Search

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain adaptation scenarios where some unlabeled target domain data is available. However, these methods often have limited performance improvement and lack generalization in various mismatch situations. In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning. For prototype contrastive learning, we generate pseudo labels via clustering to create dynamically updated prototype representations, aligning instances with their corresponding class or cluster prototypes. For instance contrastive learning, we minimize the distance between different views or augmentations of the same instance, ensuring robust and invariant representations resilient to variations like noise. This dual-level approach provides both high-level and low-level supervision, leading to improved generalization and robustness of the speaker verification model. Unlike previous studies that only evaluated mismatches in one situation, we have conducted relevant explorations on various datasets and achieved state-of-the-art performance currently, which also proves the generalization of our method., Comment: Accepted to ISCSLP 2024

This paper presents a discrete homotopy theory and a discrete homology theory for finite posets. In particular, the discrete and classical homotopy groups of finite posets are always isomorphic. Moreover, this discrete homology theory is related to the discrete homotopy theory through a discrete analogue of the Hurewicz map.

Human Activity Recognition (HAR) is essential in ubiquitous computing, with far-reaching real-world applications. While recent SOTA HAR research has demonstrated impressive performance, some key aspects remain under-explored. Firstly, HAR can be both highly contextualized and personalized. However, prior work has predominantly focused on being Context-Aware (CA) while largely ignoring the necessity of being User-Aware (UA). We argue that addressing the impact of innate user action-performing differences is equally crucial as considering external contextual environment settings in HAR tasks. Secondly, being user-aware makes the model acknowledge user discrepancies but does not necessarily guarantee mitigation of these discrepancies, i.e., unified predictions under the same activities. There is a need for a methodology that explicitly enforces closer (different user, same activity) representations. To bridge this gap, we introduce CLAUDIA, a novel framework designed to address these issues. Specifically, we expand the contextual scope of the CA-HAR task by integrating User Identification (UI) within the CA-HAR framework, jointly predicting both CA-HAR and UI in a new task called User and Context-Aware HAR (UCA-HAR). This approach enriches personalized and contextual understanding by jointly learning user-invariant and user-specific patterns. Inspired by SOTA designs in the visual domain, we introduce a supervised contrastive loss objective on instance-instance pairs to enhance model efficacy and improve learned feature quality. Evaluation across three real-world CA-HAR datasets reveals substantial performance enhancements, with average improvements ranging from 5.8% to 14.1% in Matthew's Correlation Coefficient and 3.0% to 7.2% in Macro F1 score., Comment: Accepted in ICMLA 2024

We present the results of a search for gravitational-wave transients associated with core-collapse supernova SN 2023ixf, which was observed in the galaxy Messier 101 via optical emission on 2023 May 19th, during the LIGO-Virgo-KAGRA 15th Engineering Run. We define a five-day on-source window during which an accompanying gravitational-wave signal may have occurred. No gravitational waves have been identified in data when at least two gravitational-wave observatories were operating, which covered $\sim 14\%$ of this five-day window. We report the search detection efficiency for various possible gravitational-wave emission models. Considering the distance to M101 (6.7 Mpc), we derive constraints on the gravitational-wave emission mechanism of core-collapse supernovae across a broad frequency spectrum, ranging from 50 Hz to 2 kHz where we assume the GW emission occurred when coincident data are available in the on-source window. Considering an ellipsoid model for a rotating proto-neutron star, our search is sensitive to gravitational-wave energy $1 \times 10^{-5} M_{\odot} c^2$ and luminosity $4 \times 10^{-5} M_{\odot} c^2/\text{s}$ for a source emitting at 50 Hz. These constraints are around an order of magnitude more stringent than those obtained so far with gravitational-wave data. The constraint on the ellipticity of the proto-neutron star that is formed is as low as $1.04$, at frequencies above $1200$ Hz, surpassing results from SN 2019ejj., Comment: Main paper: 6 pages, 4 figures and 1 table. Total with appendices: 20 pages, 4 figures, and 1 table

The global symmetry, either invertible or non-invertible, has been extensively studied in two dimensional conformal field theories in recent years. When the theory is defined on a manifold with open boundaries, however, many interesting conformal boundary conditions will fully or partially break such global symmetry. In this work, we study the effect of symmetry-breaking boundaries or interfaces when the system is out of equilibrium. We show that the boundary or interface symmetry-breaking can be detected by the time evolution of string order parameters, which are constructed from the symmetry operators that implement the symmetry transformations. While the string order parameters are independent of time if the symmetry is preserved over the whole system, they evolve in time in a universal way if the boundary or interface breaks the symmetry. More explicitly, in the presence of boundary or interface symmetry-breaking, the string order parameters decay exponentially in time after a global quantum quench, and decay as a power-law in time after a local quantum quench. We also generalize our study to the case when the string order parameters are defined in a subsystem, which are related to the full counting statistics. It is found there are also universal features in the time evolution of string order parameters in this case. We verify our field theory results by studying the time evolution of these two different types of string order parameters in lattice models., Comment: are welcome. 32 pages, many figures; v2: Refs added

Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. These planners promise better generalizations on complicated and few-shot cases than previous methods. However, experiment results show that many of these approaches produce limited generalization abilities in planning performance due to overly complex designs or training paradigms. In this paper, we review and benchmark previous methods focusing on generalizations. The experimental results indicate that as models are appropriately scaled, many design elements become redundant. We introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner that uses a Vision Transformer (ViT) encoder and a mixture-of-experts (MoE) causal Transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. Furthermore, we assess its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow., Comment: 7 pages, 3 figures

Cooperative path planning, a crucial aspect of multi-agent systems research, serves a variety of sectors, including military, agriculture, and industry. Many existing algorithms, however, come with certain limitations, such as simplified kinematic models and inadequate support for multiple group scenarios. Focusing on the planning problem associated with a nonholonomic Ackermann model for Unmanned Ground Vehicles (UGV), we propose a leaderless, hierarchical Search-Based Cooperative Motion Planning (SCMP) method. The high-level utilizes a binary conflict search tree to minimize runtime, while the low-level fabricates kinematically feasible, collision-free paths that are shape-constrained. Our algorithm can adapt to scenarios featuring multiple groups with different shapes, outlier agents, and elaborate obstacles. We conduct algorithm comparisons, performance testing, simulation, and real-world testing, verifying the effectiveness and applicability of our algorithm. The implementation of our method will be open-sourced at https://github.com/WYCUniverStar/SCMP.

