Search

Autonomous agents powered by large language models (LLMs) show significant potential for achieving high autonomy in various scenarios such as software development. Recent research has shown that LLM agents can leverage past experiences to reduce errors and enhance efficiency. However, the static experience paradigm, reliant on a fixed collection of past experiences acquired heuristically, lacks iterative refinement and thus hampers agents' adaptability. In this paper, we introduce the Iterative Experience Refinement framework, enabling LLM agents to refine experiences iteratively during task execution. We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquiring experiences across all previous task batches. Augmented with our heuristic experience elimination, the method prioritizes high-quality and frequently-used experiences, effectively managing the experience space and enhancing efficiency. Extensive experiments show that while the successive pattern may yield superior results, the cumulative pattern provides more stable performance. Moreover, experience elimination facilitates achieving better performance using just 11.54% of a high-quality subset., Comment: Work in progress

This paper presents CleanGraph, an interactive web-based tool designed to facilitate the refinement and completion of knowledge graphs. Maintaining the reliability of knowledge graphs, which are grounded in high-quality and error-free facts, is crucial for real-world applications such as question-answering and information retrieval systems. These graphs are often automatically assembled from textual sources by extracting semantic triples via information extraction. However, assuring the quality of these extracted triples, especially when dealing with large or low-quality datasets, can pose a significant challenge and adversely affect the performance of downstream applications. CleanGraph allows users to perform Create, Read, Update, and Delete (CRUD) operations on their graphs, as well as apply models in the form of plugins for graph refinement and completion tasks. These functionalities enable users to enhance the integrity and reliability of their graph data. A demonstration of CleanGraph and its source code can be accessed at https://github.com/nlp-tlp/CleanGraph under the MIT License.

Purpose: Historically, spot scanning proton therapy (SSPT) treatment planning utilizes dose volume constraints and linear-energy-transfer (LET) volume constraints separately to balance tumor control and organs-at-risk (OARs) protection. We propose a novel dose-LET volume constraint (DLVC)-based robust optimization (DLVCRO) method for SSPT in treating prostate cancer to obtain a desirable joint dose and LET distribution to minimize adverse events (AEs). Methods: DLVCRO treats DLVC as soft constraints controlling the joint distribution of dose and LET. Ten prostate cancer patients were included with rectum and bladder as OARs. DLVCRO was compared with the conventional robust optimization (RO) method using the worst-case analysis method. Besides the dose-volume histogram (DVH) indices, the analogous LETVH and extra-biological-dose (xBD)-volume histogram indices were also used. The Wilcoxon signed rank test was used to measure statistical significance. Results: In nominal scenario, DLVCRO significantly improved dose, LET and xBD distributions to protect OARs (rectum: V70Gy: 3.07\% vs. 2.90\%, p = .0063, RO vs. DLVCRO; $\text{LET}_{\max}$ (keV/um): 11.53 vs. 9.44, p = .0101; $\text{xBD}_{\max}$ (Gy$\cdot$keV/um): 420.55 vs. 398.79, p = .0086; bladder: V65Gy: 4.82\% vs. 4.61\%, p = .0032; $\text{LET}_{\max}$ 8.97 vs. 7.51, p = .0047; $\text{xBD}_{\max}$ 490.11 vs. 476.71, p = .0641). The physical dose distributions in targets are comparable (D2%: 98.57\% vs. 98.39\%; p = .0805; CTV D2% - D98%: 7.10\% vs. 7.75\%, p = .4624). In the worst-case scenario, DLVCRO robustly enhanced OAR while maintaining the similar plan robustness in target dose coverage and homogeneity. Conclusion: DLVCRO upgrades 2D DVH-based to 3D DLVH-based treatment planning to adjust dose/LET distributions simultaneously and robustly. DLVCRO is potentially a powerful tool to improve patient outcomes in SSPT.

