Search

Large language models (LLMs) have significantly advanced the field of automated code generation. However, a notable research gap exists in the evaluation of social biases that may be present in the code produced by LLMs. To solve this issue, we propose a novel fairness framework, i.e., Solar, to assess and mitigate the social biases of LLM-generated code. Specifically, Solar can automatically generate test cases for quantitatively uncovering social biases of the auto-generated code by LLMs. To quantify the severity of social biases in generated code, we develop a dataset that covers a diverse set of social problems. We applied Solar and the crafted dataset to four state-of-the-art LLMs for code generation. Our evaluation reveals severe bias in the LLM-generated code from all the subject LLMs. Furthermore, we explore several strategies for bias mitigation, including Chain-of-Thought (CoT) prompting, combining positive role-playing with CoT prompting and iterative prompting. Our experiments show that iterative prompting can effectively reduce social bias in LLM-generated code by up to 90%. Solar is highly extensible to evaluate new social problems., Comment: 9pages, 3 figures

Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments demonstrate the superiority of the proposed FedGLS over five baselines., Comment: Accepted by Transactions on Machine Learning Research (TMLR)

We report the discovery of a close binary J0606+2132 (Gaia DR3 3423365496448406272) with $P_{\rm obs}=2.77$ days containing a possible massive white dwarf or a neutron star using the LAMOST spectroscopic data. By a joint fitting of the radial velocity from LAMOST and the light curve from TESS, we derived a circular Keplerian orbit with an inclination of $i=$81.31$^{\circ}$$^{+6.26^{\circ}}_{-7.85^{\circ}}$, which is consistent with that derived from $v{\rm sin}I$. Together with the mass of the visible star, we derived the mass of the invisible object to be 1.34$^{+0.35}_{-0.40} M_{\odot}$. Spectral disentangling with the LAMOST medium-resolution spectra shows no absorption feature from an additional component, suggesting the presence of a compact object. No X-ray or radio pulsed signal is detected from ROSAT and FAST archive observations. J0606+2132 could evolve into either a Type Ia supernova or a neutron star through accretion-induced collapse if it is a white dwarf, or into an intermediate-mass X-ray binary if it is a neutron star., Comment: 17 pages, 8 figures, accepted for publication in APJ

Hallucinations, the tendency to produce irrelevant/incorrect responses, are prevalent concerns in generative AI-based tools like ChatGPT. Although hallucinations in ChatGPT are studied for textual responses, it is unknown how ChatGPT hallucinates for technical texts that contain both textual and technical terms. We surveyed 47 software engineers and produced a benchmark of 412 Q&A pairs from the bug reports of two OSS projects. We find that a RAG-based ChatGPT (i.e., ChatGPT tuned with the benchmark issue reports) is 36.4% correct when producing answers to the questions, due to two reasons 1) limitations to understand complex technical contents in code snippets like stack traces, and 2) limitations to integrate contexts denoted in the technical terms and texts. We present CHIME (ChatGPT Inaccuracy Mitigation Engine) whose underlying principle is that if we can preprocess the technical reports better and guide the query validation process in ChatGPT, we can address the observed limitations. CHIME uses context-free grammar (CFG) to parse stack traces in technical reports. CHIME then verifies and fixes ChatGPT responses by applying metamorphic testing and query transformation. In our benchmark, CHIME shows 30.3% more correction over ChatGPT responses. In a user study, we find that the improved responses with CHIME are considered more useful than those generated from ChatGPT without CHIME.

The ongoing discovery of exoplanets has sparked significant interest in finding suitable worlds that could potentially support life. Stellar ultraviolet (UV; 100-3000 \AA) radiation may play a crucial role in determining the habitability of their planets. In this paper, we conducted a detailed analysis of the UV photometry of over 2700 host stars with confirmed planets, using observational data from the GALEX and Swift UVOT missions. We performed aperture photometry on single-exposure images, and provided photometric catalogs that can be used to explore a wide range of scientific questions, such as stellar UV activity and planet habitability. By calculating the circumstellar habitable zone (CHZ) and UV habitable zone (UHZ), we found that fewer than 100 exoplanets fall within both of these zones, with the majority being gas giants. We also examined stellar activity based on their far-UV (FUV) and near-UV (NUV) emissions. We found the FUV$-$NUV color more effectively represents stellar activity compared to the $R^{\prime}_{\rm FUV}$ and $R^{\prime}_{\rm NUV}$ indices. The Sun's low FUV emission and moderate NUV emission highlight its uniqueness among (solar-like) stars., Comment: 22 pages, 14 figures, 6 tables. Accepted by APJS. Comments welcome!

We report the discovery of a peculiar X-ray transient, EP240408a, by Einstein Probe (EP) and follow-up studies made with EP, Swift, NICER, GROND, ATCA and other ground-based multi-wavelength telescopes. The new transient was first detected with Wide-field X-ray Telescope (WXT) on board EP on April 8th, 2024, manifested in an intense yet brief X-ray flare lasting for 12 seconds. The flare reached a peak flux of 3.9x10^(-9) erg/cm2/s in 0.5-4 keV, about 300 times brighter than the underlying X-ray emission detected throughout the observation. Rapid and more precise follow-up observations by EP/FXT, Swift and NICER confirmed the finding of this new transient. Its X-ray spectrum is non-thermal in 0.5-10 keV, with a power-law photon index varying within 1.8-2.5. The X-ray light curve shows a plateau lasting for about 4 days, followed by a steep decay till becoming undetectable about 10 days after the initial detection. Based on its temporal property and constraints from previous EP observations, an unusual timescale in the range of 7-23 days is found for EP240408a, which is intermediate between the commonly found fast and long-term transients. No counterparts have been found in optical and near-infrared, with the earliest observation at 17 hours after the initial X-ray detection, suggestive of intrinsically weak emission in these bands. We demonstrate that the remarkable properties of EP240408a are inconsistent with any of the transient types known so far, by comparison with, in particular, jetted tidal disruption events, gamma-ray bursts, X-ray binaries and fast blue optical transients. The nature of EP240408a thus remains an enigma. We suggest that EP240408a may represent a new type of transients with intermediate timescales of the order of about 10 days. The detection and follow-ups of more of such objects are essential for revealing their origin., Comment: 25 pages, 11 figures

