Search

The 2017 observing campaign of the Event Horizon Telescope (EHT) delivered the first very long baseline interferometry (VLBI) images at the observing frequency of 230 GHz, leading to a number of unique studies on black holes and relativistic jets from active galactic nuclei (AGN). In total, eighteen sources were observed: the main science targets, Sgr A* and M87 along with various calibrators. We investigated the morphology of the sixteen AGN in the EHT 2017 data set, focusing on the properties of the VLBI cores: size, flux density, and brightness temperature. We studied their dependence on the observing frequency in order to compare it with the Blandford-K\"onigl (BK) jet model. We modeled the source structure of seven AGN in the EHT 2017 data set using linearly polarized circular Gaussian components and collected results for the other nine AGN from dedicated EHT publications, complemented by lower frequency data in the 2-86 GHz range. Then, we studied the dependences of the VLBI core flux density, size, and brightness temperature on the frequency measured in the AGN host frame. We compared the observations with the BK jet model and estimated the magnetic field strength dependence on the distance from the central black hole. Our results indicate a deviation from the standard BK model, particularly in the decrease of the brightness temperature with the observing frequency. Either bulk acceleration of the jet material, energy transfer from the magnetic field to the particles, or both are required to explain the observations.

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training paradigm to teach models to first understand non-English questions and then reason. However, this method suffers from both substantial computational resource computing and catastrophic forgetting. The fundamental cause is that, with the primary goal of enhancing multilingual comprehension, an excessive number of irrelevant layers and parameters are tuned during the first stage. Given our findings that the representation learning of languages is merely conducted in lower-level layers, we propose an efficient multilingual reasoning alignment approach that precisely identifies and fine-tunes the layers responsible for handling multilingualism. Experimental results show that our method, SLAM, only tunes 6 layers' feed-forward sub-layers including 6.5-8% of all parameters within 7B and 13B LLMs, achieving superior average performance than all strong baselines across 10 languages. Meanwhile, SLAM only involves one training stage, reducing training time by 4.1-11.9 compared to the two-stage method., Comment: Accepted by COLING 2025 (Oral)

Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is a fundamental requirement in many real-world applications. Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use. In this paper, we propose a novel iterative sampling framework for text length control, integrating the Metropolis-Hastings algorithm with an importance sampling acceleration strategy. This framework efficiently and reliably regulates LLMs to generate length-constrained text without modifying the underlying parameters, thereby preserving the original capabilities of LLMs. Experimental results demonstrate that our framework achieves almost 100\% success rates of length control on Llama3.1 for tasks such as length-controlled abstractive summarization and length-constrained instruction following, with minimal additional computational overhead. This also highlights the significant potential of our method for precise length control across a broader range of applications, without compromising the versatility of LLMs., Comment: Preprint

Current large language models (LLMs) often exhibit imbalances in multilingual capabilities and cultural adaptability, largely due to their English-centric pretraining data. To address this imbalance, we propose a probing method named XTransplant that explores cross-lingual latent interactions via cross-lingual feed-forward transplantation during inference stage, with the hope of enabling the model to leverage the strengths of both English and non-English languages. Through extensive pilot experiments, we empirically prove that both the multilingual capabilities and cultural adaptability of LLMs hold the potential to be significantly improved by XTransplant, respectively from En -> non-En and non-En -> En, highlighting the underutilization of current LLMs' multilingual potential. And the patterns observed in these pilot experiments further motivate an offline scaling inference strategy, which demonstrates consistent performance improvements in multilingual and culture-aware tasks, sometimes even surpassing multilingual supervised fine-tuning. And we do hope our further analysis and discussion could help gain deeper insights into XTransplant mechanism.

Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a benchmark dataset for training the router. Moreover, we formulate Query-Level and Subject-Level approaches based on our framework, and analyze the merits and drawbacks of these two approaches. Finally, we conduct a series of experiments with vary data distributions on both language and multimodal tasks to validate that our proposed Bench-CoE outperforms any single model in terms of overall performance. We hope this method serves as a baseline for further research in this area. The code is available at \url{https://github.com/ZhangXJ199/Bench-CoE}., Comment: The code is available at \url{https://github.com/ZhangXJ199/Bench-CoE}

This paper introduces the task of Remote Sensing Copy-Move Question Answering (RSCMQA). Unlike traditional Remote Sensing Visual Question Answering (RSVQA), RSCMQA focuses on interpreting complex tampering scenarios and inferring relationships between objects. Based on the practical needs of national defense security and land resource monitoring, we have developed an accurate and comprehensive global dataset for remote sensing image copy-move question answering, named RS-CMQA-2.1M. These images were collected from 29 different regions across 14 countries. Additionally, we have refined a balanced dataset, RS-CMQA-B, to address the long-standing issue of long-tail data in the remote sensing field. Furthermore, we propose a region-discriminative guided multimodal CMQA model, which enhances the accuracy of answering questions about tampered images by leveraging prompt about the differences and connections between the source and tampered domains. Extensive experiments demonstrate that our method provides a stronger benchmark for RS-CMQA compared to general VQA and RSVQA models. Our dataset and code are available at https://github.com/shenyedepisa/RSCMQA., Comment: 7 figs, 7 tables

In the regime of Rydberg electromagnetically induced transparency, we study the correlated behaviors between the transmission spectra of a pair of probe fields passing through respective parallel one-dimensional cold Rydberg ensembles. Due to the van der Waals (vdW) interactions between Rydberg atoms, each ensemble exhibits a local optical nonlinearity, where the output EIT spectra are sensitive to both the input probe intensity and the photonic statistics. More interestingly, a nonlocal optical nonlinearity emerges between two spatially separated ensembles, as the probe transmissivity and probe correlation at the exit of one Rydberg ensemble can be manipulated by the probe field at the input of the other Rydberg ensemble. Realizing correlated Rydberg EITs holds great potential for applications in quantum control, quantum network, quantum walk and so on., Comment: 7 pages, 6 figures

The MUltiplexed Survey Telescope (MUST) is a 6.5-meter telescope under development. Dedicated to highly-multiplexed, wide-field spectroscopic surveys, MUST observes over 20,000 targets simultaneously using 6.2-mm pitch positioning robots within a ~5 deg2 field of view. MUST aims to carry out the first Stage-V spectroscopic survey in the 2030s to map the 3D Universe with over 100 million galaxies and quasars, spanning from the nearby Universe to redshift z~5.5, corresponding to around 1 billion years after the Big Bang. To cover this extensive redshift range, we present an initial conceptual target selection algorithm for different types of galaxies, from local bright galaxies, luminous red galaxies, and emission line galaxies to high-redshift (2 < z < 5.5) Lyman-break galaxies. Using Fisher forecasts, we demonstrate that MUST can address fundamental questions in cosmology, including the nature of dark energy, test of gravity theories, and investigations into primordial physics. This is the first paper in the series of science white papers for MUST, with subsequent developments focusing on additional scientific cases such as galaxy and quasar evolution, Milky Way physics, and dynamic phenomena in the time-domain Universe., Comment: To be submitted to SCPMA

Real-world processes involve multiple object types with intricate interrelationships. Traditional event logs (in XES format), which record process execution centred around the case notion, are restricted to a single-object perspective, making it difficult to capture the behaviour of multiple objects and their interactions. To address this limitation, object-centric event logs (OCEL) have been introduced to capture both the objects involved in a process and their interactions with events. The object-centric event data (OCED) metamodel extends the OCEL format by further capturing dynamic object attributes and object-to-object relations. Recently OCEL 2.0 has been proposed based on OCED metamodel. Current research on generating OCEL logs requires specific input data sources, and resulting log data often fails to fully conform to OCEL 2.0. Moreover, the generated OCEL logs vary across different representational formats and their quality remains unevaluated. To address these challenges, a set of quality criteria for evaluating OCEL log representations is established. Guided by these criteria, $\textit{Dirigo}$ is proposed -- a method for extracting event logs that not only conforms to OCEL 2.0 but also extends it by capturing the temporal aspect of dynamic object-to-object relations. Object-role Modelling (ORM), a conceptual data modelling technique, is employed to describe the artifact produced at each step of $\textit{Dirigo}$. To validate the applicability of $\textit{Dirigo}$, it is applied to a real-life use case, extracting an event log via simulation. The quality of the log representation of the extracted event log is compared to those of existing OCEL logs using the established quality criteria.