The low efficiency of conventional liquefaction technologies based on the Joule-Thomson expansion makes liquid hydrogen currently not attractive enough for large-scale energy-related technologies that are important for the transition to a carbon-neutral society. Magnetocaloric hydrogen liquefaction has great potential to achieve higher efficiency and is therefore a crucial enabler for affordable liquid hydrogen. Cost-effective magnetocaloric materials with large magnetic entropy and adiabatic temperature changes in the temperature range of 77 $\sim$ 20 K under commercially practicable magnetic fields are the foundation for the success of magnetocaloric hydrogen liquefaction. Heavy rare-earth-based magnetocaloric intermetallic compounds generally show excellent magnetocaloric performances, but the heavy rare-earth elements (Gd, Tb, Dy, Ho, Er, and Tm) are highly critical in resources. Yttrium and light rare-earth elements (La, Ce, Pr, and Nd) are relatively abundant, but their alloys generally show less excellent magnetocaloric properties. A dilemma appears: higher performance or lower criticality? In this review, we study how cryogenic temperature influences magnetocaloric performance by first reviewing heavy rare-earth-based intermetallic compounds. Next, we look at light rare-earth-based, "mixed" rare-earth-based, and Gd-based intermetallic compounds with the nature of the phase transition order taken into consideration, and summarize ways to resolve the dilemma.

Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high energy consumption and latency time (energy-latency cost), it will exhaust computational resources and harm availability of service. In this paper, we investigate this vulnerability for MLLMs, particularly image-based and video-based ones, and aim to induce high energy-latency cost during inference by crafting an imperceptible perturbation. We find that high energy-latency cost can be manipulated by maximizing the length of generated sequences, which motivates us to propose verbose samples, including verbose images and videos. Concretely, two modality non-specific losses are proposed, including a loss to delay end-of-sequence (EOS) token and an uncertainty loss to increase the uncertainty over each generated token. In addition, improving diversity is important to encourage longer responses by increasing the complexity, which inspires the following modality specific loss. For verbose images, a token diversity loss is proposed to promote diverse hidden states. For verbose videos, a frame feature diversity loss is proposed to increase the feature diversity among frames. To balance these losses, we propose a temporal weight adjustment algorithm. Experiments demonstrate that our verbose samples can largely extend the length of generated sequences., Comment: arXiv admin note: substantial text overlap with arXiv:2401.11170

Molecule-and-text cross-modal representation learning has emerged as a promising direction for enhancing the quality of molecular representation, thereby improving performance in various scientific fields, including drug discovery and materials science. Existing studies adopt a global alignment approach to learn the knowledge from different modalities. These global alignment approaches fail to capture fine-grained information, such as molecular fragments and their corresponding textual description, which is crucial for downstream tasks. Furthermore, it is incapable to model such information using a similar global alignment strategy due to data scarcity of paired local part annotated data from existing datasets. In this paper, we propose Atomas, a multi-modal molecular representation learning framework to jointly learn representations from SMILES string and text. We design a Hierarchical Adaptive Alignment model to concurrently learn the fine-grained fragment correspondence between two modalities and align these representations of fragments in three levels. Additionally, Atomas's end-to-end training framework incorporates the tasks of understanding and generating molecule, thereby supporting a wider range of downstream tasks. In the retrieval task, Atomas exhibits robust generalization ability and outperforms the baseline by 30.8% of recall@1 on average. In the generation task, Atomas achieves state-of-the-art results in both molecule captioning task and molecule generation task. Moreover, the visualization of the Hierarchical Adaptive Alignment model further confirms the chemical significance of our approach. Our codes can be found at https://anonymous.4open.science/r/Atomas-03C3.

This article examines the critical role of fast Monte Carlo dose calculations in advancing proton therapy techniques, particularly in the context of increasing treatment customization and precision. As adaptive radiotherapy and other patient-specific approaches evolve, the need for accurate and precise dose calculations, essential for techniques like proton-based stereotactic radiosurgery, becomes more prominent. These calculations, however, are time-intensive, with the treatment planning/optimization process constrained by the achievable speed of dose computations. Thus, enhancing the speed of Monte Carlo methods is vital, as it not only facilitates the implementation of novel treatment modalities but also improves the optimality of treatment plans. Today, the state-of-the-art in Monte Carlo dose calculation speeds is 106 - 107 protons per second. This review highlights the latest advancements in fast Monte Carlo dose calculations that have led to such speeds, including emerging artificial intelligence-based techniques, and discusses their application in both current and emerging proton therapy strategies., Comment: 41 pages