Neural code models have found widespread success in tasks pertaining to code intelligence, yet they are vulnerable to backdoor attacks, where an adversary can manipulate the victim model's behavior by inserting triggers into the source code. Recent studies indicate that advanced backdoor attacks can achieve nearly 100% attack success rates on many software engineering tasks. However, effective defense techniques against such attacks remain insufficiently explored. In this study, we propose CodePurify, a novel defense against backdoor attacks on code models through entropy-based purification. Entropy-based purification involves the process of precisely detecting and eliminating the possible triggers in the source code while preserving its semantic information. Within this process, CodePurify first develops a confidence-driven entropy-based measurement to determine whether a code snippet is poisoned and, if so, locates the triggers. Subsequently, it purifies the code by substituting the triggers with benign tokens using a masked language model. We extensively evaluate CodePurify against four advanced backdoor attacks across three representative tasks and two popular code models. The results show that CodePurify significantly outperforms four commonly used defense baselines, improving average defense performance by at least 40%, 40%, and 12% across the three tasks, respectively. These findings highlight the potential of CodePurify to serve as a robust defense against backdoor attacks on neural code models.

Distribution shifts on graphs -- the discrepancies in data distribution between training and employing a graph machine learning model -- are ubiquitous and often unavoidable in real-world scenarios. These shifts may severely deteriorate model performance, posing significant challenges for reliable graph machine learning. Consequently, there has been a surge in research on graph machine learning under distribution shifts, aiming to train models to achieve satisfactory performance on out-of-distribution (OOD) test data. In our survey, we provide an up-to-date and forward-looking review of deep graph learning under distribution shifts. Specifically, we cover three primary scenarios: graph OOD generalization, training-time graph OOD adaptation, and test-time graph OOD adaptation. We begin by formally formulating the problems and discussing various types of distribution shifts that can affect graph learning, such as covariate shifts and concept shifts. To provide a better understanding of the literature, we systematically categorize the existing models based on our proposed taxonomy and investigate the adopted techniques behind. We also summarize commonly used datasets in this research area to facilitate further investigation. Finally, we point out promising research directions and the corresponding challenges to encourage further study in this vital domain. Additionally, we provide a continuously updated reading list at https://github.com/kaize0409/Awesome-Graph-OOD., Comment: 18 pages, 2 figures. arXiv admin note: text overlap with arXiv:2402.11153

LEIA (Lobster Eye Imager for Astronomy) detected a new X-ray transient on November 7, 2022, identified as a superflare event occurring on a nearby RS CVn-type binary HD 251108. The flux increase was also detected in follow-up observations at X-ray, UV and optical wavelengths. The flare lasted for about 40 days in soft X-ray observations, reaching a peak luminosity of ~1.1 * 10^34 erg/s in 0.5-4.0 keV, which is roughly 60 times the quiescent luminosity. Optical brightening was observed for only one night. The X-ray light curve is well described by a double "FRED" (fast rise and exponential decay) model, attributed to the cooling process of a loop arcade structure formed subsequent to the initial large loop with a half-length of ~1.9 times the radius of the host star. Time-resolved X-ray spectra were fitted with a two-temperature apec model, showing significant evolution of plasma temperature, emission measure, and metal abundance over time. The estimated energy released in the LEIA band is ~3 * 10^39 erg, suggesting this is likely the most energetic X-ray stellar flare with the longest duration detected to date., Comment: submitted to ApJL, 22 pages, 9 figures, 7 tables

The discrepancies between theoretical and observed spectra, and the systematic differences between various spectroscopic parameter estimates, complicate the determination of atmospheric parameters of M-type stars. In this work, we present an empirical sample of 5105 M-type star spectra with homogeneous atmospheric parameter labels through stellar-label transfer and sample cleaning. We addressed systematic discrepancies in spectroscopic parameter estimates by adopting recent results for Gaia EDR3 stars as a reference standard. Then, we used a density-based spatial clustering of applications with noise to remove unreliable samples in each subgrid of parameters. To confirm the reliability of the stellar labels, a 5-layer neural network was utilized, randomly partitioning the samples into training and testing sets. The standard deviations between the predicted and actual values in the testing set are 14 K for Teff , 0.06 dex for log g, and 0.05 dex for [M/H], respectively. In addition, we conducted an internal cross-validation to enhance validation and obtained precisions of 11 K, 0.05 dex, and 0.05 dex for Teff , log g, and [M/H], respectively. A grid of 1365 high Signal-to-Noise ratio (S/N) spectra and their labels, selected from the empirical sample, was utilized in the stellar parameter pipeline for M-Type stars (LASPM) of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), producing an almost seamless Kiel distribution diagram for LAMOST DR10 and DR11 data. The atmospheric parameters for M-type stars from LAMOST DR11 show improved precision compared to the data from DR9, with improvements (for spectra with S/N higher than 10) from 118 to 67 K in Teff , 0.2 to 0.07 dex in log g, and 0.29 to 0.14 dex in [M/H]., Comment: 28 pages, 23 figures, Journal

Using the LAMOST DR7 low-resolution spectra, we carried out a systematic study of stellar chromospheric activity in both single and binary stars. We constructed a binary sample and a single-star sample, mainly using the binary belt and the main sequence in the Hertzsprung-Russell diagram, respectively. By comparing the $S$ indices between single and binary stars within each color bin, we found for K type stars, binaries exhibit enhanced activity compared to single stars, which could be attributed to the increase in spin rate caused by tidal synchronization or to the interactions of magnetic fields. Both single stars and binaries fall on a common sequence in the activity-period relation, indicating that chromospheric activities of binaries are dominated by the more active components. More intriguingly, in some color ranges, a slight decline of the $S$ index for smaller orbital period was observed for binary stars. Although the possibility of sample selection effects cannot be excluded, this may mark the first example of super-saturation (i.e., caused by reduced active regions) being detected in chromospheric activity, or provide evidence of the suppressing effect on the magnetic dynamo and stellar activities by strong tidal interaction in very close binaries. Our study suggests that tidal interaction acts as a double-edged sword in relation to stellar activities., Comment: 10 pages,7 figures. Accepted for publication in ApJ