We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling. Our study reveals that the absence of guidance from discrete boundaries in learning probability contours is one of the main reasons. To address this issue, we propose a two-step forward process that first estimates the boundary as a prior distribution and then rescales the forward trajectory to construct a boundary conditional diffusion model. The reverse process is proportionally adjusted to guarantee that the learned contours yield more precise discrete data. Experimental results indicate that our approach achieves strong performance in both language modeling and discrete image generation tasks. In language modeling, our approach surpasses previous state-of-the-art continuous diffusion language models in three translation tasks and a summarization task, while also demonstrating competitive performance compared to auto-regressive transformers. Moreover, our method achieves comparable results to continuous diffusion models when using discrete ordinal pixels and establishes a new state-of-the-art for categorical image generation on the Cifar-10 dataset., Comment: NeuraIPS 2024 poster

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks for MLLMs show limitations in query quality and evaluation reliability limiting the detection of model safety implications as MLLMs continue to evolve. In this paper, we propose \toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol that aims to address the above limitations, respectively. We first design an automatic safety dataset generation pipeline, where we employ a set of LLM judges to recognize and categorize the risk scenarios that are most harmful and diverse for MLLMs; based on the taxonomy, we further ask these judges to generate high-quality harmful queries accordingly resulting in 23 risk scenarios with 2,300 multi-modal harmful query pairs. During safety evaluation, we draw inspiration from the jury system in judicial proceedings and pioneer the jury deliberation evaluation protocol that adopts collaborative LLMs to evaluate whether target models exhibit specific harmful behaviors, providing a reliable and unbiased assessment of content security risks. In addition, our benchmark can also be extended to the audio modality showing high scalability and potential. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs (e.g., GPT-4o, Gemini), where we revealed widespread safety issues in existing MLLMs and instantiated several insights on MLLM safety performance such as image quality and parameter size.

Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality attribution data, which is costly and labor-intensive. Inspired by recent advances in self-improvement that enhance LLMs without manual annotation, we present START, a Self-Taught AttRibuTion framework for iteratively improving the attribution capability of LLMs. First, to prevent models from stagnating due to initially insufficient supervision signals, START leverages the model to self-construct synthetic training data for warming up. To further self-improve the model's attribution ability, START iteratively utilizes fine-grained preference supervision signals constructed from its sampled responses to encourage robust, comprehensive, and attributable generation. Experiments on three open-domain question-answering datasets, covering long-form QA and multi-step reasoning, demonstrate significant performance gains of 25.13% on average without relying on human annotations and more advanced models. Further analysis reveals that START excels in aggregating information across multiple sources., Comment: Accepted by EMNLP 2024 Main Conference

The first very long baseline interferometry (VLBI) detections at 870$\mu$m wavelength (345$\,$GHz frequency) are reported, achieving the highest diffraction-limited angular resolution yet obtained from the surface of the Earth, and the highest-frequency example of the VLBI technique to date. These include strong detections for multiple sources observed on inter-continental baselines between telescopes in Chile, Hawaii, and Spain, obtained during observations in October 2018. The longest-baseline detections approach 11$\,$G$\lambda$ corresponding to an angular resolution, or fringe spacing, of 19$\mu$as. The Allan deviation of the visibility phase at 870$\mu$m is comparable to that at 1.3$\,$mm on the relevant integration time scales between 2 and 100$\,$s. The detections confirm that the sensitivity and signal chain stability of stations in the Event Horizon Telescope (EHT) array are suitable for VLBI observations at 870$\mu$m. Operation at this short wavelength, combined with anticipated enhancements of the EHT, will lead to a unique high angular resolution instrument for black hole studies, capable of resolving the event horizons of supermassive black holes in both space and time., Comment: Corresponding author: S. Doeleman