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information remains unexplored with previous research on single LLM's safety be challenging to transfer. In this paper, we focus on the safety of multi-agent networks from a topological perspective, investigating which topological properties contribute to safer networks. To this end, we propose a general framework, NetSafe along with an iterative RelCom interaction to unify existing diverse LLM-based agent frameworks, laying the foundation for generalized topological safety research. We identify several critical phenomena when multi-agent networks are exposed to attacks involving misinformation, bias, and harmful information, termed as Agent Hallucination and Aggregation Safety. Furthermore, we find that highly connected networks are more susceptible to the spread of adversarial attacks, with task performance in a Star Graph Topology decreasing by 29.7%. Besides, our proposed static metrics aligned more closely with real-world dynamic evaluations than traditional graph-theoretic metrics, indicating that networks with greater average distances from attackers exhibit enhanced safety. In conclusion, our work introduces a new topological perspective on the safety of LLM-based multi-agent networks and discovers several unreported phenomena, paving the way for future research to explore the safety of such networks.

The inverse scattering transform for the defocusing-defocusing coupled Hirota equations is strictly discussed with non-zero boundary conditions at infinity including non-parallel boundary conditions, specifically referring to the asymptotic polarization vectors. To address the non-analyticity encountered in some of the Jost eigenfunctions, the "adjoint" Lax pair is employed. The inverse problem is formulated as an appropriate matrix Riemann-Hilbert problem. A key difference between non-parallel and parallel boundary conditions lies in the asymptotic behavior of the scattering coefficients, which significantly impacts the normalization of the eigenfunctions and the properties of sectionally meromorphic matrices within the Riemann-Hilbert problem framework. When the asymptotic polarization vectors are non-orthogonal, two distinct methodologies are introduced to convert the Riemann-Hilbert problem into a series of linear algebraic-integral equations. In contrast, when the asymptotic polarization vectors are orthogonal, only one method is feasible. Ultimately, it is demonstrated that pure soliton solutions do not exist in both orthogonal and non orthogonal polarization vector cases. This study provides a comprehensive framework for analyzing the defocusing-defocusing coupled Hirota equations using the inverse scattering transform, offering new insights into the characteristics and solutions of the equations.

Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, these methods often struggle with controllability, as they lack information from multiple views, leading to incomplete or inconsistent 3D reconstructions. To address this limitation, we introduce LucidFusion, a flexible end-to-end feed-forward framework that leverages the Relative Coordinate Map (RCM). Unlike traditional methods linking images to 3D world thorough pose, LucidFusion utilizes RCM to align geometric features coherently across different views, making it highly adaptable for 3D generation from arbitrary, unposed images. Furthermore, LucidFusion seamlessly integrates with the original single-image-to-3D pipeline, producing detailed 3D Gaussians at a resolution of $512 \times 512$, making it well-suited for a wide range of applications., Comment: 17 pages, 12 figures, [project page](https://heye0507.github.io/LucidFusion_page/)

Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder models from learning robust and generalizable feature representations, particularly for tail classes. In contrast to existing methods, we offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance. In this paper, we investigate this phenomenon through both quantitative and qualitative studies, showing that increased granularity enhances the generalization of learned features in tail categories. Motivated by these findings, we propose a method to increase dataset granularity through category extrapolation. Specifically, we introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes. This forms the core contribution and insight of our approach. To automate the curation of auxiliary data, we leverage large language models (LLMs) as knowledge bases to search for auxiliary categories and retrieve relevant images through web crawling. To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss that encourages the model to focus on class discrimination within the target dataset. During inference, the classifier weights for auxiliary categories are masked out, leaving only the target class weights for use. Extensive experiments and ablation studies on three standard long-tail benchmarks demonstrate the effectiveness of our approach, notably outperforming strong baseline methods that use the same amount of data. The code will be made publicly available.

The task of point cloud upsampling (PCU) is to generate dense and uniform point clouds from sparse input captured by 3D sensors like LiDAR, holding potential applications in real yet is still a challenging task. Existing deep learning-based methods have shown significant achievements in this field. However, they still face limitations in effectively handling long sequences and addressing the issue of shrinkage artifacts around the surface of the point cloud. Inspired by the newly proposed Mamba, in this paper, we introduce a network named MBPU built on top of the Mamba architecture, which performs well in long sequence modeling, especially for large-scale point cloud upsampling, and achieves fast convergence speed. Moreover, MBPU is an arbitrary-scale upsampling framework as the predictor of point distance in the point refinement phase. At the same time, we simultaneously predict the 3D position shift and 1D point-to-point distance as regression quantities to constrain the global features while ensuring the accuracy of local details. We also introduce a fast differentiable renderer to further enhance the fidelity of the upsampled point cloud and reduce artifacts. It is noted that, by the merits of our fast point rendering, MBPU yields high-quality upsampled point clouds by effectively eliminating surface noise. Extensive experiments have demonstrated that our MBPU outperforms other off-the-shelf methods in terms of point cloud upsampling, especially for large-scale point clouds.

Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://github.com/Zaiwen/HNCL-DTI.

