arXiv subjects

Bo Wang

Publications and source records attributed to Bo Wang.

At least 361 records · Page 20Linked to original sources

arXiv2024

Constrain the linear scalar perturbation theory of Cotton gravity

We perform a cosmological test of Cotton gravity, which describes gravity by cotton tensor. We assume in Cotton gravity the background evolution is the same as the flat FLRW background. We derive the cosmological perturbation theory of the scalar mode at the linear level, where the difference from the $Λ$CDM model is characterized by the parameter $β$. We incorporate Cotton gravity with a neutrino model and perform a Monte Carlo Markov Chain (MCMC) analysis using data from the Cosmic Microwave Background (CMB) and Sloan Digital Sky Survey (SDSS). The analysis constrains parameter $β=-0.00008^{+0.00080}_{-0.00104}$ at the 1-$σ$ confidence level. We conclude that currently, there is no obvious deviation between Cotton gravity and the $Λ$CDM model in the linear cosmological perturbation level for observations.

astro-ph.CO↗

arXiv2024

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism

While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing techniques such as compression, summarization, and structuring to facilitate nuanced and efficient handling of large volumes of text. However, existing techniques face challenges with static knowledge integration, leading to insufficient adaptation to task-specific needs and missing multi-segmentation relationships, which hinders the dynamic reorganization and logical combination of relevant segments during the response process. To address these issues, we introduce a novel strategy, Question then Reflection Memory Mechanism (QRMeM), incorporating a dual-structured memory pool. This pool synergizes static textual content with structured graph guidance, fostering a reflective trial-and-error approach for navigating and identifying relevant segments. Our evaluation across multiple-choice questions (MCQ) and multi-document question answering (Multi-doc QA) benchmarks showcases QRMeM enhanced performance compared to existing approaches.

cs.CL↗

arXiv2024

On the Evaluation of Large Language Models in Unit Test Generation

Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.

cs.SE↗

arXiv2024

He-accreting oxygen-neon white dwarfs and accretion-induced collapse events

It has been widely accepted that mass-accreting white dwarfs (WDs) are the progenitors of Type Ia supernovae or electron-capture supernovae. Previous work has shown that the accretion rate could affect the elemental abundance on the outer layers of CO WDs, and therefore affect the observational characteristics after they exploded as SNe Ia. However, it has not been well studied how elemental abundance changes on the outer layers of He-accreting ONe WDs as they approach the Chandrasekhar mass limit. In this paper, we investigated the evolution of He-accreting ONe WDs with MESA. We found that a CO-rich mantle will accumulate beneath the He layers resulting from the He burning, after which the ignition of the CO-rich mantle could transform carbon into silicon (Si). The amount of Si produced by carbon burning is strongly anti-correlated with the accretion rate. As the ONe WD nearly approaches the Chandrasekhar mass limit (Mch) through accretion, it is likely to undergo accretion-induced collapse (AIC), resulting in the formation of the neutron star (NS).

astro-ph.SR↗

arXiv2024

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

Role-playing systems powered by large language models (LLMs) have become increasingly influential in emotional communication applications. However, these systems are susceptible to character hallucinations, where the model deviates from predefined character roles and generates responses that are inconsistent with the intended persona. This paper presents the first systematic analysis of character hallucination from an attack perspective, introducing the RoleBreak framework. Our framework identifies two core mechanisms-query sparsity and role-query conflict-as key factors driving character hallucination. Leveraging these insights, we construct a novel dataset, RoleBreakEval, to evaluate existing hallucination mitigation techniques. Our experiments reveal that even enhanced models trained to minimize hallucination remain vulnerable to attacks. To address these vulnerabilities, we propose a novel defence strategy, the Narrator Mode, which generates supplemental context through narration to mitigate role-query conflicts and improve query generalization. Experimental results demonstrate that Narrator Mode significantly outperforms traditional refusal-based strategies by reducing hallucinations, enhancing fidelity to character roles and queries, and improving overall narrative coherence.

cs.CL↗

arXiv2024

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. We encourage readers to listen to demo audio examples at https://team.doubao.com/seed-music "https://team.doubao.com/seed-music".