Protein function prediction is a crucial task in bioinformatics, with significant implications for understanding biological processes and disease mechanisms. While the relationship between sequence and function has been extensively explored, translating protein structure to function continues to present substantial challenges. Various models, particularly, CNN and graph-based deep learning approaches that integrate structural and functional data, have been proposed to address these challenges. However, these methods often fall short in elucidating the functional significance of key residues essential for protein functionality, as they predominantly adopt a retrospective perspective, leading to suboptimal performance. Inspired by region proposal networks in computer vision, we introduce the Protein Region Proposal Network (ProteinRPN) for accurate protein function prediction. Specifically, the region proposal module component of ProteinRPN identifies potential functional regions (anchors) which are refined through the hierarchy-aware node drop pooling layer favoring nodes with defined secondary structures and spatial proximity. The representations of the predicted functional nodes are enriched using attention mechanisms and subsequently fed into a Graph Multiset Transformer, which is trained with supervised contrastive (SupCon) and InfoNCE losses on perturbed protein structures. Our model demonstrates significant improvements in predicting Gene Ontology (GO) terms, effectively localizing functional residues within protein structures. The proposed framework provides a robust, scalable solution for protein function annotation, advancing the understanding of protein structure-function relationships in computational biology.

The rapid advancement of single-cell ATAC sequencing (scATAC-seq) technologies holds great promise for investigating the heterogeneity of epigenetic landscapes at the cellular level. The amplification process in scATAC-seq experiments often introduces noise due to dropout events, which results in extreme sparsity that hinders accurate analysis. Consequently, there is a significant demand for the generation of high-quality scATAC-seq data in silico. Furthermore, current methodologies are typically task-specific, lacking a versatile framework capable of handling multiple tasks within a single model. In this work, we propose ATAC-Diff, a versatile framework, which is based on a latent diffusion model conditioned on the latent auxiliary variables to adapt for various tasks. ATAC-Diff is the first diffusion model for the scATAC-seq data generation and analysis, composed of auxiliary modules encoding the latent high-level variables to enable the model to learn the semantic information to sample high-quality data. Gaussian Mixture Model (GMM) as the latent prior and auxiliary decoder, the yield variables reserve the refined genomic information beneficial for downstream analyses. Another innovation is the incorporation of mutual information between observed and hidden variables as a regularization term to prevent the model from decoupling from latent variables. Through extensive experiments, we demonstrate that ATAC-Diff achieves high performance in both generation and analysis tasks, outperforming state-of-the-art models.

Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information with the novel data, an instruction-following dataset is meticulously crafted. This dataset is then utilized to fine-tune the LLM, aiming for excelsior generation performance. In the final stage, a tree-like expansion method is deployed to facilitate the generation of arbitrarily long novels. Evaluation against previous methods showcases Ex3's ability to produce higher-quality long-form novels.

Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, have shown potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of citing only coarse document identifiers makes it challenging for users to perform fine-grained verification. In this work, we introduce FRONT, a training framework designed to teach LLMs to generate Fine-Grained Grounded Citations. By grounding model outputs in fine-grained supporting quotes, these quotes guide the generation of grounded and consistent responses, not only improving citation quality but also facilitating fine-grained verification. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT., Comment: Accepted by ACL 2024 Findings

Cross-domain recommendation has attracted substantial interest in industrial apps such as Meituan, which serves multiple business domains via knowledge transfer and meets the diverse interests of users. However, existing methods typically follow an implicit modeling paradigm that blends the knowledge from both the source and target domains, and design intricate network structures to share learned embeddings or patterns between domains to improve recommendation accuracy. Since the transfer of interest signals is unsupervised, these implicit paradigms often struggle with the negative transfer resulting from differences in service functions and presentation forms across different domains. In this paper, we propose a simple and effective EXplicit Interest Transfer framework named EXIT to address the stated challenge. Specifically, we propose a novel label combination approach that enables the model to directly learn beneficial source domain interests through supervised learning, while excluding inappropriate interest signals. Moreover, we introduce a scene selector network to model the interest transfer intensity under fine-grained scenes. Offline experiments conducted on the industrial production dataset and online A/B tests validate the superiority and effectiveness of our proposed framework. Without complex network structures or training processes, EXIT can be easily deployed in the industrial recommendation system. EXIT has been successfully deployed in the online homepage recommendation system of Meituan App, serving the main traffic., Comment: Accepted at CIKM 2024