This book offers an in-depth exploration of object detection and semantic segmentation, combining theoretical foundations with practical applications. It covers state-of-the-art advancements in machine learning and deep learning, with a focus on convolutional neural networks (CNNs), YOLO architectures, and transformer-based approaches like DETR. The book also delves into the integration of artificial intelligence (AI) techniques and large language models for enhanced object detection in complex environments. A thorough discussion of big data analysis is presented, highlighting the importance of data processing, model optimization, and performance evaluation metrics. By bridging the gap between traditional methods and modern deep learning frameworks, this book serves as a comprehensive guide for researchers, data scientists, and engineers aiming to leverage AI-driven methodologies in large-scale object detection tasks., Comment: 167 pages

Interactions of isolated quantum many-body systems typically scramble local information into the entire system and make it unrecoverable. Ergodicity-breaking systems possess the potential to exhibit fundamentally different information scrambling dynamics beyond this paradigm. For many-body localized systems with strong ergodicity breaking, local transport vanishes and information scrambles logarithmically slowly. Whereas in Rydberg atom arrays, local qubit flips induce dynamical retardation on surrounding qubits through the Rydberg blockade effect, giving rise to quantum many-body scars that weakly break ergodicity, and resulting in the predicted unconventional quantum information spreading behaviours. Here, we present the first measurements of out-of-time-ordered correlators and Holevo information in a Rydberg atom array, enabling us to precisely track quantum information scrambling and transport dynamics. By leveraging these tools, we observe a novel spatio-temporal collapse-and-revival behaviour of quantum information, which differs from both typical chaotic and many-body localized systems. Our experiment sheds light on the unique information dynamics in many-body systems with kinetic constraints, and demonstrates an effective digital-analogue approach to coherently reverse time evolution and steer information propagation in near-term quantum devices., Comment: 12 pages, 6 figures + Supplementary Information 37 pages, 24 figures

The antiferromagnetism in transition metal compounds is mostly mediated by the bridging anions through a so-called superexchange mechanism. However, in materials like normal spinels $AB_2X_4$ with local moments only at the $A$ site, such an anion-mediated superexchange needs to be modified. Here we report a new spinel compound Co$_{1+x}$Ir$_{2-x}$S$_4$ ($x$ = 0.3). The physical property measurements strongly suggest an antiferromagnetic-like transition at 292 K in the Co($A$) diamond sublattice. The first-principle calculations reveal that the nearest-neighbor Co($A$) spins align antiferromagnetically with an ordered magnetic moment of 1.67 $\mu_\mathrm{B}$, smaller than the expected $S = 3/2$ for Co$^{2+}$. In the antiferromagnetic state, there exists an inter-cation charge-transfer gap between the non-bonding Ir-$t_\mathrm{2g}$ orbitals at the valence band maximum and the Co-S antibonding molecular orbitals at the conduction band minimum. The small charge transfer energy significantly enhances the virtual hopping between these two states, facilitating a robust long-range superexchange interaction between two neighboring CoS$_4$ complexes, which accounts for the high N\'{e}el temperature in Co$_{1+x}$Ir$_{2-x}$S$_4$. This inter-cation charge transfer mediated magnetic interaction expands the traditional superexchange theory, which could be applicable in complex magnetic materials with multiple cations., Comment: 10 pages, 7 figures

Magnetic frustration has been recognized as pivotal to investigating new phases of matter in correlation-driven Kondo breakdown quantum phase transitions that are not clearly associated with broken symmetry. The nature of these new phases, however, remains underexplored. Here, we report quantum criticalities emerging from a cluster spin-glass in the heavy-fermion metal TiFe$_x$Cu$_{2x-1}$Sb, where frustration originates from intrinsic disorder. Specific heat and magnetic Gr\"uneisen parameter measurements under varying magnetic fields exhibit quantum critical scaling, indicating a quantum critical point near 0.13 Tesla. As the magnetic field increases, the cluster spin-glass phase is progressively suppressed. Upon crossing the quantum critical point, resistivity and Hall effect measurements reveal enhanced screening of local moments and an expanding Fermi surface, consistent with the Kondo breakdown scenario., Comment: 18 pages, 4 figures, with Supplementary Information

The discrepancies between observations and theoretical predictions of cataclysmic variables (CVs) suggest that there exists unknown angular momentum loss mechanism(s) besides magnetic braking and gravitational radiation. Mass loss due to nova eruptions belongs to the most likely candidates. While standard theory assumes that mass is lost in the form of radiation driven, optically thick wind (fast wind; FW), recent numerical simulations indicate that most of the mass loss is initiated and shaped by binary interaction. We explore the effect of this binary-driven mass-loss (BDML) on the CV evolutions assuming a major fraction of the lost mass leaves the system from the outer Lagrangian point. Different from the traditional continuous wind picture, we consider the mass loss process to be instantaneous, because the duration of nova eruptions is much shorter than the binary evolutionary timescale. Our detailed binary evolution calculations reveal the following results. (1) BDML seems able to provide extra angular momentum loss below the period gap. The mass transfer rates at a given orbital period occupy a large range, in agreement with the observed secular mass transfer rate distribution in CVs. (2) The enhanced mass transfer rates do not lead to runaway mass transfer process, and allow the white dwarfs to grow mass $\lesssim 0.1\,M_{\odot}$. (3) BDML can cause both positive and negative variations of the orbital period induced by nova eruptions, in line with observations, and can potentially explain the properties of some peculiar supersoft X-ray sources likely CAL 87, 1E 0035.4$-$7230, and RX J0537.7$-$7034., Comment: 18 pages, 10 figures, Accepted by ApJ

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems. Despite these advancements in the past few years, LLMs have shown considerable vulnerabilities, particularly to prompt injection and jailbreaking attacks. This review analyzes the state of research on these vulnerabilities and presents available defense strategies. We roughly categorize attack approaches into prompt-based, model-based, multimodal, and multilingual, covering techniques such as adversarial prompting, backdoor injections, and cross-modality exploits. We also review various defense mechanisms, including prompt filtering, transformation, alignment techniques, multi-agent defenses, and self-regulation, evaluating their strengths and shortcomings. We also discuss key metrics and benchmarks used to assess LLM safety and robustness, noting challenges like the quantification of attack success in interactive contexts and biases in existing datasets. Identifying current research gaps, we suggest future directions for resilient alignment strategies, advanced defenses against evolving attacks, automation of jailbreak detection, and consideration of ethical and societal impacts. This review emphasizes the need for continued research and cooperation within the AI community to enhance LLM security and ensure their safe deployment.