cs.SD↗

arXiv2024

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning.

cs.CL↗

arXiv2024

Tracking Any Point with Frame-Event Fusion Network at High Frame Rate

Tracking any point based on image frames is constrained by frame rates, leading to instability in high-speed scenarios and limited generalization in real-world applications. To overcome these limitations, we propose an image-event fusion point tracker, FE-TAP, which combines the contextual information from image frames with the high temporal resolution of events, achieving high frame rate and robust point tracking under various challenging conditions. Specifically, we designed an Evolution Fusion module (EvoFusion) to model the image generation process guided by events. This module can effectively integrate valuable information from both modalities operating at different frequencies. To achieve smoother point trajectories, we employed a transformer-based refinement strategy that updates the point's trajectories and features iteratively. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches, particularly improving expected feature age by 24$\%$ on EDS datasets. Finally, we qualitatively validated the robustness of our algorithm in real driving scenarios using our custom-designed high-resolution image-event synchronization device. Our source code will be released at https://github.com/ljx1002/FE-TAP.

cs.CV↗

arXiv2024

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this work we propose a number of incremental improvements to the ColBERT model architecture and training pipeline, using methods shown to work in the more mature single-vector embedding model training paradigm, particularly those that apply to heterogeneous multilingual data or boost efficiency with little tradeoff. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks.

cs.IR↗

arXiv2024

Strong decays of the isovector-scalar $D^\ast\bar{D}^\ast$ hadronic molecule

We adopt the effective Lagrangian approach to study the strong decays of the $1^-(0^{++})$ $D^\ast\bar{D}^\ast$ molecular state [denoted as $T_{\psi0}^a(4010)$ according to the LHCb naming convention] through triangle diagrams. The decay channels include the open-charm $D\bar{D}$, and the hidden-charm $η_cπ$, $J/ψρ$, and $χ_{c1}π$. The coupling between the $T_{\psi0}^a(4010)$ and its constituents $D^\ast\bar{D}^\ast$ is obtained by solving for the residue of the scattering $T$-matrix at the pole. Our calculations yield a total width of few tens MeV for the $T_{\psi0}^a(4010)$ state using three different form factors, with its main decay channels being $η_cπ$ and $χ_{c1}π$. The $X(4100)$ and $X(4050)$ have similar masses and widths, with both masses being close to the $D^\ast\bar{D}^\ast$ threshold. Additionally, their decay final states are consistent with those of the $T_{\psi0}^a(4010)$. Therefore, it is likely that they represent the same state and both potentially correspond to the $T_{\psi0}^a(4010)$. We suggest that future experiments focus on searching for the $T_{\psi0}^a(4010)$ signal in the final states $η_cπ^-$, $χ_{c1}π^-$ and $D^0D^-$ of the $B^0\toη_cπ^-K^+$, $χ_{c1}π^- K^+$ and $D^0D^-K^+$ processes, respectively, as well as further investigating its resonance parameters with Flatté-like formula.

hep-ph↗

arXiv2024

Physics-Inspired Deep Learning and Transferable Models for Bridge Scour Prediction

This paper introduces scour physics-inspired neural networks (SPINNs), a hybrid physics-data-driven framework for bridge scour prediction using deep learning. SPINNs integrate physics-based, empirical equations into deep neural networks and are trained using site-specific historical scour monitoring data. Long-short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) are considered as the base deep learning (DL) models. We also explore transferable/general models, trained by aggregating datasets from a cluster of bridges, versus the site/bridge-specific models. Despite variation in performance, SPINNs outperformed pure data-driven models in the majority of cases. In some bridge cases, SPINN reduced forecasting errors by up to 50 percent. The pure data-driven models showed better transferability compared to hybrid models. The transferable DL models particularly proved effective for bridges with limited data. In addition, the calibrated time-dependent empirical equations derived from SPINNs showed great potential for maximum scour depth estimation, providing more accurate predictions compared to commonly used HEC-18 model. Comparing SPINNs with traditional empirical models indicates substantial improvements in scour prediction accuracy. This study can pave the way for further exploration of physics-inspired machine learning methods for scour prediction.

