential observations. Such decoupling brings about not only subsystems describing the dynamics of each latent entity but also a meta-system capturing the interaction between entities over time. Specifically, we argue that the meta-system evolving within a simplex is governed by projected differential equations (ProjDEs). We further analyze and provide neural-friendly projection operators in the context of Bregman divergence. Experimental results on synthetic and real-world datasets show the advantages of our approach when facing complex and cluttered sequential data compared to the state-of-the-art.