One of the tasks in color image processing and computer vision is to recover clean data from partial observations corrupted by noise. To this end, robust quaternion matrix completion (QMC) has recently attracted more attention and shown its effectiveness, whose convex relaxation is to minimize the quaternion nuclear norm plus the quaternion $L_1$-norm. However, there is still room to improve due to the convexity of the convex surrogates. This paper proposes a new nonconvex robust QMC model, in which the nonconvex MCP function and the quaternion $L_p$-norm are used to enhance the low-rankness and sparseness of the low-rank term and sparse term, respectively. An alternating direction method of multipliers (ADMM) algorithm is developed to solve the proposed model and its convergence is given. Moreover, a novel nonlocal-self-similarity-based nonconvex robust quaternion completion method is proposed to handle large-scale data. Numerical results on color images and videos indicate the advantages of the proposed method over some existing ones.

The focus of this work is the study of Parikh matrices with emphasis on two concrete problems. In the first part of our presentation we show that a conjecture by Dick at al. in 2021 only stands in the case of ternary alphabets, while providing counterexamples for larger alphabets. In particular, we show that the only type of distinguishability in the case of 3-letter alphabets is the trivial one. The second part of the paper builds on the notion of Parikh matrices for projections of words, discussed initially in this work, and answers, once more in the case of a ternary alphabet, a question posed by Atanasiu et al. in 2022 with regards to the minimal Hamming distance in between words sharing a congruency class., Comment: Submitted for journal publication

In this Letter, we investigate the turbulence and energy injection in the extended nebulae surrounding two luminous obscured quasars, WISEA J100211.29$+$013706.7 ($z=1.5933$) and SDSS J165202.64$+$172852.3 ($z=2.9489$). Utilizing high-resolution data from the NIRSpec IFU onboard the James Webb Space Telescope, we analyze the velocity fields of line-emitting gas in and around these quasars and construct the second-order velocity structure functions (VSFs) to quantify turbulent motions across different spatial scales. Our findings reveal a notable flattening in the VSFs from $\approx\!3$ kpc up to a scale of 10--20 kpc, suggesting that energy injection predominantly occurs at a scale $\lesssim$10 kpc, likely powered by quasar outflows and jet-driven bubbles. The extended spatial range of flat VSFs may also indicate the presence of multiple energy injection sources at these scales. For J1652, the turbulent energy in the host interstellar medium (ISM) is significantly higher than in tidally stripped gas, consistent with the expectation of active galactic nucleus (AGN) activities stirring up the host ISM. Compared to the VSFs observed on spatial scales of 10--50 kpc around lower-redshift UV-bright quasars, these obscured quasars exhibit higher turbulent energies in their immediate surroundings, implying different turbulence drivers between the ISM and halo-scale gas. Future studies with an expanded sample are essential to elucidate further the extent and the pivotal role of AGNs in shaping the gas kinematics of host galaxies and beyond., Comment: 10 pages, 4 figures; submitted; comments welcome!

In light of recent experimental data indicating a substantial thermal Hall effect in square lattice antiferromagnetic Mott insulators, we investigate whether a simple Mott insulator can sustain a finite thermal Hall effect. We verify that the answer is "no" if one performs calculations within a spin-only low-energy effective spin model with non-interacting magnons. However, by performing determinant quantum Monte Carlo simulations, we show the single-band $t$-$t'$-$U$ Hubbard model coupled to an orbital magnetic field does support a finite thermal Hall effect when $t' \neq 0$ and $B \neq 0$ in the Mott insulating phase. We argue that the (carrier agnostic) necessary conditions for observing a finite thermal Hall effect are time-reversal and particle-hole symmetry breaking. By considering magnon-magnon scattering using a semi-classical Boltzmann analysis, we illustrate a physical mechanism by which finite transverse thermal conductivity may arise, consistent with our symmetry argument and numerical results. Our results contradict the conventional wisdom that square and triangular lattices with SU(2) symmetry do not support a finite thermal Hall effect and call for a critical re-examination of thermal Hall effect data in insulating magnets, as the magnon contribution should not be excluded a priori., Comment: 6+23 pages, 3+11 figures

Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or repetitive RL training. To address these issues, we propose CARD, a LLM-driven Reward Design framework that iteratively generates and improves reward function code. Specifically, CARD includes a Coder that generates and verifies the code, while a Evaluator provides dynamic feedback to guide the Coder in improving the code, eliminating the need for human feedback. In addition to process feedback and trajectory feedback, we introduce Trajectory Preference Evaluation (TPE), which evaluates the current reward function based on trajectory preferences. If the code fails the TPE, the Evaluator provides preference feedback, avoiding RL training at every iteration and making the reward function better aligned with the task objective. Empirical results on Meta-World and ManiSkill2 demonstrate that our method achieves an effective balance between task performance and token efficiency, outperforming or matching the baselines across all tasks. On 10 out of 12 tasks, CARD shows better or comparable performance to policies trained with expert-designed rewards, and our method even surpasses the oracle on 3 tasks.