The core challenge of de novo protein design lies in creating proteins with specific functions or properties, guided by certain conditions. Current models explore to generate protein using structural and evolutionary guidance, which only provide indirect conditions concerning functions and properties. However, textual annotations of proteins, especially the annotations for protein domains, which directly describe the protein's high-level functionalities, properties, and their correlation with target amino acid sequences, remain unexplored in the context of protein design tasks. In this paper, we propose Protein-Annotation Alignment Generation (PAAG), a multi-modality protein design framework that integrates the textual annotations extracted from protein database for controllable generation in sequence space. Specifically, within a multi-level alignment module, PAAG can explicitly generate proteins containing specific domains conditioned on the corresponding domain annotations, and can even design novel proteins with flexible combinations of different kinds of annotations. Our experimental results underscore the superiority of the aligned protein representations from PAAG over 7 prediction tasks. Furthermore, PAAG demonstrates a nearly sixfold increase in generation success rate (24.7% vs 4.7% in zinc finger, and 54.3% vs 8.7% in the immunoglobulin domain) in comparison to the existing model.

A Nehari manifold optimization method (NMOM) is introduced for finding 1-saddles, i.e., saddle points with the Morse index equal to one, of a generic nonlinear functional in Hilbert spaces. Actually, it is based on the variational characterization that 1-saddles of the generic functional are local minimizers of the same functional restricted on the associated Nehari manifold. The framework contains two important ingredients: one is the retraction mapping to make the iteration points always lie on the Nehari manifold; the other is the tangential search direction to decrease the generic functional with suitable step-size search rules. Particularly, the global convergence is rigorously established by virtue of some crucial analysis techniques (including a weak convergence method) overcoming difficulties in the infinite-dimensional setting. In practice, combining with an easy-to-implement Nehari retraction and the negative Riemannian gradient direction, the NMOM is successfully applied to compute the unstable ground-state solutions of a class of typical semilinear elliptic PDEs such as H\'enon equation and the stationary nonlinear Schr\"odinger equation. In particular, the symmetry-breaking phenomenon of the ground states of H\'enon equation is explored numerically in 1D and 2D with interesting numerical findings on the critical value of symmetry-breaking reported., Comment: 26 pages, 8 figures

Laser metal additive manufacturing technology is capable of producing components with complex geometries and compositions that cannot be realized by conventional manufacturing methods. However, a large number of pores generated during the additive manufacturing process greatly affect the mechanical properties of the additively manufactured parts, and the mechanism of such pore generation has not been revealed by direct observation clearly. Here, we report the mechanism of pore generation in the laser direct energy deposition process as revealed by {\it in-situ} high-speed high-resolution synchrotron X-ray imaging. We found that dissolution and re-precipitation of external gases and precipitation of metal vapors are the two main mechanisms of pore formation. We further explored the effects of different process parameters on the generation of pores and optimized the process to suppress pore generation. This work provides important insights into the formation of porosity defects during laser metal additive manufacturing, and can provide guidance for related process optimization., Comment: 7 figures

A representative volume element (RVE) is a reasonably small unit of microstructure that can be simulated to obtain the same effective properties as the entire microstructure sample. Finite element (FE) simulation of RVEs, as opposed to much larger samples, saves computational expense, especially in multiscale modeling. Therefore, it is desirable to have a framework that determines RVE size prior to FE simulations. Existing methods select the RVE size based on when the FE-simulated properties of samples of increasing size converge with insignificant statistical variations, with the drawback that many samples must be simulated. We propose a simulation-free alternative that determines RVE size based only on a micrograph. The approach utilizes a machine learning model trained to implicitly characterize the stochastic nature of the input micrograph. The underlying rationale is to view RVE size as the smallest moving window size for which the stochastic nature of the microstructure within the window is stationary as the window moves across a large micrograph. For this purpose, we adapt a recently developed Fisher score-based framework for microstructure nonstationarity monitoring. Because the resulting RVE size is based solely on the micrograph and does not involve any FE simulation of specific properties, it constitutes an RVE for any property of interest that solely depends on the microstructure characteristics. Through numerical experiments of simple and complex microstructures, we validate our approach and show that our selected RVE sizes are consistent with when the chosen FE-simulated properties converge.

