arXiv subjects

Ke Wang

Publications and source records attributed to Ke Wang.

At least 307 records · Page 17Linked to original sources

arXiv2024

MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs

Large language models (LLMs) have exhibited great potential in mathematical reasoning. However, there remains a performance gap in this area between existing open-source models and closed-source models such as GPT-4. In this paper, we introduce MathGenie, a novel method for generating diverse and reliable math problems from a small-scale problem-solution dataset (denoted as seed data). We augment the ground-truth solutions of our seed data and train a back-translation model to translate the augmented solutions back into new questions. Subsequently, we generate code-integrated solutions for the new questions. To ensure the correctness of the code-integrated solutions, we employ rationale-based strategy for solution verification. Various pretrained models, ranging from 7B to 70B, are trained on the newly curated data to test the effectiveness of the proposed augmentation technique, resulting in a family of models known as MathGenieLM. These models consistently outperform previous open-source models across five representative mathematical reasoning datasets, achieving state-of-the-art performance. In particular, MathGenieLM-InternLM2 achieves an accuracy of 87.7% on GSM8K and 55.7% on MATH, securing the best overall score among open-source language models.

cs.CL↗

arXiv2024

JCMT 850 $\micron$ continuum observations of density structures in the G35 molecular complex

Filaments are believed to play a key role in high-mass star formation. We present a systematic study of the filaments and their hosting clumps in the G35 molecular complex using JCMT SCUBA-2 850 $\micron$ continuum data. We identified five clouds in the complex and 91 filaments within them, some of which form 10 hub-filament systems (HFSs), each with at least 3 hub-composing filaments. We also compiled a catalogue of 350 dense clumps, 183 of which are associated with the filaments. We investigated the physical properties of the filaments and clumps, such as mass, density, and size, and their relation to star formation. We find that the global mass-length trend of the filaments is consistent with a turbulent origin, while the hub-composing filaments of high line masses ($m_{\rm l}\,>$\,230\,$\mathrm{M_{\odot}~pc^{-1}}$) in HFSs deviate from this relation, possibly due to feedback from massive star formation. We also find that the most massive and densest clumps (R\,$>$\,0.2\,pc, M\,$>35\,\mathrm{M_{\odot}}$, $\mathrmΣ>\,0.05\,\mathrm{g~cm^{-2}}$) are located in the filaments and in the hubs of HFS with the latter bearing a higher probability of occurrence of high-mass star-forming signatures, highlighting the preferential sites of HFSs for high-mass star formation. We do not find significant variation in the clump mass surface density across different evolutionary environments of the clouds, which may reflect the balance between mass accretion and stellar feedback.

astro-ph.GA↗

arXiv2024

The Formation of Milky Way "Bones": Ubiquitous HI Narrow Self-Absorption Associated with CO Emission

Long and skinny molecular filaments running along Galactic spiral arms are known as "bones", since they make up the skeleton of the Milky Way. However, their origin is still an open question. Here, we compare spectral images of HI taken by FAST with archival CO and Herschel dust emission to investigate the conversion from HI to H$_2$ in two typical Galactic bones, CFG028.68-0.28 and CFG047.06+0.26. Sensitive FAST HI images and an improved methodology enabled us to extract HI narrow self-absorption (HINSA) features associated with CO line emission on and off the filaments, revealing the ubiquity of HINSA towards distant clouds for the first time. The derived cold HI abundances, [HI]/[H$_2$], of the two bones range from $\sim$(0.5 to 44.7)$\times10^{-3}$, which reveal different degrees of HI-H$_2$ conversion and are similar to that of nearby, low-mass star forming clouds, Planck Galactic cold clumps and a nearby active high-mass star forming region G176.51+00.20. The HI-H$_2$ conversion has been ongoing for 2.2 to 13.2 Myr in the bones, a timescale comparable to that of massive star formation therein. Therefore, we are witnessing young giant molecular clouds with rapid massive star formation. Our study paves the way of using HINSA to study cloud formation in Galactic bones, and more generally, in distant giant molecular clouds, in the FAST era.

astro-ph.GA↗

arXiv2024

Search for the $Σ(1380)1/2^-$ state in $Λ^+_c \to γπ^+ Λ$ decay by triangle singularity