Multi-modal entity alignment (MMEA) is essential for enhancing knowledge graphs and improving information retrieval and question-answering systems. Existing methods often focus on integrating modalities through their complementarity but overlook the specificity of each modality, which can obscure crucial features and reduce alignment accuracy. To solve this, we propose the Multi-modal Consistency and Specificity Fusion Framework (MCSFF), which innovatively integrates both complementary and specific aspects of modalities. We utilize Scale Computing's hyper-converged infrastructure to optimize IT management and resource allocation in large-scale data processing. Our framework first computes similarity matrices for each modality using modality embeddings to preserve their unique characteristics. Then, an iterative update method denoises and enhances modality features to fully express critical information. Finally, we integrate the updated information from all modalities to create enriched and precise entity representations. Experiments show our method outperforms current state-of-the-art MMEA baselines on the MMKG dataset, demonstrating its effectiveness and practical potential., Comment: 6 pages, 1 figures

Quantum resource distillation is a fundamental task in quantum information science. Minimizing the distillation overhead, i.e., the amount of noisy source states required to produce some desired output state within some target error, is crucial for the scalability of quantum computation and communication. Here, we show that quantum catalysts -- an additional resource that facilitates the transformation but remains unchanged before and after the process -- can help surpass previously known fundamental limitations on distillation overhead. Specifically, we show that multi-shot distillation protocols can be converted into one-shot catalytic protocols, which hold significant practical benefits, while maintaining the distillation overhead. In particular, in the context of magic state distillation, our result indicates that the code-based low-overhead distillation protocols that rely on divergingly large batches can be promoted to the one-shot setting where the batch volume can be arbitrarily small for any accuracy. Combining with very recent results on asymptotically good quantum codes with transversal non-Clifford gates, we demonstrate that magic state distillation with constant overhead can be achieved with controllable output size using catalytic protocols. Furthermore, we demonstrate that catalysis enables a spacetime trade-off between overhead and success probability. Notably, we show that the optimal constant for constant-overhead catalytic magic state distillation can be reduced to $1$ at the price of compromising the success probability by a constant factor. Finally, we present an illustrative example that extends the catalysis techniques to the study of dynamic quantum resources. This provides the channel mutual information with a one-shot operational interpretation, thereby addressing an open question posed by Wilming., Comment: 13 pages, 3 figures; comments are welcome

Quasar feedback may play a key role in the evolution of massive galaxies. The dust-reddened quasar, F2M110648.35$+$480712 at $z = 0.4352$ is one of the few cases at its redshift that exhibits powerful quasar feedback through bipolar outflows. Our new observation with the integral field unit mode of Near-infrared Spectrograph onboard JWST opens a new window to examine this spectacular outflow through Pa$\alpha$ emission line with $\sim$3$\times$ better spatial resolution than previous work. The morphology and kinematics of the Pa$\alpha$ nebula confirm the existence of a bipolar outflow extending on a scale of $\sim$17$\times$14 kpc and with a velocity reaching $\sim$1100 km s$^{-1}$. The higher spatial resolution of our new observation leads to more reliable measurements of outflow kinematics. Considering only the spatially resolved outflow and assuming an electron density of 100 cm$^{-2}$, the mass, momentum and kinetic energy outflow rates are $\sim$50-210 M$_{\odot}$ yr$^{-1}$, $\sim$0.3-1.7$\times$10$^{36}$ dynes ($\sim$14-78\% of the quasar photon momentum flux) and $\sim$0.16-1.27$\times$10$^{44}$ erg s$^{-1}$ ($\sim$0.02-0.20\% of the quasar bolometric luminosity), respectively. The local instantaneous outflow rates generally decrease radially. We infer that the quasar is powerful enough to drive the outflow, while stellar processes cannot be overlooked as a contributing energy source. The mass outflow rate is $\sim$0.4-1.5 times the star formation rate, and the ratio of kinetic energy outflow rate to the quasar bolometric luminosity is comparable to the minimum value required for negative quasar feedback in simulations. This outflow may help regulate the star formation activity within the system to some extent., Comment: 14 pages, 6 figures, 1 table, ApJ in review

Passive visible light communication (VLC) modulates light propagation or reflection to transmit data without directly modulating the light source. Thus, passive VLC provides an alternative to conventional VLC, enabling communication where the light source cannot be directly controlled. There have been ongoing efforts to explore new methods and devices for modulating light propagation or reflection. The state-of-the-art has broken the 100 kbps data rate barrier for passive VLC by using a digital micro-mirror device (DMD) as the light modulating platform, or transmitter, and a photo-diode as the receiver. We significantly extend this work by proposing a massive spatial data channel framework for DMDs, where individual channels can be decoded in parallel using an event camera at the receiver. For the event camera, we introduce event processing algorithms to detect numerous channels and decode bits from individual channels with high reliability. Our prototype, built with off-the-shelf event cameras and DMDs, can decode up to $\sim$2,000 parallel channels, achieving a data transmission rate of 1.6 Mbps, markedly surpassing current benchmarks by 16x., Comment: 14 pages, 21 figures, nonacm

In this paper, we study the system-level advantages provided by rateless coding, early termination and power allocation strategy for multiple users distributed across multiple cells. In a multi-cell scenario, the early termination of coded transmission not only reduces finite-length loss akin to the single-user scenario but also yields capacity enhancements due to the cancellation of interference across cells. We term this technique \emph{coded water-filling}, a concept that diverges from traditional water-filling by incorporating variable-length rateless coding and interference cancellation. We formulate a series of analytical models to quantify the gains associated with coded water-filling in multi-user scenarios. First, we analyze the capacity gains from interference cancellation in Additive White Gaussian Noise (AWGN) channels, which arises from the disparity in the number of bits transmitted by distinct users. Building upon this, we broaden our analysis to encompass fading channels to show the robustness of the interference cancellation algorithms. Finally, we address the power allocation problem analogous to the water-filling problem under a multi-user framework, proving that an elevation in the water-filling threshold facilitates overall system capacity enhancement. Our analysis reveals the capacity gains achievable through early termination and power allocation techniques in multi-user settings. These results show that coded water-filling is instrumental for further improving spectral efficiency in crowded spectrums.