Stellar ultraviolet (UV) emission serves as a crucial indicator for estimating magnetic activity and evaluating the habitability of exoplanets orbiting stars. In this paper, we present a straightforward method to derive stellar photospheric UV emission for F to M main-sequence stars. By using PARSEC models, we establish relations between near-UV (NUV) and far-UV (FUV) magnitudes from the Galaxy Evolution Explorer (GALEX), NUV magnitudes from the China Space Station Telescope, and stellar effective temperatures and Gaia BP$-$RP color for different metallicities. Together with the observed sample, we find that for NUV emission, the photospheric contribution to the observed flux is less than 20% for M stars, around 10% to 70% for G stars, and ranges from 30% to 85% for G and F stars. For FUV emission, the photospheric contribution is less than $10^{-6}$ for M stars, below $10^{-4}$ for K stars, around $10^{-4}$ to 10% for G stars, and between 6% and 50% for F stars. Our work enables the simple and effective determination of stellar excess UV emission and the exploration of magnetic activity., Comment: 10 pages, 6 figures, 3 tables. Accepted for publication in ApJ

Human pose estimation aims at locating the specific joints of humans from the images or videos. While existing deep learning-based methods have achieved high positioning accuracy, they often struggle with generalization in occlusion scenarios. In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies. Specifically, the occlusion blocks are at first employed to randomly cover the limb joints of the human bodies from the training images, imitating the scene where the objects or other people partially occlude the human body. Trained by the augmented samples, the pose estimation model is encouraged to accurately locate the occluded keypoints based on the visible ones. To further enhance the localization ability of the model, this paper constructs a dynamic structure loss function based on limb graphs to explore the distribution of occluded joints by evaluating the dependence between adjacent joints. Extensive experimental evaluations on two occluded datasets, OCHuman and CrowdPose, demonstrate significant performance improvements without additional computation cost during inference., Comment: Accept by NCAA

Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. introduced the SWE-bench dataset, which comprises 2,294 real-world GitHub issues and their corresponding pull requests, collected from 12 widely used Python repositories. Several impressive LLM-based toolkits recently are developed and evaluated on this dataset. However, a systematic evaluation of the quality of SWE-bench remains missing. In this paper, we addressed this gap by presenting an empirical analysis of the SWE-bench dataset. We conducted a manual screening of instances where SWEAgent + GPT-4 successfully resolved issues by comparing the model-generated patches with the actual pull requests. SWE-Agent+GPT-4 was at the top of SWE-bench leaderboard during the time of our study. Our analysis reveals some critical issues with the SWE-bench dataset: 1) 32.67% of the successful patches involve cheating as the solutions were directly provided in the issue report or the comments. We refer to as solution leakage problem. 2) 31.08% of the passed patches are suspicious patches due to weak test cases, i.e., the tests were not adequate to verify the correctness of a patch. When we filtered out these problematic issues, the resolution rate of SWE-Agent+GPT-4 dropped from 12.47% to 3.97%. We also observed that the same data quality issues also exist in the two variants of SWE-bench, i.e., SWE-bench Lite and SWE-Bench Verified. In addition, over 94% of the issues were created before LLM's knowledge cutoff dates, posing potential data leakage issues.

Checker bugs in Deep Learning (DL) libraries are critical yet not well-explored. These bugs are often concealed in the input validation and error-checking code of DL libraries and can lead to silent failures, incorrect results, or unexpected program behavior in DL applications. Despite their potential to significantly impact the reliability and performance of DL-enabled systems built with these libraries, checker bugs have received limited attention. We present the first comprehensive study of DL checker bugs in two widely-used DL libraries, i.e., TensorFlow and PyTorch. Initially, we automatically collected a dataset of 2,418 commits from TensorFlow and PyTorch repositories on GitHub from Sept. 2016 to Dec. 2023 using specific keywords related to checker bugs. Through manual inspection, we identified 527 DL checker bugs. Subsequently, we analyzed these bugs from three perspectives, i.e., root causes, symptoms, and fixing patterns. Using the knowledge gained via root cause analysis of checker bugs, we further propose TensorGuard, a proof-of-concept RAG-based LLM-based tool to detect and fix checker bugs in DL libraries via prompt engineering a series of ChatGPT prompts. We evaluated TensorGuard's performance on a test dataset that includes 92 buggy and 135 clean checker-related changes in TensorFlow and PyTorch from January 2024 to July 2024. Our results demonstrate that TensorGuard has high average recall (94.51\%) using Chain of Thought prompting, a balanced performance between precision and recall using Zero-Shot prompting and Few-Shot prompting strategies. In terms of patch generation, TensorGuard achieves an accuracy of 11.1\%, which outperforms the state-of-the-art bug repair baseline by 2\%. We have also applied TensorGuard on the latest six months' checker-related changes (493 changes) of the JAX library from Google, which resulted in the detection of 64 new checker bugs.

An assurance case is a structured set of arguments supported by evidence, demonstrating that a system's non-functional requirements (e.g., safety, security, reliability) have been correctly implemented. Assurance case patterns serve as templates derived from previous successful assurance cases, aimed at facilitating the creation of new assurance cases. Despite the use of these patterns to generate assurance cases, their instantiation remains a largely manual and error-prone process that heavily relies on domain expertise. Thus, exploring techniques to support their automatic instantiation becomes crucial. This study aims to investigate the potential of Large Language Models (LLMs) in automating the generation of assurance cases that comply with specific patterns. Specifically, we formalize assurance case patterns using predicate-based rules and then utilize LLMs, i.e., GPT-4o and GPT-4 Turbo, to automatically instantiate assurance cases from these formalized patterns. Our findings suggest that LLMs can generate assurance cases that comply with the given patterns. However, this study also highlights that LLMs may struggle with understanding some nuances related to pattern-specific relationships. While LLMs exhibit potential in the automatic generation of assurance cases, their capabilities still fall short compared to human experts. Therefore, a semi-automatic approach to instantiating assurance cases may be more practical at this time.

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheless, existing methods usually have strict constraints on the task format, largely limiting their applicability. In this paper, we present Integrative Decoding (ID), to unlock the potential of self-consistency in open-ended generation tasks. ID operates by constructing a set of inputs, each prepended with a previously sampled response, and then processes them concurrently, with the next token being selected by aggregating of all their corresponding predictions at each decoding step. In essence, this simple approach implicitly incorporates self-consistency in the decoding objective. Extensive evaluation shows that ID consistently enhances factuality over a wide range of language models, with substantial improvements on the TruthfulQA (+11.2%), Biographies (+15.4%) and LongFact (+8.5%) benchmarks. The performance gains amplify progressively as the number of sampled responses increases, indicating the potential of ID to scale up with repeated sampling.