We analyze the photo-production of $\eta_{c,b}$ off a proton in the threshold region, in terms of C-odd gluonic correlations in the off-forward proton matrix element. Near threshold, the skewness is large leading to a production amplitude that is dominated by four C-odd twist-3 gluon GPDs. We use the QCD instanton vacuum to estimate these C-odd contributions in the proton. The results are used to estimate the differential cross sections for coherent photo-production of $\eta_{c,b}$ in the threshold region, at current electron facilities., Comment: 25 pages, 9 figures

We discuss a general framework for the evaluation of the gluonic form factors in light hadrons at low momentum transfer, in the QCD instanton vacuum. At medium resolution of the order of the inverse mean instanton size, the glue is mostly localized in single or pair of pseudoparticles, and globally constrained by the fluctuations of their topological charges. These pseudoparticles trap light quarks, giving rise to emerging multiflavor 't Hooft interactions. We explicitly evaluate the gluonic scalar, pseudoscalar, energy-momentum tensor (EMT), and the leading C-odd and C-even three gluons hadronic form factors, at next to leading order (NLO) in the instanton density, including molecular clusters of like and unlike instantons. We use the results for the EMT to address the contribution of the gluons in Ji$^\prime$s mass and spin sum rules, at low resolution. When evolved, our results for the mass and spin composition of the nucleon, are shown to be in good agreement with the recently reported lattice results at higher resolution., Comment: 67 pages, 16 figures

We study a graph partition problem where we are given a directed acyclic graph (DAG) whose vertices and arcs can be respectively regarded as tasks and dependencies among tasks. The objective of the problem is to minimize the total energy consumed for completing these tasks by assigning the tasks to k heterogeneous machines. We first show that the problem is NP-hard. Then, we present polynomial-time algorithms for two special cases where there are only two machines and where the input DAG is a directed path. Finally, we study a natural variant where there are only two machines with one of them being capable of executing a limited number of tasks. We show that this special case remains computationally hard.

We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios? Prior work claimed this is due to linguistic dissimilarity between explicit and implicit examples but provided no empirical evidence. In this study, we show that one cause for such failure is a label shift after connectives are eliminated. Specifically, we find that the discourse relations expressed by some explicit instances will change when connectives disappear. Unlike previous work manually analyzing a few examples, we present empirical evidence at the corpus level to prove the existence of such shift. Then, we analyze why label shift occurs by considering factors such as the syntactic role played by connectives, ambiguity of connectives, and more. Finally, we investigate two strategies to mitigate the label shift: filtering out noisy data and joint learning with connectives. Experiments on PDTB 2.0, PDTB 3.0, and the GUM dataset demonstrate that classifiers trained with our strategies outperform strong baselines., Comment: Accepted by NAACL2024 (Long Paper)

Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference. In recent years, graph neural networks (GNNs) have emerged as powerful graph models for inductive learning tasks such as node classification, whereas they typically heavily rely on the annotated nodes under a fully supervised training setting. Compared with the GNN-based methods, variational graph auto-encoders (VGAEs) are known to be more generalizable to capture the internal structural information of graphs independent of node labels and have achieved prominent performance on multiple unsupervised learning tasks. However, so far there is still a lack of work focusing on leveraging the VGAE framework for inductive learning, due to the difficulties in training the model in a supervised manner and avoiding over-fitting the proximity information of graphs. To solve these problems and improve the model performance of VGAEs for inductive graph representation learning, in this work, we propose the Self-Label Augmented VGAE model. To leverage the label information for training, our model takes node labels as one-hot encoded inputs and then performs label reconstruction in model training. To overcome the scarcity problem of node labels for semi-supervised settings, we further propose the Self-Label Augmentation Method (SLAM), which uses pseudo labels generated by our model with a node-wise masking approach to enhance the label information. Experiments on benchmark inductive learning graph datasets verify that our proposed model archives promising results on node classification with particular superiority under semi-supervised learning settings.