Bilevel optimization, crucial for hyperparameter tuning, meta-learning and reinforcement learning, remains less explored in the decentralized learning paradigm, such as decentralized federated learning (DFL). Typically, decentralized bilevel methods rely on both gradients and Hessian matrices to approximate hypergradients of upper-level models. However, acquiring and sharing the second-order oracle is compute and communication intensive. % and sharing this information incurs heavy communication overhead. To overcome these challenges, this paper introduces a fully first-order decentralized method for decentralized Bilevel optimization, $\text{C}^2$DFB which is both compute- and communicate-efficient. In $\text{C}^2$DFB, each learning node optimizes a min-min-max problem to approximate hypergradient by exclusively using gradients information. To reduce the traffic load at the inner-loop of solving the lower-level problem, $\text{C}^2$DFB incorporates a lightweight communication protocol for efficiently transmitting compressed residuals of local parameters. % during the inner loops. Rigorous theoretical analysis ensures its convergence % of the algorithm, indicating a first-order oracle calls of $\tilde{\mathcal{O}}(\epsilon^{-4})$. Experiments on hyperparameter tuning and hyper-representation tasks validate the superiority of $\text{C}^2$DFB across various typologies and heterogeneous data distributions., Comment: 19 Pages

This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The distinct properties of the proposed ROI-based correspondence are discussed, in the context of potential benefits in clinical applications following image registration, compared with alternative correspondence-representing approaches, such as those based on sampled displacements and spatial transformation functions. These benefits include a clear connection between learning-based image registration and segmentation, which in turn motivates two cases of image registration approaches using (pre-)trained segmentation networks. Based on the segment anything model (SAM), a vision foundation model for segmentation, we develop a new registration algorithm SAMReg, which does not require any training (or training data), gradient-based fine-tuning or prompt engineering. The proposed SAMReg models are evaluated across five real-world applications, including intra-subject registration tasks with cardiac MR and lung CT, challenging inter-subject registration scenarios with prostate MR and retinal imaging, and an additional evaluation with a non-clinical example with aerial image registration. The proposed methods outperform both intensity-based iterative algorithms and DDF-predicting learning-based networks across tested metrics including Dice and target registration errors on anatomical structures, and further demonstrates competitive performance compared to weakly-supervised registration approaches that rely on fully-segmented training data. Open source code and examples are available at: https://github.com/sqhuang0103/SAMReg.git.

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models like LLaVA, projected visual tokens are prepended to textual tokens. Oftentimes, visual tokens are significantly more than prompt tokens, resulting in increased computational overhead during both training and inference. In this paper, we propose Visual Compact Token Registers (Victor), a method that reduces the number of visual tokens by summarizing them into a smaller set of register tokens. Victor adds a few learnable register tokens after the visual tokens and summarizes the visual information into these registers using the first few layers in the language tower of VLMs. After these few layers, all visual tokens are discarded, significantly improving computational efficiency for both training and inference. Notably, our method is easy to implement and requires a small number of new trainable parameters with minimal impact on model performance. In our experiment, with merely 8 visual registers--about 1% of the original tokens--Victor shows less than a 4% accuracy drop while reducing the total training time by 43% and boosting the inference throughput by 3.3X.

Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function, and can therefore be thought of as the sequential generalization of a Generative Adversarial Network (GAN). A prominent example of this framework is Generative Adversarial Imitation Learning (GAIL). However, in recent years, diffusion models have emerged as a non-adversarial alternative to GANs that merely require training a score function via regression, yet produce generations of a higher quality. In response, we investigate how to lift insights from diffusion modeling to the sequential setting. We propose diffusing states and performing score-matching along diffused states to measure the discrepancy between the expert's and learner's states. Thus, our approach only requires training score functions to predict noises via standard regression, making it significantly easier and more stable to train than adversarial methods. Theoretically, we prove first- and second-order instance-dependent bounds with linear scaling in the horizon, proving that our approach avoids the compounding errors that stymie offline approaches to imitation learning. Empirically, we show our approach outperforms GAN-style imitation learning baselines across various continuous control problems, including complex tasks like controlling humanoids to walk, sit, and crawl.

In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both tasks, such as Chameleon. However, due to the differing levels of information granularity required by multimodal understanding and generation, this approach can lead to suboptimal performance, particularly in multimodal understanding. To address this issue, we decouple visual encoding into separate pathways, while still leveraging a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder's roles in understanding and generation, but also enhances the framework's flexibility. For instance, both the multimodal understanding and generation components can independently select their most suitable encoding methods. Experiments show that Janus surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models., Comment: Technical Report

Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation, which refers to the scheme to select frames from a video and further select the tokens from a frame. In this paper, we explore the design space for visual context representation, and aim to improve the performance of video MLLMs by finding more effective representation schemes. Firstly, we formulate the task of visual context representation as a constrained optimization problem, and model the language modeling loss as a function of the number of frames and the number of embeddings (or tokens) per frame, given the maximum visual context window size. Then, we explore the scaling effects in frame selection and token selection respectively, and fit the corresponding function curve by conducting extensive empirical experiments. We examine the effectiveness of typical selection strategies and present empirical findings to determine the two factors. Furthermore, we study the joint effect of frame selection and token selection, and derive the optimal formula for determining the two factors. We demonstrate that the derived optimal settings show alignment with the best-performed results of empirical experiments. Our code and model are available at: https://github.com/RUCAIBox/Opt-Visor., Comment: Long Video MLLM; work in progress

For metaplectic groups over a local field of characteristic zero, we define the Arthur packet attached to any Arthur parameter $\psi$ as a multi-set of unitary genuine irreducible representations, characterized by endoscopic character relations. Over number fields, we obtain a multiplicity formula for the genuine discrete $L^2$-automorphic spectrum in terms of global Arthur parameters and $\epsilon$-factors, by leveraging the trace formula for metaplectic groups. This confirms a conjecture of Gan, and extends earlier results of Gan-Ichino on the Shimura-Waldspurger correspondences, whereas their works play a critical role in our proof. Furthermore, all these are shown to be compatible with existing results in rank one (Waldspurger) and two (Gan-Ichino)., Comment: 90 pages with an index. Minor improvements

Semantic segmentation of remote sensing (RS) images is a challenging yet crucial task. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field, acquiring high-quality labeled data is expensive and time-consuming. Additionally, variations in ground sampling distance, imaging equipment, and geographic differences cause domain shifts between datasets, which limit model performance across domains. Unsupervised domain adaptation (UDA) offers a solution by enabling models to learn from unlabeled target domain data while training on labeled source domain data. Recent self-supervised learning approaches using pseudo-label generation have shown promise in addressing domain discrepancies. Combining source and target images with their true and pseudo labels has proven effective in reducing domain bias. However, the use of pseudo-labeling for RS image segmentation is underexplored. Existing methods often rely on high-confidence pixel points as pseudo-labels, reducing supervision in low-confidence areas. Noise in pseudo-labels further weakens the model's ability to learn target domain semantics. While some methods assign confidence weights, noisy pseudo-labels remain an issue. To address these limitations, we propose integrating contrastive learning into UDA, enhancing the model's capacity to capture semantic information by maximizing the similarity between augmented views of the same image. This provides additional supervision to improve performance in the target domain. Extensive experiments on key RS datasets (Potsdam, Vaihingen, LoveDA) demonstrate that our SimSeg method outperforms existing approaches, achieving state-of-the-art results. Visualization and quantitative analyses confirm its superior ability to learn from the target domain. The code is available at \url{https://github.com/woldier/SiamSeg}.