Vision-centric semantic occupancy prediction plays a crucial role in autonomous driving, which requires accurate and reliable predictions from low-cost sensors. Although having notably narrowed the accuracy gap with LiDAR, there is still few research effort to explore the reliability in predicting semantic occupancy from camera. In this paper, we conduct a comprehensive evaluation of existing semantic occupancy prediction models from a reliability perspective for the first time. Despite the gradual alignment of camera-based models with LiDAR in term of accuracy, a significant reliability gap persists. To addresses this concern, we propose ReliOcc, a method designed to enhance the reliability of camera-based occupancy networks. ReliOcc provides a plug-and-play scheme for existing models, which integrates hybrid uncertainty from individual voxels with sampling-based noise and relative voxels through mix-up learning. Besides, an uncertainty-aware calibration strategy is devised to further enhance model reliability in offline mode. Extensive experiments under various settings demonstrate that ReliOcc significantly enhances model reliability while maintaining the accuracy of both geometric and semantic predictions. Importantly, our proposed approach exhibits robustness to sensor failures and out of domain noises during inference., Comment: Technical report. Work in progress

Retrieval Augmented Generation (RAG) has shown notable advancements in software engineering tasks. Despite its potential, RAG's application in unit test generation remains under-explored. To bridge this gap, we take the initiative to investigate the efficacy of RAG-based LLMs in test generation. As RAGs can leverage various knowledge sources to enhance their performance, we also explore the impact of different sources of RAGs' knowledge bases on unit test generation to provide insights into their practical benefits and limitations. Specifically, we examine RAG built upon three types of domain knowledge: 1) API documentation, 2) GitHub issues, and 3) StackOverflow Q&As. Each source offers essential knowledge for creating tests from different perspectives, i.e., API documentations provide official API usage guidelines, GitHub issues offer resolutions of issues related to the APIs from the library developers, and StackOverflow Q&As present community-driven solutions and best practices. For our experiment, we focus on five widely used and typical Python-based machine learning (ML) projects, i.e., TensorFlow, PyTorch, Scikit-learn, Google JAX, and XGBoost to build, train, and deploy complex neural networks efficiently. We conducted experiments using the top 10% most widely used APIs across these projects, involving a total of 188 APIs. We investigate the effectiveness of four state-of-the-art LLMs (open and closed-sourced), i.e., GPT-3.5-Turbo, GPT-4o, Mistral MoE 8x22B, and Llamma 3.1 405B. Additionally, we compare three prompting strategies in generating unit test cases for the experimental APIs, i.e., zero-shot, a Basic RAG, and an API-level RAG on the three external sources. Finally, we compare the cost of different sources of knowledge used for the RAG., Comment: 18 pages + reference

Program slicing is a critical technique in software engineering, enabling developers to isolate relevant portions of code for tasks such as bug detection, code comprehension, and debugging. In this study, we investigate the application of large language models (LLMs) to both static and dynamic program slicing, with a focus on Java programs. We evaluate the performance of four state-of-the-art LLMs- GPT-4o, GPT-3.5 Turbo, Llama-2, and Gemma-7B leveraging advanced prompting techniques, including few-shot learning and chain-of-thought reasoning. Using a dataset of 100 Java programs derived from LeetCode problems, our experiments reveal that GPT-4o performs the best in both static and dynamic slicing across other LLMs, achieving an accuracy of 60.84% and 59.69%, respectively. Our results also show that the LLMs we experimented with are yet to achieve reasonable performance for either static slicing or dynamic slicing. Through a rigorous manual analysis, we developed a taxonomy of root causes and failure locations to explore the unsuccessful cases in more depth. We identified Complex Control Flow as the most frequent root cause of failures, with the majority of issues occurring in Variable Declarations and Assignments locations. To improve the performance of LLMs, we further examined two independent strategies for prompting guided by our taxonomy, including prompt crafting, which involved refining the prompts to better guide the LLM through the slicing process, and iterative prompting, where the model receives feedback on the root cause and location of the failure and re-generates its responses. Our evaluation shows these two prompting enhancement approaches can improve accuracy by 4% and 3.9%, respectively.

Online High-Definition (HD) maps have emerged as the preferred option for autonomous driving, overshadowing the counterpart offline HD maps due to flexible update capability and lower maintenance costs. However, contemporary online HD map models embed parameters of visual sensors into training, resulting in a significant decrease in generalization performance when applied to visual sensors with different parameters. Inspired by the inherent potential of Inverse Perspective Mapping (IPM), where camera parameters are decoupled from the training process, we have designed a universal map generation framework, GenMapping. The framework is established with a triadic synergy architecture, including principal and dual auxiliary branches. When faced with a coarse road image with local distortion translated via IPM, the principal branch learns robust global features under the state space models. The two auxiliary branches are a dense perspective branch and a sparse prior branch. The former exploits the correlation information between static and moving objects, whereas the latter introduces the prior knowledge of OpenStreetMap (OSM). The triple-enhanced merging module is crafted to synergistically integrate the unique spatial features from all three branches. To further improve generalization capabilities, a Cross-View Map Learning (CVML) scheme is leveraged to realize joint learning within the common space. Additionally, a Bidirectional Data Augmentation (BiDA) module is introduced to mitigate reliance on datasets concurrently. A thorough array of experimental results shows that the proposed model surpasses current state-of-the-art methods in both semantic mapping and vectorized mapping, while also maintaining a rapid inference speed. The source code will be publicly available at https://github.com/lynn-yu/GenMapping., Comment: The source code will be publicly available at https://github.com/lynn-yu/GenMapping

We investigate the acoustical characteristics of the Chinese transverse flute, the dizi, employing input impedance measurements, modeling and analysis. The input impedances for various fingerings of a bangdi in the key of F, a particular type of the dizi, are measured and compared to models using both the transfer matrix method and the Transfer Matrix Method with external Interaction (TMMI). In order to get more accurate modeling results, we provide specific transfer matrices for the unique components of the dizi, such as back end-holes, membrane hole and upstream branch. The matching volume length correction for holes drilled in a thick wall is also derived. Comparative analysis of modeling and measurement data validates the improved accuracy of TMMI, confirming the influence of radiated sound from closely spaced toneholes., Comment: 11 pages, 11 figures