In this work, we investigate the resonance production in $Λ^+_c \to γπ^+ Λ$ decay through the triangle singularity (TS) mechanism, within an effective Lagrangian approach. We find that the appropriate loop decay process could develop a triangle singularity in the invariant mass $M_{πΛ}$ around $1.35$ GeV, with the shape depending on the quantum numbers of $Σ^*$ states that couple to the final $πΛ$ system. Especially, the $Σ(1380)1/2^-$ state newly predicted in the pentaquark model, if exists, significantly enhances the TS contribution and sharpens the TS peak due to the $S$-wave $Σ^*πΣ$ vertex in the loop. Therefore, the existence of the $Σ(1380)1/2^-$ state can be examined by measuring the TS signal in $Λ^+_c \to γπ^+ Λ$. Considering also possible tree-level diagrams, we additionally obtain the branching ratio ${\rm Br}(Λ^+_c \to γπ^+ Λ)\simeq 1.5\times 10^{-5}$. We suggest the investigation of this reaction by future BESIII, LHCb, and Belle experiments.

hep-ph↗

arXiv2024

Quantum highway: Observation of minimal and maximal speed limits for few and many-body states

Tracking the time evolution of a quantum state allows one to verify the thermalization rate or the propagation speed of correlations in generic quantum systems. Inspired by the energy-time uncertainty principle, bounds have been demonstrated on the maximal speed at which a quantum state can change, resulting in immediate and practical tasks. Based on a programmable superconducting quantum processor, we test the dynamics of various emulated quantum mechanical systems encompassing single- and many-body states. We show that one can test the known quantum speed limits and that modifying a single Hamiltonian parameter allows the observation of the crossover of the different bounds on the dynamics. We also unveil the observation of minimal quantum speed limits in addition to more common maximal ones, i.e., the lowest rate of change of a unitarily evolved quantum state. Our results establish a comprehensive experimental characterization of quantum speed limits and pave the way for their subsequent study in engineered non-unitary conditions.

quant-ph↗

arXiv2024

Absence of High-mass Prestellar Cores in the Orion Giant Molecular Cloud

A fundamental difference between "core-fed" and "clump-fed" star formation theories lies in the existence or absence of high-mass cores at the prestellar stage. However, only a handful of such cores have been observed. Here, different than previous search in distributed star formation regions in the Galactic plane, we search for high-mass prestellar cores in the Orion GMC, by observing the 7 most massive starless cores selected from previous deep continuum surveys. We present ALMA ACA Band 6 and Band 7 continuum and line observations toward the 7 cores, in which we identify 9 dense cores at both bands. The derived maximum core mass is less than 11 Msun, based on different dust temperatures. We find no high-mass prestellar cores in this sample, aligning with the results of previous surveys, thereby challenging the existence of such cores in Orion. Outside Orion, further detailed studies are needed for remaining high-mass prestellar core candidates to confirm their status as massive, starless cores.

astro-ph.GA↗

arXiv2024

Research on Tibetan Tourism Viewpoints information generation system based on LLM

Tibet, ensconced within China's territorial expanse, is distinguished by its labyrinthine and heterogeneous topography, a testament to its profound historical heritage, and the cradle of a unique religious ethos. The very essence of these attributes, however, has impeded the advancement of Tibet's tourism service infrastructure, rendering existing smart tourism services inadequate for the region's visitors. This study delves into the ramifications of informational disparities at tourist sites on Tibetan tourism and addresses the challenge of establishing the Large Language Model (LLM) evaluation criteria. It introduces an innovative approach, the DualGen Bridge AI system, employing supervised fine-tuning techniques to bolster model functionality and enhance optimization processes. Furthermore, it pioneers a multi-structured generative results assessment framework. Empirical validation confirms the efficacy of this framework. The study also explores the application of the supervised fine-tuning method within the proprietary DualGen Bridge AI, aimed at refining the generation of tourist site information. The study's findings offer valuable insights for optimizing system performance and provide support and inspiration for the application of LLM technology in Tibet's tourism services and beyond, potentially revolutionizing the smart tourism industry with advanced, tailored information generation capabilities.

cs.CL↗

arXiv2024

Improved Nonlocality Certification via Bouncing between Bell Operators and Inequalities

Bell nonlocality is an intrinsic feature of quantum mechanics, which can be certified via the violation of Bell inequalities. It is therefore a fundamental question to certify Bell nonlocality from experimental data. Here, we present an optimization scheme to improve nonlocality certification by exploring flexible mappings between Bell inequalities and Hamiltonians corresponding to the Bell operators. We show that several Hamiltonian models can be mapped to new inequalities with improved classical bounds than the original one, enabling a more robust detection of nonlocality. From the other direction, we investigate the mapping from fixed Bell inequalities to Hamiltonians, aiming to maximize quantum violations while considering experimental imperfections. As a practical demonstration, we apply this method to an XXZ-like honeycomb-lattice model utilizing over 70 superconducting qubits. The successful application of this technique, as well as combining the two directions to form an optimization loop, may open new avenues for developing more practical and noise-resilient nonlocality certification techniques and enable broader experimental explorations.