Citation intention Classification (CIC) tools classify citations by their intention (e.g., background, motivation) and assist readers in evaluating the contribution of scientific literature. Prior research has shown that pretrained language models (PLMs) such as SciBERT can achieve state-of-the-art performance on CIC benchmarks. PLMs are trained via self-supervision tasks on a large corpus of general text and can quickly adapt to CIC tasks via moderate fine-tuning on the corresponding dataset. Despite their advantages, PLMs can easily overfit small datasets during fine-tuning. In this paper, we propose a multi-task learning (MTL) framework that jointly fine-tunes PLMs on a dataset of primary interest together with multiple auxiliary CIC datasets to take advantage of additional supervision signals. We develop a data-driven task relation learning (TRL) method that controls the contribution of auxiliary datasets to avoid negative transfer and expensive hyper-parameter tuning. We conduct experiments on three CIC datasets and show that fine-tuning with additional datasets can improve the PLMs' generalization performance on the primary dataset. PLMs fine-tuned with our proposed framework outperform the current state-of-the-art models by 7% to 11% on small datasets while aligning with the best-performing model on a large dataset., Comment: To be appear as a Findings paper at EMNLP 2024

Lieb excitations are fundamental to the understanding of the low energy behaviour of many-body quantum gases. Here we study the spectral function of a Tonks-Girardeau gas in a finite sized Kronig-Penney potential and show that the Lieb-I and Lieb-II excitations can become gapped as a function of the barrier height. Moreover, we reveal the existence of a topological flat mode near the Fermi energy and at zero momentum and show that this is robust to perturbations in the system. Through a scaling analysis, we determine the divergent behaviour of the spectral function. Our results provide a significant reference for the observation and understanding of the gapped Lieb excitations and the topological flat mode of quantum gases in experimentally realistic subwavelength optical lattice potentials.

Deterministic creation of quantum emitters with high single-photon-purity and excellent indistinguishability is essential for practical applications in quantum information science. Many successful attempts have been carried out in hexagonal boron nitride showing its capability of hosting room temperature quantum emitters. However, most of the existing methods produce emitters with heterogeneous optical properties and unclear creation mechanisms. Here, the authors report a deterministic creation of identical room temperature quantum emitters using masked-carbon-ion implantation on freestanding hBN flakes. Quantum emitters fabricated by our approach showed thermally limited monochromaticity with an emission center wavelength distribution of 590.7 +- 2.7 nm, a narrow full width half maximum of 7.1 +- 1.7 nm, excellent brightness (1MHz emission rate), and extraordinary stability. Our method provides a reliable platform for characterization and fabrication research on hBN based quantum emitters, helping to reveal the origins of the single-photon-emission behavior in hBN and favoring practical applications, especially the industrial-scale production of quantum technology., Comment: 29 pages, 5 figures, research article

Pre-training foundation models has become the de-facto procedure for deep learning approaches, yet its application remains limited in the geological studies, where in needs of the model transferability to break the shackle of data scarcity. Here we target on the X-ray fluorescence (XRF) scanning data, a standard high-resolution measurement in extensive scientific drilling projects. We propose a scalable self-supervised learner, masked autoencoders on XRF spectra (MAX), to pre-train a foundation model covering geological records from multiple regions of the Pacific and Southern Ocean. In pre-training, we find that masking a high proportion of the input spectrum (50\%) yields a nontrivial and meaningful self-supervisory task. For downstream tasks, we select the quantification of XRF spectra into two costly geochemical measurements, CaCO$_3$ and total organic carbon, due to their importance in understanding the paleo-oceanic carbon system. Our results show that MAX, requiring only one-third of the data, outperforms models without pre-training in terms of quantification accuracy. Additionally, the model's generalizability improves by more than 60\% in zero-shot tests on new materials, with explainability further ensuring its robustness. Thus, our approach offers a promising pathway to overcome data scarcity in geological discovery by leveraging the self-supervised foundation model and fast-acquired XRF scanning data.

Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and is designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PersonalityBench, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI.

This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy to predict two sets of actions: one for maximizing task rewards in simulation and another specifically for domain adaptation via reward adjustments. This decoupling makes it easier to maximize the overall reward in the source domain during training. Additionally, DAP incorporates uncertainty-based exploration during training to enhance agent robustness. Experimental results demonstrate DAP's effectiveness in bridging the sim-to-real gap, outperforming baselines on challenging tasks in simulation, and further improvement is achieved by incorporating uncertainty estimation.

Offline Reinforcement Learning (RL) offers an attractive alternative to interactive data acquisition by leveraging pre-existing datasets. However, its effectiveness hinges on the quantity and quality of the data samples. This work explores the use of more readily available, albeit off-dynamics datasets, to address the challenge of data scarcity in Offline RL. We propose a novel approach using conditional Diffusion Probabilistic Models (DPMs) to learn the joint distribution of the large-scale off-dynamics dataset and the limited target dataset. To enable the model to capture the underlying dynamics structure, we introduce two contexts for the conditional model: (1) a continuous dynamics score allows for partial overlap between trajectories from both datasets, providing the model with richer information; (2) an inverse-dynamics context guides the model to generate trajectories that adhere to the target environment's dynamic constraints. Empirical results demonstrate that our method significantly outperforms several strong baselines. Ablation studies further reveal the critical role of each dynamics context. Additionally, our model demonstrates that by modifying the context, we can interpolate between source and target dynamics, making it more robust to subtle shifts in the environment.