In this reply, we present a comprehensive analysis addressing the concerns raised by Dehnen et al. (2024) regarding our recent measurement of the disk warp precession using the `motion-picture' method (Huang et al. 2024). We carefully examine the impact of ignoring the twist of the disk warp and the so-called $R$-$\tau$ correlation on the estimation of the precession rate. The results indicate that the effect is minor and does not exceed the systematic and statistical uncertainties. Using N-body+SPH simulation data, we confirm that the `motion-picture' technique is effective in measuring retrograde precession of disk warp in stellar populations younger than 170 Myr, similar to classical Cepheids. Therefore, the overall conclusions of Huang et al. (2024) remain robust., Comment: 4 pages, 2 figures, 1 table, in response to Dehnen et al. (arXiv:2407.06341)

Currently, prompting techniques can be mainly divided into two categories:1)shot method implicitly inspires the model to answer the question by mimicing the steps in the given example, e.g., the few-shot CoT. 2) Guideline method explicitly instructs the model to reason by following guidelines, which contains succinct and concise task-specific knowledge. Shot method is prone to difficulties in terms of selection of shots type, the number of shots, and the design of the reasoning steps, so a question arises: can we only use guideline instead of shot in the prompt? To this end, we propose the FGT framework to automatically learn task-specific guidelines from dataset consisting of Feedback, Guideline, and Tree-gather agents. First, the feedback agent is designed to evaluate the outcomes, both right and wrong, of each Q&A to gather insights guiding more effective optimization strategies. Next, the guideline agent is tasked with deriving guidelines from each piece of feedback and storing them in local memory. Lastly, the tree-gather agent aggregates all guidelines hierarchically through a tree structure, ultimately obtaining all unduplicated guidelines from a global perspective. In addition, we induce the model to generate intermediate processes to ensure the reasoning consistent with the guidelines. Experimental results demonstrate that our approach achieves superior performance across multiple tasks, thereby highlighting the effectiveness of using the guidelines in prompt.

Binary stars are responsible for many unusual astrophysical phenomena, including some important explosive cosmic events. The stability criteria for rapid mass transfer and common-envelope evolution are fundamental to binary star evolution. They determine the mass, mass ratio, and orbital distribution of systems such as X-ray binaries and merging gravitational-wave sources. We use our adiabatic mass-loss model to systematically survey metal-poor and solar-metallicity donor thresholds for dynamical timescale mass transfer. The critical mass ratios qad are systematically explored, and the impact of metallicity and nonconservative mass transfer are studied. For metal-poor radiative-envelope donors, qad are smaller than those for solar-metallicity stars at the same evolutionary stage. However, qad do the opposite for convective-envelope donors. Nonconservative mass transfer significantly decreases qad for massive donors. This is because it matters how conservative mass transfer is during the thermal timescale phase immediately preceding a delayed dynamical mass transfer. We apply our theoretical predictions to observed high-mass X-ray binaries that have overfilled their Roche lobes and find a good agreement with their mass ratios. Our results can be applied to study individual binary objects or large samples of binary objects with binary population synthesis codes., Comment: Submitted to ApJ. Comments are welcome

Large Language Models (LLMs) have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in generating correct code, in an iterative process. While effective, these methods could be costly and time-consuming due to numerous interactions with the LLM and the extensive token usage. To address this issue, we propose an alternative approach named Evolutionary Prompt Engineering for Code (EPiC), which leverages a lightweight evolutionary algorithm to evolve the original prompts toward better ones that produce high-quality code, with minimal interactions with LLM. Our evaluation against state-of-the-art (SOTA) LLM-based code generation models shows that EPiC outperforms all the baselines in terms of cost-effectiveness., Comment: Submitted to TSE

Job marketplace is a heterogeneous graph composed of interactions among members (job-seekers), companies, and jobs. Understanding and modeling job marketplace can benefit both job seekers and employers, ultimately contributing to the greater good of the society. However, existing graph neural network (GNN)-based methods have shallow understandings of the associated textual features and heterogeneous relations. To address the above challenges, we propose PLM4Job, a job marketplace foundation model that tightly couples pretrained language models (PLM) with job market graph, aiming to fully utilize the pretrained knowledge and reasoning ability to model member/job textual features as well as various member-job relations simultaneously. In the pretraining phase, we propose a heterogeneous ego-graph-based prompting strategy to model and aggregate member/job textual features based on the topological structure around the target member/job node, where entity type embeddings and graph positional embeddings are introduced accordingly to model different entities and their heterogeneous relations. Meanwhile, a proximity-aware attention alignment strategy is designed to dynamically adjust the attention of the PLM on ego-graph node tokens in the prompt, such that the attention can be better aligned with job marketplace semantics. Extensive experiments at LinkedIn demonstrate the effectiveness of PLM4Job., Comment: accepted by CIKM'24 applied research track

Implicit representation mapping (IRM) can translate image features to any continuous resolution, showcasing its potent capability for ultra-high-resolution image segmentation refinement. Current IRM-based methods for refining ultra-high-resolution image segmentation often rely on CNN-based encoders to extract image features and apply a Shared Implicit Representation Mapping Function (SIRMF) to convert pixel-wise features into segmented results. Hence, these methods exhibit two crucial limitations. Firstly, the CNN-based encoder may not effectively capture long-distance information, resulting in a lack of global semantic information in the pixel-wise features. Secondly, SIRMF is shared across all samples, which limits its ability to generalize and handle diverse inputs. To address these limitations, we propose a novel approach that leverages the newly proposed Adaptive Implicit Representation Mapping (AIRM) for ultra-high-resolution Image Segmentation. Specifically, the proposed method comprises two components: (1) the Affinity Empowered Encoder (AEE), a robust feature extractor that leverages the benefits of the transformer architecture and semantic affinity to model long-distance features effectively, and (2) the Adaptive Implicit Representation Mapping Function (AIRMF), which adaptively translates pixel-wise features without neglecting the global semantic information, allowing for flexible and precise feature translation. We evaluated our method on the commonly used ultra-high-resolution segmentation refinement datasets, i.e., BIG and PASCAL VOC 2012. The extensive experiments demonstrate that our method outperforms competitors by a large margin. The code is provided in supplementary material.

Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It achieved tenfold and twentyfold reductions in time and cost respectively, and superior consistency with human annotators measured by Cohen's kappa of up to 0.92. The innovative combination of SDoH-GPT and XGBoost leverages the strengths of both, ensuring high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores. Testing across three distinct datasets has confirmed its robustness and accuracy. This study highlights the potential of leveraging LLMs to revolutionize medical note classification, demonstrating their capability to achieve highly accurate classifications with significantly reduced time and cost.

Image inpainting aims to fill missing pixels in damaged images and has achieved significant progress with cut-edging learning techniques. Nevertheless, state-of-the-art inpainting methods are mainly designed for nature images and cannot correctly recover text within scene text images, and training existing models on the scene text images cannot fix the issues. In this work, we identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion: Given a scene text image with unknown missing regions and the corresponding text with unknown missing characters, we aim to complete the missing information in both images and text by leveraging their complementary information. Intuitively, the input text, even if damaged, contains language priors of the contents within the images and can guide the image inpainting. Meanwhile, the scene text image includes the appearance cues of the characters that could benefit text recovery. To this end, we design the cross-modal predictive interaction (CLII) model containing two branches, i.e., ImgBranch and TxtBranch, for scene text inpainting and text completion, respectively while leveraging their complementary effectively. Moreover, we propose to embed our model into the SOTA scene text spotting method and significantly enhance its robustness against missing pixels, which demonstrates the practicality of the newly developed task. To validate the effectiveness of our method, we construct three real datasets based on existing text-related datasets, containing 1838 images and covering three scenarios with curved, incidental, and styled texts, and conduct extensive experiments to show that our method outperforms baselines significantly.

Hallucination, a phenomenon where large language models (LLMs) produce output that is factually incorrect or unrelated to the input, is a major challenge for LLM applications that require accuracy and dependability. In this paper, we introduce a reliable and high-speed production system aimed at detecting and rectifying the hallucination issue within LLMs. Our system encompasses named entity recognition (NER), natural language inference (NLI), span-based detection (SBD), and an intricate decision tree-based process to reliably detect a wide range of hallucinations in LLM responses. Furthermore, our team has crafted a rewriting mechanism that maintains an optimal mix of precision, response time, and cost-effectiveness. We detail the core elements of our framework and underscore the paramount challenges tied to response time, availability, and performance metrics, which are crucial for real-world deployment of these technologies. Our extensive evaluation, utilizing offline data and live production traffic, confirms the efficacy of our proposed framework and service.

We study a novel yet practical problem of open-corpus multi-object tracking (OCMOT), which extends the MOT into localizing, associating, and recognizing generic-category objects of both seen (base) and unseen (novel) classes, but without the category text list as prompt. To study this problem, the top priority is to build a benchmark. In this work, we build OCTrackB, a large-scale and comprehensive benchmark, to provide a standard evaluation platform for the OCMOT problem. Compared to previous datasets, OCTrackB has more abundant and balanced base/novel classes and the corresponding samples for evaluation with less bias. We also propose a new multi-granularity recognition metric to better evaluate the generative object recognition in OCMOT. By conducting the extensive benchmark evaluation, we report and analyze the results of various state-of-the-art methods, which demonstrate the rationale of OCMOT, as well as the usefulness and advantages of OCTrackB.

Fairness-aware graph learning has gained increasing attention in recent years. Nevertheless, there lacks a comprehensive benchmark to evaluate and compare different fairness-aware graph learning methods, which blocks practitioners from choosing appropriate ones for broader real-world applications. In this paper, we present an extensive benchmark on ten representative fairness-aware graph learning methods. Specifically, we design a systematic evaluation protocol and conduct experiments on seven real-world datasets to evaluate these methods from multiple perspectives, including group fairness, individual fairness, the balance between different fairness criteria, and computational efficiency. Our in-depth analysis reveals key insights into the strengths and limitations of existing methods. Additionally, we provide practical guidance for applying fairness-aware graph learning methods in applications. To the best of our knowledge, this work serves as an initial step towards comprehensively understanding representative fairness-aware graph learning methods to facilitate future advancements in this area.

Justifying the correct implementation of the non-functional requirements (e.g., safety, security) of mission-critical systems is crucial to prevent system failure. The later could have severe consequences such as the death of people and financial losses. Assurance cases can be used to prevent system failure, They are structured arguments that allow arguing and relaying various safety-critical systems' requirements extensively as well as checking the compliance of such systems with industrial standards to support their certification. Still, the creation of assurance cases is usually manual, error-prone, and time-consuming. Besides, it may involve numerous alterations as the system evolves. To overcome the bottlenecks in creating assurance cases, existing approaches usually promote the reuse of common structured evidence-based arguments (i.e. patterns) to aid the creation of assurance cases. To gain insights into the advancements of the research on assurance case patterns, we relied on SEGRESS to conduct a bibliometric analysis of 92 primary studies published within the past two decades. This allows capturing the evolutionary trends and patterns characterizing the research in that field. Our findings notably indicate the emergence of new assurance case patterns to support the assurance of ML-enabled systems that are characterized by their evolving requirements (e.g., cybersecurity and ethics).

Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach., Comment: Accepted by TCSVT 2024

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation. However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly. Some recent works have introduced resampler or abstractor to reduce the number of resulting visual tokens. Unfortunately, they fail to capture finer details and undermine the visual reasoning capabilities of MLLMs. In this work, we propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. In specific, we first interpolate the visual features as a low-resolution point query, providing the overall visual representation as the foundation. Then, we introduce a region-to-point injection module that utilizes high-resolution, multi-level region-based cues as fine-grained reference keys and values, allowing them to be fully absorbed within the corresponding local context region. This step effectively updates the coarse point query, transforming it into an enriched one for the subsequent LLM reasoning. Extensive experiments demonstrate that our approach compresses the visual tokens by 75%~89%, while achieves comparable or even better performance across diverse benchmarks with significantly higher efficiency. The source codes can be found at https://github.com/CircleRadon/TokenPacker., Comment: 16 pages, Codes:https://github.com/CircleRadon/TokenPacker

As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets. However, existing bias evaluation efforts often focus on only a particular type of bias and employ inconsistent evaluation metrics, leading to difficulties in comparison across different datasets and LLMs. To address these limitations, we collect a variety of datasets designed for the bias evaluation of LLMs, and further propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks. The curation of CEB is based on our newly proposed compositional taxonomy, which characterizes each dataset from three dimensions: bias types, social groups, and tasks. By combining the three dimensions, we develop a comprehensive evaluation strategy for the bias in LLMs. Our experiments demonstrate that the levels of bias vary across these dimensions, thereby providing guidance for the development of specific bias mitigation methods., Comment: 37 pages, 32 figures