cs.LG↗

arXiv2024

Data reconstruction of the dynamical connection function in $f(Q)$ cosmology

We employ Hubble data and Gaussian Processes in order to reconstruct the dynamical connection function in $f(Q)$ cosmology beyond the coincident gauge. In particular, there exist three branches of connections that satisfy the torsionless and curvatureless conditions, parameterized by a new dynamical function $γ$. We express the redshift dependence of $γ$ in terms of the $H(z)$ function and the $f(Q)$ form and parameters, and then we reconstruct it using 55 $H(z)$ observation data. Firstly, we investigate the case where ordinary conservation law holds, and we reconstruct the $f(Q)$ function, which is very well described by a quadratic correction on top of Symmetric Teleparallel Equivalent of General Relativity. Proceeding to the general case, we consider two of the most studied $f(Q)$ models of the literature, namely the square-root and the exponential one. In both cases we reconstruct $γ(z)$, and we show that according to AIC and BIC information criteria its inclusion is favoured compared to both $Λ$CDM paradigm, as well as to the same $f(Q)$ models under the coincident gauge. This feature acts as an indication that $f(Q)$ cosmology should be studied beyond the coincident gauge.

astro-ph.CO↗

arXiv2024

Learning Exposure Correction in Dynamic Scenes

Exposure correction aims to enhance visual data suffering from improper exposures, which can greatly improve satisfactory visual effects. However, previous methods mainly focus on the image modality, and the video counterpart is less explored in the literature. Directly applying prior image-based methods to videos results in temporal incoherence with low visual quality. Through thorough investigation, we find that the development of relevant communities is limited by the absence of a benchmark dataset. Therefore, in this paper, we construct the first real-world paired video dataset, including both underexposure and overexposure dynamic scenes. To achieve spatial alignment, we utilize two DSLR cameras and a beam splitter to simultaneously capture improper and normal exposure videos. Additionally, we propose an end-to-end video exposure correction network, in which a dual-stream module is designed to deal with both underexposure and overexposure factors, enhancing the illumination based on Retinex theory. The extensive experiments based on various metrics and user studies demonstrate the significance of our dataset and the effectiveness of our method. The code and dataset are available at https://github.com/kravrolens/VECNet.

cs.CV↗

arXiv2024

Automatic Organ and Pan-cancer Segmentation in Abdomen CT: the FLARE 2023 Challenge

Organ and cancer segmentation in abdomen Computed Tomography (CT) scans is the prerequisite for precise cancer diagnosis and treatment. Most existing benchmarks and algorithms are tailored to specific cancer types, limiting their ability to provide comprehensive cancer analysis. This work presents the first international competition on abdominal organ and pan-cancer segmentation by providing a large-scale and diverse dataset, including 4650 CT scans with various cancer types from over 40 medical centers. The winning team established a new state-of-the-art with a deep learning-based cascaded framework, achieving average Dice Similarity Coefficient scores of 92.3% for organs and 64.9% for lesions on the hidden multi-national testing set. The dataset and code of top teams are publicly available, offering a benchmark platform to drive further innovations https://codalab.lisn.upsaclay.fr/competitions/12239.

eess.IV↗

arXiv2024

Enhanced Barrier-Smoothing Technique for Bilevel Optimization with Nonsmooth Mappings

Bilevel optimization problems, encountered in fields such as economics, engineering, and machine learning, pose significant computational challenges due to their hierarchical structure and constraints at both upper and lower levels. Traditional gradient-based methods are effective for unconstrained bilevel programs with unique lower level solutions, but struggle with constrained bilevel problems due to the nonsmoothness of lower level solution mappings. To overcome these challenges, this paper introduces the Enhanced Barrier-Smoothing Algorithm (EBSA), a novel approach that integrates gradient-based techniques with an augmented Lagrangian framework. EBSA utilizes innovative smoothing functions to approximate the primal-dual solution mapping of the lower level problem, and then transforms the bilevel problem into a sequence of smooth single-level problems. This approach not only addresses the nonsmoothness but also enhances convergence properties. Theoretical analysis demonstrates its superiority in achieving Clarke and, under certain conditions, Bouligand stationary points for bilevel problems. Both theoretical analysis and preliminary numerical experiments confirm the robustness and efficiency of EBSA.