quant-ph↗

arXiv2024

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for automatically providing stepwise error supervision by creating negative samples of mathematical reasoning rationales that start making errors at a specified step. By applying these samples in DPO training, SCDPO can better align the model to understand reasoning errors and output accurate reasoning steps. We apply SCDPO to both code-integrated and chain-of-thought solutions, empirically showing that it consistently improves the performance compared to naive DPO on three different SFT models, including one existing SFT model and two models we finetuned. Qualitative analysis of the credit assignment of SCDPO and DPO demonstrates the effectiveness of SCDPO at identifying errors in mathematical solutions. We then apply SCDPO to an InternLM2-20B model, resulting in a 20B model that achieves high scores of 88.5% on GSM8K and 58.1% on MATH, rivaling all other open-source LLMs, showing the great potential of our method.

cs.CL↗

arXiv2024

Stability and Dynamics of Atom-Molecule Superfluids Near a Narrow Feshbach Resonance

The recent observations of a stable molecular condensate emerging from a condensate of bosonic atoms and related "super-chemical" dynamics have raised an intriguing set of questions. Here we provide a microscopic understanding of this unexpected stability and dynamics in atom-molecule superfluids; we show one essential element behind these phenomena is an extremely narrow Feshbach resonance in $^{133}$Cs at 19.849G. Comparing theory and experiment we demonstrate how this narrow resonance enables the dynamical creation of a large closed-channel molecular fraction superfluid, appearing in the vicinity of unitarity. Theoretically the observed superchemistry (\textit{i.e.}, Bose enhanced reactions of atoms and molecules), is found to be assisted by the formation of Cooper-like pairs of bosonic atoms that have opposite momenta. Importantly, this narrow resonance opens the possibility to explore the quantum critical point of a molecular Bose superfluid and related phenomena which would not be possible near a more typically broad Feshbach resonance.

cond-mat.quant-gas↗

arXiv2024

A Quantum Automatic Tool for Finding Impossible Differentials

Due to the superiority of quantum computing, traditional cryptography is facing severe threat. This makes the security evaluation of cryptographic systems in quantum attack models significant and urgent. For symmetric ciphers, the security analysis heavily relies on cyptanalytic tools. Thus exploring the use of quantum algorithms to traditional cyptanalytic tools has drawn a lot of attention. In this study, we utilize quantum algorithms to improve impossible differential attack, and design two quantum automatic tools for searching impossible differentials. The proposed quantum algorithms exploit the idea of miss-in-the-middle and the properties of truncated differentials. We rigorously prove their validity and calculate the quantum resources required to implement them. Compared to existing classical automatic cryptanalysis, the quantum tools proposed have the advantage of accurately characterizing S-boxes while only requiring polynomial complexity, and can take into consideration the impact of the key schedules in single-key model.

quant-ph↗

arXiv2024

Simulation-assisted learning of open quantum systems

Models for open quantum systems, which play important roles in electron transport problems and quantum computing, must take into account the interaction of the quantum system with the surrounding environment. Although such models can be derived in some special cases, in most practical situations, the exact models are unknown and have to be calibrated. This paper presents a learning method to infer parameters in Markovian open quantum systems from measurement data. One important ingredient in the method is a direct simulation technique of the quantum master equation, which is designed to preserve the completely-positive property with guaranteed accuracy. The method is particularly helpful in the situation where the time intervals between measurements are large. The approach is validated with error estimates and numerical experiments.

quant-ph↗

arXiv2024

Semi-adaptive Synergetic Two-way Pseudoinverse Learning System

Deep learning has become a crucial technology for making breakthroughs in many fields. Nevertheless, it still faces two important challenges in theoretical and applied aspects. The first lies in the shortcomings of gradient descent based learning schemes which are time-consuming and difficult to determine the learning control hyperparameters. Next, the architectural design of the model is usually tricky. In this paper, we propose a semi-adaptive synergetic two-way pseudoinverse learning system, wherein each subsystem encompasses forward learning, backward learning, and feature concatenation modules. The whole system is trained using a non-gradient descent learning algorithm. It simplifies the hyperparameter tuning while improving the training efficiency. The architecture of the subsystems is designed using a data-driven approach that enables automated determination of the depth of the subsystems. We compare our method with the baselines of mainstream non-gradient descent based methods and the results demonstrate the effectiveness of our proposed method. The source code for this paper is available at http://github.com/B-berrypie/Semi-adaptive-Synergetic-Two-way-Pseudoinverse-Learning-System}{http://github.com/B-berrypie/Semi-adaptive-Synergetic-Two-way-Pseudoinverse-Learning-System.