Although continuous-variable quantum secret sharing (CVQSS) has been theoretically proven to be secure, it may still be vulnerable to various local oscillator (LO)-aimed attacks. To close this loophole, we propose a practical CVQSS scheme using local LO (LLO), which is called LLO-CVQSS. In this scheme, LO is no longer generated by each user but can be locally generated by the legitimate party, i.e., the dealer. This waives the necessity that all LOs have to be transmitted through an untrusted channel, which makes CVQSS system naturally immune to all LO-aimed attacks, greatly enhancing its practical security. We also develop a specially designed phase compensation method for LLO-CVQSS so that the phase noise of the whole system can be eliminated. We finally construct a noise model for LLO-CVQSS and derive its security bound against both eavesdroppers and dishonest users. Numerical simulation shows that LLO-CVQSS is able to support 30 users at the same time and its maximal transmission distance reaches 112 km, revealing that LLO-CVQSS is not only has the ability to defend itself against all LO-aimed attacks but also has the potential for building large-scale practical quantum communication networks., Comment: 13 pages, 7 figures

M-type stars are the ones that flare most frequently, but how big their maximum flare energy can reach is still unknown. We present 163 flares from 162 individual M2 through L1-type stars that triggered the GWAC, with flare energies ranging from $10^{32.2}$ to $10^{36.4}$ erg . The flare amplitudes range from $\triangle G = 0.84$ to $\sim 10$ mag. Flare energy increases with stellar surface temperature ($T_{\rm eff}$) but both $\triangle G$ and equivalent duration $\log_{10}(ED)$ seem to be independent of $T_{\rm eff}$. Combining periods detected from light curves of TESS and K2, spectra from LAMOST, SDSS and the 2.16 m Telescope, and the Gaia DR3 data, we found that these GWAC flare stars are young. For the stars that have spectra, we found that these stars are in or very near to the saturation region, and $\log_{10}(L_{\rm H\alpha}/L_{\rm bol})$ is lower for M7-L1 stars than for M2-M6 stars. We also studied the relation between GWAC flare bolometric energy $E_{\rm bol}$ and stellar hemispherical area $S$, and found that $\log_{10}E_{\rm bol}$ (in erg) increases with increasing $S$ (in cm$^2$), and the maximum flare energy $\log_{10}E_{\rm bol, max} \geqslant \log_{10}S + 14.25$. For M7-L1 stars, there seem to be other factors limiting their maximum flare energies in addition to stellar hemispherical area., Comment: 18 pages, 11 figures, 4 tables

This work addresses the problem of intelligent reflecting surface (IRS) assisted target sensing in a non-line-of-sight (NLOS) scenario, where an IRS is employed to facilitate the radar/access point (AP) to sense the targets when the line-of-sight (LOS) path between the AP and the target is blocked by obstacles. To sense the targets, the AP transmits a train of uniformly-spaced orthogonal frequency division multiplexing (OFDM) pulses, and then perceives the targets based on the echoes from the AP-IRS-targets-IRS-AP channel. To resolve an inherent scaling ambiguity associated with IRS-assisted NLOS sensing, we propose a two-phase sensing scheme by exploiting the diversity in the illumination pattern of the IRS across two different phases. Specifically, the received echo signals from the two phases are formulated as third-order tensors. Then a canonical polyadic (CP) decomposition-based method is developed to estimate each target's parameters including the direction of arrival (DOA), Doppler shift and time delay. Our analysis reveals that the proposed method achieves reliable NLOS sensing using a modest quantity of pulse/subcarrier resources. Simulation results are provided to show the effectiveness of the proposed method under the challenging scenario where the degrees-of-freedom provided by the AP-IRS channel are not enough for resolving the scaling ambiguity.

Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs' subsequent generation. Thus, we raise a question: When presented with a query relevant to the previously generated hallucination, will LVLMs be misled and respond incorrectly, even though the ground visual information exists? To answer this, we propose a framework called MMHalSnowball to evaluate LVLMs' behaviors when encountering generated hallucinations, where LVLMs are required to answer specific visual questions within a curated hallucinatory conversation. Crucially, our experiment shows that the performance of open-source LVLMs drops by at least $31\%$, indicating that LVLMs are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions. We term this phenomenon Multimodal Hallucination Snowballing. To mitigate this, we further propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input, providing models with direct access to the visual information. Experiments show that our method can mitigate more than $24\%$ of the snowballed multimodal hallucination while maintaining capabilities., Comment: Accepted to ACL 2024 Main Conference. 21 pages, 20 figures

Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, much of this research has concentrated on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. This focus has left a significant gap in the exploration of full entity-level unlearning, which is critical in real-world scenarios such as copyright protection. To this end, we propose a novel task of Entity-level unlearning, which aims to erase entity-related knowledge from the target model completely. To thoroughly investigate this task, we systematically evaluate trending unlearning algorithms, revealing that current methods struggle to achieve effective entity-level unlearning. Then, we further explore the factors that influence the performance of the unlearning algorithms, identifying that knowledge coverage and the size of the forget set play pivotal roles. Notably, our analysis also uncovers that entities introduced through fine-tuning are more vulnerable to unlearning than pre-trained entities. These findings collectively offer valuable insights for advancing entity-level unlearning for LLMs., Comment: Accepted by COLING 2025

This paper studies the complexity of matrix Putinar's Positivstellens{\"a}tz on the semialgebraic set that is given by the polynomial matrix inequality. \rev{When the quadratic module generated by the constrained polynomial matrix is Archimedean}, we prove a polynomial bound on the degrees of terms appearing in the representation of matrix Putinar's Positivstellens{\"a}tz. Estimates on the exponent and constant are given. As a byproduct, a polynomial bound on the convergence rate of matrix sum-of-squares relaxations is obtained, which resolves an open question raised by Dinh and Pham. When the constraining set is unbounded, we also prove a similar bound for the matrix version of Putinar--Vasilescu's Positivstellens{\"a}tz by exploiting homogenization techniques.

Advertising platforms have evolved in estimating Lifetime Value (LTV) to better align with advertisers' true performance metric. However, the sparsity of real-world LTV data presents a significant challenge to LTV predictive model(i.e., pLTV), severely limiting the their capabilities. Therefore, we propose to utilize external data, in addition to the internal data of advertising platform, to expand the size of purchase samples and enhance the LTV prediction model of the advertising platform. To tackle the issue of data distribution shift between internal and external platforms, we introduce an Adaptive Difference Siamese Network (ADSNet), which employs cross-domain transfer learning to prevent negative transfer. Specifically, ADSNet is designed to learn information that is beneficial to the target domain. We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer. Additionally, we also design a Domain Adaptation Module as a bridge to connect different domains, reduce the distribution distance between them, and enhance the consistency of representation space distribution. We conduct extensive offline experiments and online A/B tests on a real advertising platform. Our proposed ADSNet method outperforms other methods, improving GINI by 2$\%$. The ablation study highlights the importance of the gain evaluation strategy in negative gain sample rejection and improving model performance. Additionally, ADSNet significantly improves long-tail prediction. The online A/B tests confirm ADSNet's efficacy, increasing online LTV by 3.47$\%$ and GMV by 3.89$\%$., Comment: Accepted to KDD 2024

Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation capacity. We investigate the representation capacity of a network with layerwise composition of linear and LN transformations, referred to as LN-Net. We theoretically show that, given $m$ samples with any label assignment, an LN-Net with only 3 neurons in each layer and $O(m)$ LN layers can correctly classify them. We further show the lower bound of the VC dimension of an LN-Net. The nonlinearity of LN can be amplified by group partition, which is also theoretically demonstrated with mild assumption and empirically supported by our experiments. Based on our analyses, we consider to design neural architecture by exploiting and amplifying the nonlinearity of LN, and the effectiveness is supported by our experiments., Comment: 42 pages, accepted to ICML 2024