A light pseudoscalar $A$ in the sufficient large $\tan\beta$ region of type-I two-Higgs-doublet model (2HDM) can be naturally a long-lived particle (LLP). We focus on the $H^{\pm}A$, $HA$ and $AA$ pair productions via the electroweak processes mediated by the bosons at the LHC, including $pp \rightarrow W^\pm/Z \rightarrow H^{\pm}/H A$ and $pp \rightarrow h \rightarrow AA$ at the 14 TeV LHC. The possibility of probing $A$ as a LLP at the FASER-2, FACET, MoEDAL-MAPP-2, MATHUSLA is discussed. We find that FASER-2 fails to probe any parameter space within 0.2 GeV $< m_A <$ 10 GeV for both processes. For 130 $< m_{H\pm} = m_H <$ 400 GeV, FACET, MoEDAL-MAPP-2 and MATHUSLA can probes $\tan \beta \lesssim 10^{4-6}$ for $m_A \lesssim 3$ GeV, and $\tan \beta \lesssim 10^{6-8}$ for 3 GeV $\lesssim m_A <$ 10 GeV from $pp \rightarrow W^\pm/Z \rightarrow H^{\pm}/Z A$ processes. And $pp \rightarrow h \rightarrow AA$ covers similar parameter space. All processes can surpass the current limits., Comment: 13 pages+refs, 7 figures

The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task., Comment: https://github.com/NL2Code/CodeS

This paper considers the state estimation problem for discrete-time linear systems under event-triggered scheme. In order to improve performance, a novel event-triggered scheme based on confidence level is proposed using the chi-square distribution and mild regularity assumption. In terms of the novel event-triggered scheme, a minimum mean squared error (MMSE) state estimator is proposed using some results presented in this paper. Two algorithms for communication rate estimation of the proposed MMSE state estimator are developed where the first algorithm is based on information with one-step delay, and the second algorithm is based on information with two-step delay. The performance and effectiveness of the proposed MMSE state estimator and the two communication rate estimation algorithms are illustrated using a target tracking scenario.

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic hierarchical rules that are agnostic to the optimal adversarial examples, a strategy that often results in adversarial samples with a suboptimal balance between magnitudes of changes and attack successes. To this end, in this research we propose two algorithms, Reversible Jump Attack (RJA) and Metropolis-Hasting Modification Reduction (MMR), to generate highly effective adversarial examples and to improve the imperceptibility of the examples, respectively. RJA utilizes a novel randomization mechanism to enlarge the search space and efficiently adapts to a number of perturbed words for adversarial examples. With these generated adversarial examples, MMR applies the Metropolis-Hasting sampler to enhance the imperceptibility of adversarial examples. Extensive experiments demonstrate that RJA-MMR outperforms current state-of-the-art methods in attack performance, imperceptibility, fluency and grammar correctness.

The Sun stands out as the closest and clearest astrophysical accelerator of cosmic rays, while other objects within and beyond the galaxy remain enigmatic. It is probable that the cosmic ray spectrum and mass components from these celestial sources share similarities, offering a novel approach to study their origin. In this study, we analyze of spectra and mass in the energy range from MeV to 10~EeV. We find: (1) the mean-logarithmic mass $\rm\left\langle lnA \right\rangle$ distribution with energy exhibits much clearer feature structures than the spectra; (2) a 100~TeV bump is presented in the $\rm\left\langle lnA \right\rangle$ distribution; (3) for protons, the knee is located at $\sim2$ PeV, the boundary between the galaxy and extra-galaxy occurs at $\sim30$ PeV, marked by a sharp dip; (4) the all-particle spectrum exhibits hardening at $\sim30$~PeV due to the contribution of nearby galaxies, and the extra-galactic dominate $\sim0.7$~EeV. We hope the LHAASO experiment can perform spectral measurements of individual species to validate our results., Comment: 6 pages, 3 figures