cs.LG↗

arXiv2024

Towards Stable 3D Object Detection

In autonomous driving, the temporal stability of 3D object detection greatly impacts the driving safety. However, the detection stability cannot be accessed by existing metrics such as mAP and MOTA, and consequently is less explored by the community. To bridge this gap, this work proposes Stability Index (SI), a new metric that can comprehensively evaluate the stability of 3D detectors in terms of confidence, box localization, extent, and heading. By benchmarking state-of-the-art object detectors on the Waymo Open Dataset, SI reveals interesting properties of object stability that have not been previously discovered by other metrics. To help models improve their stability, we further introduce a general and effective training strategy, called Prediction Consistency Learning (PCL). PCL essentially encourages the prediction consistency of the same objects under different timestamps and augmentations, leading to enhanced detection stability. Furthermore, we examine the effectiveness of PCL with the widely-used CenterPoint, and achieve a remarkable SI of 86.00 for vehicle class, surpassing the baseline by 5.48. We hope our work could serve as a reliable baseline and draw the community's attention to this crucial issue in 3D object detection. Codes will be made publicly available.

cs.CV↗

arXiv2024

Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation.

cs.CV↗

arXiv2024

E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion

Online GUI navigation on mobile devices has driven a lot of attention recent years since it contributes to many real-world applications. With the rapid development of large language models (LLM), multimodal large language models (MLLM) have tremendous potential on this task. However, existing MLLMs need high quality data to improve its abilities of making the correct navigation decisions according to the human user inputs. In this paper, we developed a novel and highly valuable dataset, named \textbf{E-ANT}, as the first Chinese GUI navigation dataset that contains real human behaviour and high quality screenshots with annotations, containing nearly 40,000 real human traces over 5000+ different tinyAPPs. Furthermore, we evaluate various powerful MLLMs on E-ANT and show their experiments results with sufficient ablations. We believe that our proposed dataset will be beneficial for both the evaluation and development of GUI navigation and LLM/MLLM decision-making capabilities.

cs.CV↗

arXiv2024

Machine Learning-Assisted 3D Printing of Thermoelectric Materials of Ultrahigh Performances at Room Temperature

Thermoelectric energy conversion is an attractive technology for generating electricity from waste heat and using electricity for solid-state cooling. However, conventional manufacturing processes for thermoelectric devices are costly and limited to simple device geometries. This work reports an extrusion printing method to fabricate high-performance thermoelectric materials with complex 3D architectures. By integrating high-throughput experimentation and Bayesian optimization (BO), our approach significantly accelerates the simultaneous search for the optimal ink formulation and printing parameters that deliver high thermoelectric performances while maintaining desired shape fidelity. A Gaussian process regression (GPR)-based machine learning model is employed to expeditiously predict thermoelectric power factor as a function of ink formulation and printing parameters. The printed bismuth antimony telluride (BiSbTe)-based thermoelectric materials under the optimized conditions exhibit an ultrahigh room temperature zT of 1.3, which is by far the highest in the printed thermoelectric materials. The machine learning-guided ink-based printing strategy can be highly generalizable to a wide range of functional materials and devices for broad technological applications.

physics.app-ph↗

arXiv2024

Forecasting constraints on the no-hair theorem from the stochastic gravitational wave background

Although the constraints on general relativity (GR) from each individual gravitational-wave (GW) event can be combined to form a cumulative estimate of the deviations from GR, the ever-increasing number of GW events used also leads to the ever-increasing computational cost during the parameter estimation. Therefore, in this paper, we will introduce the deviations from GR into GWs from all events in advance and then create a modified stochastic gravitational-wave background (SGWB) to perform tests of GR. More precisely, we use the $\mathtt{pSEOBNRv4HM\_PA}$ model to include the model-independent hairs and calculate the corresponding SGWB with a given merger rate. Then we turn to the Fisher information matrix to forecast the constraints on the no-hair theorem from SGWB at frequency $10[{\rm Hz}]\lesssim f\lesssim10^3[{\rm Hz}]$ detected by the third-generation ground-based GW detectors, such as the Cosmic Explorer. We find that the forecasting constraints on hairs at $68\%$ confidence range are $δω_{220}=0\pm0.1296$ and $δτ_{220}=0\pm0.0678$ when the flat priors about the merger rate are added but $δω_{220}=0\pm0.0903$ and $δτ_{220}=0\pm0.0608$ when the non-flat priors about the merger rate are added.

gr-qc↗