math.OC↗

arXiv2024

SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation

Sparse view NeRF is challenging because limited input images lead to an under constrained optimization problem for volume rendering. Existing methods address this issue by relying on supplementary information, such as depth maps. However, generating this supplementary information accurately remains problematic and often leads to NeRF producing images with undesired artifacts. To address these artifacts and enhance robustness, we propose SSNeRF, a sparse view semi supervised NeRF method based on a teacher student framework. Our key idea is to challenge the NeRF module with progressively severe sparse view degradation while providing high confidence pseudo labels. This approach helps the NeRF model become aware of noise and incomplete information associated with sparse views, thus improving its robustness. The novelty of SSNeRF lies in its sparse view specific augmentations and semi supervised learning mechanism. In this approach, the teacher NeRF generates novel views along with confidence scores, while the student NeRF, perturbed by the augmented input, learns from the high confidence pseudo labels. Our sparse view degradation augmentation progressively injects noise into volume rendering weights, perturbs feature maps in vulnerable layers, and simulates sparse view blurriness. These augmentation strategies force the student NeRF to recognize degradation and produce clearer rendered views. By transferring the student's parameters to the teacher, the teacher gains increased robustness in subsequent training iterations. Extensive experiments demonstrate the effectiveness of our SSNeRF in generating novel views with less sparse view degradation. We will release code upon acceptance.

cs.CV↗

arXiv2024

Double pole structures of $X_1(2900)$ as the $P$-wave $\bar{D}^K^$ resonances

We reveal the double pole structures of the manifestly exotic tetraquark state $X_1(2900)$ in the scenario of $P$-wave $\bar{D}^*K^*$ dimeson resonance. We find that the observed enhancement signal associated with $X_1(2900)$ in $B^+ \to D^+D^-K^+$ by LHCb contains two $P$-wave poles denoted as $T_{cs1-}(2900)$ and $T^{\prime}_{cs1-}(2900)$, respectively. After considering the channel couplings among the $\bar{D}K$, $\bar{D}^*K$, $\bar{D}K^*$ and $\bar{D}^*K^*$ and the width of the $K^*$ meson, the masses and widths of the $S$-wave pole $T_{cs0+}(2900)$ and two $P$-wave poles $T_{cs1-}(2900)$ and $T^{\prime}_{cs1-}(2900)$ coincide with those of the $X_0(2900)$ and $X_1(2900)$ remarkably, which provides strong support for identifying $X_0(2900)$ and $X_1(2900)$ as $\bar{D}^{(*)}K^{(*)}$ dimeson states. Furthermore, we extensively calculate all $S$-wave and $P$-wave $\bar{D}^{(*)}K^{(*)}$ systems up to $J=3$ and predict four new isoscalar charmed-strange dimeson-type tetraquark states: an $S$-wave state $T_{cs1+}(2900)$ with quantum number $J^P=1^+$, three $P$-wave states $T_{cs1-}(2760)$ with $J^P=1^-$, $T_{cs0-}(2760)$ with $J^P=0^-$ and $T_{cs2-}(2900)$ with $J^P=2^-$. These near-threshold poles can be searched for at LHCb, Belle II and BESIII.

hep-ph↗

arXiv2024

SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model

Large language models (LLMs) have shown remarkable achievements across various language tasks.To enhance the performance of LLMs in scientific literature services, we developed the scientific literature LLM (SciLit-LLM) through pre-training and supervised fine-tuning on scientific literature, building upon the iFLYTEK Spark LLM. Furthermore, we present a knowledge service system Spark Research Assistant (SparkRA) based on our SciLit-LLM. SparkRA is accessible online and provides three primary functions: literature investigation, paper reading, and academic writing. As of July 30, 2024, SparkRA has garnered over 50,000 registered users, with a total usage count exceeding 1.3 million.

cs.CL↗