Deploying a safe mobile robot policy in scenarios with human pedestrians is challenging due to their unpredictable movements. Current Reinforcement Learning-based motion planners rely on a single policy to simulate pedestrian movements and could suffer from the over-fitting issue. Alternatively, framing the collision avoidance problem as a multi-agent framework, where agents generate dynamic movements while learning to reach their goals, can lead to conflicts with human pedestrians due to their homogeneity. To tackle this problem, we introduce an efficient method that enhances agent diversity within a single policy by maximizing an information-theoretic objective. This diversity enriches each agent's experiences, improving its adaptability to unseen crowd behaviors. In assessing an agent's robustness against unseen crowds, we propose diverse scenarios inspired by pedestrian crowd behaviors. Our behavior-conditioned policies outperform existing works in these challenging scenes, reducing potential collisions without additional time or travel.

For decades, the Bj{\o}ntegaard Delta (BD) has been the metric for evaluating codec Rate-Distortion (R-D) performance. Yet, in most studies, BD is determined using just 4-5 R-D data points, could this be sufficient? As codecs and quality metrics advance, does the conventional BD estimation still hold up? Crucially, are the performance improvements of new codecs and tools genuine, or merely artifacts of estimation flaws? This paper addresses these concerns by reevaluating BD estimation. We present a novel approach employing a parameterized deep neural network to model R-D curves with high precision across various metrics, accompanied by a comprehensive R-D dataset. This approach both assesses the reliability of BD calculations and serves as a precise BD estimator. Our findings advocate for the adoption of rigorous R-D sampling and reliability metrics in future compression research to ensure the validity and reliability of results.

Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration. Current research focuses on detecting the anomalies after they occur, which can lead to significant financial/reputation loss or infrastructure damage. In this work we instead study a more practical yet very challenging problem, time series anomaly prediction, aiming at providing early warnings for abnormal events before their occurrence. To tackle this problem, we introduce a novel principled approach, namely future context modeling (FCM). Its key insight is that the future abnormal events in a target window can be accurately predicted if their preceding observation window exhibits any subtle difference to normal data. To effectively capture such differences, FCM first leverages long-term forecasting models to generate a discriminative future context based on the observation data, aiming to amplify those subtle but unusual difference. It then models a normality correlation of the observation data with the forecasting future context to complement the normality modeling of the observation data in foreseeing possible abnormality in the target window. A joint variate-time attention learning is also introduced in FCM to leverage both temporal signals and features of the time series data for more discriminative normality modeling in the aforementioned two views. Comprehensive experiments on five datasets demonstrate that FCM gains good recall rate (70\%+) on multiple datasets and significantly outperforms all baselines in F1 score. Code is available at https://github.com/mala-lab/FCM., Comment: 11 pages, 5 figures, submitted to KDD conference

Multivariate time-series data in fields like healthcare and industry are informative but challenging due to high dimensionality and lack of labels. Recent self-supervised learning methods excel in learning rich representations without labels but struggle with disentangled embeddings and inductive bias issues like transformation-invariance. To address these challenges, we introduce TimeDRL, a framework for multivariate time-series representation learning with dual-level disentangled embeddings. TimeDRL features: (i) disentangled timestamp-level and instance-level embeddings using a [CLS] token strategy; (ii) timestamp-predictive and instance-contrastive tasks for representation learning; and (iii) avoidance of augmentation methods to eliminate inductive biases. Experiments on forecasting and classification datasets show TimeDRL outperforms existing methods, with further validation in semi-supervised settings with limited labeled data., Comment: This submission has been withdrawn to avoid duplication with a full version of the paper that is already available in another arXiv entry (arXiv:2410.12606). The withdrawn version was a short format prepared for a NeurIPS workshop and is no longer necessary as a separate arXiv submission

Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for model fine-tuning. To address this issue, we propose LR-SQL. LR-SQL comprises two supervised fine-tuning models: the schema\_link model and the SQL\_generation model, with the schema\_link model serving as the focal point for streamlining the overall process. During the fine-tuning of the schema\_link model, LR-SQL breaks down the complete database into flexible combinations of tables with adjustable quantities, enabling the model to learn the relationships within the entire database from these dispersed slices. Furthermore, to enhance the model's ability to perceive the relationships among various discrete slices during inference, LR-SQL trains the model's Chain-of-Thought capability for this task. Experimental results demonstrate that LR-SQL can reduce the total GPU memory usage by 40\% compared to existing fine-tuning methods, while only losing 2\% of table prediction accuracy in schema\_link task. For the overall Text2SQL task, the Execution Accuracy decrease by 0.6\%.Our project is now available on https://github.com/hongWin/LR-SQL, Comment: 12pages, 4 figures,submitting to a journal

Due to powerful ability to learn representations from unlabeled graphs, graph contrastive learning (GCL) has shown excellent performance in community detection tasks. Existing GCL-based methods on the community detection usually focused on learning attribute representations of individual nodes, which, however, ignores structure semantics of communities (e.g., nodes in the same community should be close to each other). Therefore, in this paper, we will consider the semantics of community structures for the community detection, and propose an effective framework of graph contrastive learning under structure semantics (GCLS$^2$) for detecting communities. To seamlessly integrate interior dense and exterior sparse characteristics of communities with our contrastive learning strategy, we employ classic community structures to extract high-level structural views and design a structure semantic expression module to augment the original structural feature representation. Moreover, we formulate the structure contrastive loss to optimize the feature representation of nodes, which can better capture the topology of communities. Extensive experiments have been conducted on various real-world graph datasets and confirmed that GCLS$^2$ outperforms eight state-of-the-art methods, in terms of the accuracy and modularity of the detected communities.