The shape of the dark matter (DM) halo is key to understanding the hierarchical formation of the Galaxy. Despite extensive efforts in recent decades, however, its shape remains a matter of debate, with suggestions ranging from strongly oblate to prolate. Here, we present a new constraint on its present shape by directly measuring the evolution of the Galactic disk warp with time, as traced by accurate distance estimates and precise age determinations for about 2,600 classical Cepheids. We show that the Galactic warp is mildly precessing in a retrograde direction at a rate of $\omega = -2.1 \pm 0.5 ({\rm statistical}) \pm 0.6 ({\rm systematic})$ km s$^{-1}$ kpc$^{-1}$ for the outer disk over the Galactocentric radius [$7.5, 25$] kpc, decreasing with radius. This constrains the shape of the DM halo to be slightly oblate with a flattening (minor axis to major axis ratio) in the range $0.84 \le q_{\Phi} \le 0.96$. Given the young nature of the disk warp traced by Cepheids (less than 200 Myr), our approach directly measures the shape of the present-day DM halo. This measurement, combined with other measurements from older tracers, could provide vital constraints on the evolution of the DM halo and the assembly history of the Galaxy., Comment: Published in Nature Astronomy on June 27th, 2024. Final published version here: https://www.nature.com/articles/s41550-024-02309-5

Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching. In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases by injecting deceptive content into the retrieval database, intentionally changing the model's behavior. This threat is critical as it mirrors real-world usage scenarios where RAG systems interact with publicly accessible knowledge bases, such as web scrapings and user-contributed data pools. To be more realistic, we target a realistic setting where the adversary has no knowledge of users' queries, knowledge base data, and the LLM parameters. We demonstrate that it is possible to exploit the model successfully through crafted content uploads with access to the retriever. Our findings emphasize an urgent need for security measures in the design and deployment of RAG systems to prevent potential manipulation and ensure the integrity of machine-generated content., Comment: Preprint

Few-shot Knowledge Graph (KG) Relational Reasoning aims to predict unseen triplets (i.e., query triplets) for rare relations in KGs, given only several triplets of these relations as references (i.e., support triplets). This task has gained significant traction due to the widespread use of knowledge graphs in various natural language processing applications. Previous approaches have utilized meta-training methods and manually constructed meta-relation sets to tackle this task. Recent efforts have focused on edge-mask-based methods, which exploit the structure of the contextualized graphs of target triplets (i.e., a subgraph containing relevant triplets in the KG). However, existing edge-mask-based methods have limitations in extracting insufficient information from KG and are highly influenced by spurious information in KG. To overcome these challenges, we propose SAFER (Subgraph Adaptation for Few-shot Relational Reasoning), a novel approach that effectively adapts the information in contextualized graphs to various subgraphs generated from support and query triplets to perform the prediction. Specifically, SAFER enables the extraction of more comprehensive information from support triplets while minimizing the impact of spurious information when predicting query triplets. Experimental results on three prevalent datasets demonstrate the superiority of our proposed framework SAFER.

Large Language Models (LLMs) have shown unprecedented performance in various real-world applications. However, they are known to generate factually inaccurate outputs, a.k.a. the hallucination problem. In recent years, incorporating external knowledge extracted from Knowledge Graphs (KGs) has become a promising strategy to improve the factual accuracy of LLM-generated outputs. Nevertheless, most existing explorations rely on LLMs themselves to perform KG knowledge extraction, which is highly inflexible as LLMs can only provide binary judgment on whether a certain knowledge (e.g., a knowledge path in KG) should be used. In addition, LLMs tend to pick only knowledge with direct semantic relationship with the input text, while potentially useful knowledge with indirect semantics can be ignored. In this work, we propose a principled framework KELP with three stages to handle the above problems. Specifically, KELP is able to achieve finer granularity of flexible knowledge extraction by generating scores for knowledge paths with input texts via latent semantic matching. Meanwhile, knowledge paths with indirect semantic relationships with the input text can also be considered via trained encoding between the selected paths in KG and the input text. Experiments on real-world datasets validate the effectiveness of KELP.

H&E-to-IHC stain translation techniques offer a promising solution for precise cancer diagnosis, especially in low-resource regions where there is a shortage of health professionals and limited access to expensive equipment. Considering the pixel-level misalignment of H&E-IHC image pairs, current research explores the pathological consistency between patches from the same positions of the image pair. However, most of them overemphasize the correspondence between domains or patches, overlooking the side information provided by the non-corresponding objects. In this paper, we propose a Mix-Domain Contrastive Learning (MDCL) method to leverage the supervision information in unpaired H&E-to-IHC stain translation. Specifically, the proposed MDCL method aggregates the inter-domain and intra-domain pathology information by estimating the correlation between the anchor patch and all the patches from the matching images, encouraging the network to learn additional contrastive knowledge from mixed domains. With the mix-domain pathology information aggregation, MDCL enhances the pathological consistency between the corresponding patches and the component discrepancy of the patches from the different positions of the generated IHC image. Extensive experiments on two H&E-to-IHC stain translation datasets, namely MIST and BCI, demonstrate that the proposed method achieves state-of-the-art performance across multiple metrics.