Federated Learning(FL) is a privacy-preserving machine learning paradigm where a global model is trained in-situ across a large number of distributed edge devices. These systems are often comprised of millions of user devices and only a subset of available devices can be used for training in each epoch. Designing a device selection strategy is challenging, given that devices are highly heterogeneous in both their system resources and training data. This heterogeneity makes device selection very crucial for timely model convergence and sufficient model accuracy. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement in terms of model coverage and accuracy. In this work, we study the overhead of client selection algorithms in a large scale FL environment. Then we propose an efficient data distribution summary calculation algorithm to reduce the overhead in a real-world large scale FL environment. The evaluation shows that our proposed solution could achieve up to 30x reduction in data summary time, and up to 360x reduction in clustering time.

3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When training two 3D Gaussian radiance fields, we observe that the two radiance fields exhibit point disagreement and rendering disagreement that can unsupervisedly predict reconstruction quality, stemming from the randomness of densification implementation. We further quantify the two disagreements and demonstrate the negative correlation between them and accurate reconstruction, which allows us to identify inaccurate reconstruction without accessing ground-truth information. Based on the study, we propose CoR-GS, which identifies and suppresses inaccurate reconstruction based on the two disagreements: (1) Co-pruning considers Gaussians that exhibit high point disagreement in inaccurate positions and prunes them. (2) Pseudo-view co-regularization considers pixels that exhibit high rendering disagreement are inaccurate and suppress the disagreement. Results on LLFF, Mip-NeRF360, DTU, and Blender demonstrate that CoR-GS effectively regularizes the scene geometry, reconstructs the compact representations, and achieves state-of-the-art novel view synthesis quality under sparse training views., Comment: Accepted at ECCV 2024. Project page: https://jiaw-z.github.io/CoR-GS/

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. Following the design philosophy of the factory pattern in software engineering, TinyLLaVA Factory modularizes the entire system into interchangeable components, with each component integrating a suite of cutting-edge models and methods, meanwhile leaving room for extensions to more features. In addition to allowing users to customize their own LMMs, TinyLLaVA Factory provides popular training recipes to let users pretrain and finetune their models with less coding effort. Empirical experiments validate the effectiveness of our codebase. The goal of TinyLLaVA Factory is to assist researchers and practitioners in exploring the wide landscape of designing and training small-scale LMMs with affordable computational resources., Comment: Our codebase is made public at https://github.com/TinyLLaVA/TinyLLaVA_Factory with documentation available at https://tinyllava-factory.readthedocs.io/en/latest/

Quasi-periodic eruptions (QPEs) are intense repeating soft X-ray bursts with recurrence times about a few hours to a few weeks from galactic nuclei. Though the debates on the origin of QPEs have not completely settled down, more and more analyses favor the interpretation that QPEs are the result of collisions between a stellar mass object (a stellar mass black hole or a main sequence star) and an accretion disk around a supermassive black hole (SMBH) in galactic nuclei. If this interpretation is correct, QPEs will be invaluable in probing the orbits of stellar mass objects in the vicinity of SMBHs, and further inferring the formation of extreme mass ratio inspirals (EMRIs), one of the major targets of spaceborne gravitational wave missions. In this work, we extended the EMRI orbital analysis in Paper I arXiv:2401.11190 to all the known QPE sources with more than $6$ flares observed. Among all the analyzed 5 QPE sources, two distinct EMRI populations are identified: 4 EMRIs are of low orbital eccentricity (consistent with 0) which should be born in the wet EMRI formation channel, and 1 mildly eccentric EMRI (with $e= 0.25^{+0.18}_{-0.20}$ at 2-$\sigma$ confidence level) is consistent with the predictions of both the dry loss-cone formation channel and the Hills mechanism., Comment: 23 pages, 16 figures

This paper studies moment and tensor recovery problems whose decomposing vectors are contained in some given semialgebraic sets. We propose Moment-SOS relaxations with generic objectives for recovering moments and tensors, whose decomposition lengths are expected to be low. This kind of problems have broad applications in various tensor decomposition questions. Numerical experiments are provided to demonstrate the efficiency of this approach.