Recently, artificial intelligence techniques for education have been received increasing attentions, while it still remains an open problem to design the effective music instrument instructing systems. Although key presses can be directly derived from sheet music, the transitional movements among key presses require more extensive guidance in piano performance. In this work, we construct a piano-hand motion generation benchmark to guide hand movements and fingerings for piano playing. To this end, we collect an annotated dataset, PianoMotion10M, consisting of 116 hours of piano playing videos from a bird's-eye view with 10 million annotated hand poses. We also introduce a powerful baseline model that generates hand motions from piano audios through a position predictor and a position-guided gesture generator. Furthermore, a series of evaluation metrics are designed to assess the performance of the baseline model, including motion similarity, smoothness, positional accuracy of left and right hands, and overall fidelity of movement distribution. Despite that piano key presses with respect to music scores or audios are already accessible, PianoMotion10M aims to provide guidance on piano fingering for instruction purposes. The dataset and source code can be accessed at https://agnjason.github.io/PianoMotion-page., Comment: Codes and Dataset: https://agnjason.github.io/PianoMotion-page

LB-1 is a binary system that has drawn great attention since its discovery in 2019. The nature of the two components of LB-1 is not very clear, which however is suggested very possibly to be a B-type star plus a black hole (BH). In this paper, we first calculate the wind mass-loss rate of the B-type star. We then calculate the mass capture rate by the BH, with which as the initial mass accretion rate, we calculate the truncation radius of the accretion disk and the corresponding emergent spectra of the accretion flow (comprising an inner advection-dominated accretion flow (ADAF) + an outer truncated accretion disk) within the framework of the disk evaporation model. It is found that the predicted truncation radius of the accretion disk with appropriate model parameters is consistent with observations inferred from the observed broad H$_\alpha$ emission line. The predicted X-ray luminosity is definitely below the estimated upper limits with the sensitivity of Chandra X-ray Observatory of the X-ray luminosity $\sim 2\times 10^{31}$ erg/s. Finally, we argue that if the disk evaporation model indeed reflects the intrinsic physics of the accretion flow, the value of the viscosity parameter $\alpha$ is constrained to be $\alpha \gtrsim 0.05$ (with BH mass being $68M_{\rm \odot}$), or $\alpha \gtrsim 0.003$ (with BH mass being $21M_{\rm \odot}$) to match the observed upper limit of the X-ray luminosity of LB-1., Comment: 11 pages, 2 figures. Submitted to The Astrophysical Journal, comments are welcome

In-context learning (ICL) empowers large language models (LLMs) to tackle new tasks by using a series of training instances as prompts. Since generating the prompts needs to sample from a vast pool of instances and annotate them (e.g., add labels in classification task), existing methods have proposed to select a subset of unlabeled examples for annotation, thus enhancing the quality of prompts and concurrently mitigating annotation costs. However, these methods often require a long time to select instances due to their complexity, hindering their practical viability. To address this limitation, we propose a graph-based selection method, FastGAS, designed to efficiently identify high-quality instances while minimizing computational overhead. Initially, we construct a data similarity graph based on instance similarities. Subsequently, employing a graph partitioning algorithm, we partition the graph into pieces. Within each piece (i.e., subgraph), we adopt a greedy approach to pick the most representative nodes. By aggregating nodes from diverse pieces and annotating the corresponding instances, we identify a set of diverse and representative instances for ICL. Compared to prior approaches, our method not only exhibits superior performance on different tasks but also significantly reduces selection time. In addition, we demonstrate the efficacy of our approach in LLMs of larger sizes.

Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13.5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https://github.com/songw-zju/Scribble2Scene., Comment: Accepted by IJCAI2024

Graph Machine Learning (Graph ML) has witnessed substantial advancements in recent years. With their remarkable ability to process graph-structured data, Graph ML techniques have been extensively utilized across diverse applications, including critical domains like finance, healthcare, and transportation. Despite their societal benefits, recent research highlights significant safety concerns associated with the widespread use of Graph ML models. Lacking safety-focused designs, these models can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality. In high-stakes scenarios such as financial fraud detection, these vulnerabilities could jeopardize both individuals and society at large. Therefore, it is imperative to prioritize the development of safety-oriented Graph ML models to mitigate these risks and enhance public confidence in their applications. In this survey paper, we explore three critical aspects vital for enhancing safety in Graph ML: reliability, generalizability, and confidentiality. We categorize and analyze threats to each aspect under three headings: model threats, data threats, and attack threats. This novel taxonomy guides our review of effective strategies to protect against these threats. Our systematic review lays a groundwork for future research aimed at developing practical, safety-centered Graph ML models. Furthermore, we highlight the significance of safe Graph ML practices and suggest promising avenues for further investigation in this crucial area., Comment: 20 pages

Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature redundancy when constructing vectorized High-Definition (HD) maps. In this paper, we revisit the temporal fusion of vectorized HD maps, focusing on temporal instance consistency and temporal map consistency learning. To improve the representation of instances in single-frame maps, we introduce a novel method, DTCLMapper. This approach uses a dual-stream temporal consistency learning module that combines instance embedding with geometry maps. In the instance embedding component, our approach integrates temporal Instance Consistency Learning (ICL), ensuring consistency from vector points and instance features aggregated from points. A vectorized points pre-selection module is employed to enhance the regression efficiency of vector points from each instance. Then aggregated instance features obtained from the vectorized points preselection module are grounded in contrastive learning to realize temporal consistency, where positive and negative samples are selected based on position and semantic information. The geometry mapping component introduces Map Consistency Learning (MCL) designed with self-supervised learning. The MCL enhances the generalization capability of our consistent learning approach by concentrating on the global location and distribution constraints of the instances. Extensive experiments on well-recognized benchmarks indicate that the proposed DTCLMapper achieves state-of-the-art performance in vectorized mapping tasks, reaching 61.9% and 65.1% mAP scores on the nuScenes and Argoverse datasets, respectively. The source code is available at https://github.com/lynn-yu/DTCLMapper., Comment: Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS). The source code is available at https://github.com/lynn-yu/DTCLMapper

Using the homogeneous X-ray catalog from ROSAT observations, we conducted a comprehensive investigation into stellar X-ray activity-rotation relations for both single and binary stars. Generally, the relation for single stars consists of two distinct regions: a weak decay region, indicating a continued dependence of the magnetic dynamo on stellar rotation rather than a saturation regime with constant activity, and a rapid decay region, where X-ray activity is strongly correlated with the Rossby number. Detailed analysis reveals more fine structures within the relation: in the extremely fast rotating regime, a decrease in X-ray activity was observed with increasing rotation rate, referred to as super-saturation, while in the extremely slow rotating region, the relation flattens, mainly due to the scattering of F stars. This scattering may result from intrinsic variability in stellar activities over one stellar cycle or the presence of different dynamo mechanisms. Binaries exhibit a similar relation to that of single stars while the limited sample size prevented the identification of fine structures in the relation for binaries. We calculated the mass loss rates of planetary atmosphere triggered by X-ray emissions from host stars. Our findings indicate that for an Earth-like planet within the stellar habitable zone, it would easily lose its entire primordial H/He envelope (equating to about 1% of the planetary mass)., Comment: 17 pages, 12 figures, ApJS accepted