Search

Recent text-to-image models have achieved remarkable success in generating high-quality images. However, when tasked with multi-concept generation which creates images containing multiple characters or objects, existing methods often suffer from attribute confusion, resulting in severe text-image inconsistency. We found that attribute confusion occurs when a certain region of the latent features attend to multiple or incorrect prompt tokens. In this work, we propose novel Semantic Protection Diffusion (SPDiffusion) to protect the semantics of regions from the influence of irrelevant tokens, eliminating the confusion of non-corresponding attributes. In the SPDiffusion framework, we design a Semantic Protection Mask (SP-Mask) to represent the relevance of the regions and the tokens, and propose a Semantic Protection Cross-Attention (SP-Attn) to shield the influence of irrelevant tokens on specific regions in the generation process. To evaluate our method, we created a diverse multi-concept benchmark, and SPDiffusion achieves state-of-the-art results on this benchmark, proving its effectiveness. Our method can be combined with many other application methods or backbones, such as ControlNet, Story Diffusion, PhotoMaker and PixArt-alpha to enhance their multi-concept capabilities, demonstrating strong compatibility and scalability.

Effective stormwater treatment infrastructures are crucial for mitigating the adverse effects of runoff on urban water quality. However, designing cost-effective treatment systems can be challenging due to complex turbulent flow dynamics. This study presents an in-depth analysis of turbulent flow in hydrodynamic separators (HS) using time-resolving, high-resolution particle image velocimetry (PIV) and modal decomposition techniques. The examination of interrogation window sizes on PIV measurements highlights a trade-off between spatial resolution and measurement uncertainty. Additionally, the impact of sampling frequencies and durations on the convergence of turbulence statistics, such as mean flow and Reynolds stress, is quantified. Results indicate that higher-order statistics require significantly larger sampling sizes (5x) to achieve the same level of statistical convergence as mean flow statistics. Leveraging proper orthogonal decomposition (POD) and spectral proper orthogonal decomposition (SPOD), dominant turbulence structures and coherent flow features are identified, providing a foundation for the development of reduced-order models (ROM). These ROMs demonstrate improved computational efficiency and have potential for real-time control applications and integration into larger drainage-scale simulations. Furthermore, the outcome of this study establishes a high-quality, open-source turbulent flow database for HS systems, offering the civil and environmental engineering community valuable resources to guide the development and application of computational fluid dynamics (CFD) tools. This study represents a critical step toward the ultimate goal of facilitating scientifically guided HS design and optimization., Comment: 33 pages, 16 figure, submitted to Journal of Environmental Engineering

Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SEACrowd, a collaborative initiative that consolidates a comprehensive resource hub that fills the resource gap by providing standardized corpora in nearly 1,000 SEA languages across three modalities. Through our SEACrowd benchmarks, we assess the quality of AI models on 36 indigenous languages across 13 tasks, offering valuable insights into the current AI landscape in SEA. Furthermore, we propose strategies to facilitate greater AI advancements, maximizing potential utility and resource equity for the future of AI in SEA., Comment: https://github.com/SEACrowd

Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain representation and resulting in performance degradation on unseen domains. Besides, abundant data from multiple domains are needed. To address these issues, in this work, we propose prompt-based visual alignment (PVA), a robust framework to mitigate the detrimental domain bias in the image for zero-shot policy transfer. Inspired that Visual-Language Model (VLM) can serve as a bridge to connect both text space and image space, we leverage the semantic information contained in a text sequence as an explicit constraint to train a visual aligner. Thus, the visual aligner can map images from multiple domains to a unified domain and achieve good generalization performance. To better depict semantic information, prompt tuning is applied to learn a sequence of learnable tokens. With explicit constraints of semantic information, PVA can learn unified cross-domain representation under limited access to cross-domain data and achieves great zero-shot generalization ability in unseen domains. We verify PVA on a vision-based autonomous driving task with CARLA simulator. Experiments show that the agent generalizes well on unseen domains under limited access to multi-domain data., Comment: This paper has been accepted by ICML2024

In this paper, we apply the coordinate increment discrete gradient (CIDG) method to solve the Lorentz force system which can be written as a non-canonical Hamiltonian system. Then we can obtain a new energy-preserving CIDG-I method for the system. The CIDG-I method can combine with its adjoint method CIDG-II which is also a energy-preserving method to form a new method, namely CIDG-C method. The CIDG-C method is symmetrical and can conserve the Hamiltonian energy directly and exactly. With comparison to the well-used Boris method, numerical experiments indicate that the CIDG-C method holds advantage over the Boris method in terms of energy-conserving., Comment: The Fig. 5(b) in the original paper contains an error. We submit the correct Fig. 5(b) and an errata in this paper, which is described in remark4.1

Electric vertical-takeoff and landing (eVTOL) aircraft, recognized for their maneuverability and flexibility, offer a promising alternative to our transportation system. However, the operational effectiveness of these aircraft faces many challenges, such as the delicate balance between energy and time efficiency, stemming from unpredictable environmental factors, including wind fields. Mathematical modeling-based approaches have been adopted to plan aircraft flight path in urban wind fields with the goal to save energy and time costs. While effective, they are limited in adapting to dynamic and complex environments. To optimize energy and time efficiency in eVTOL's flight through dynamic wind fields, we introduce a novel path planning method leveraging deep reinforcement learning. We assess our method with extensive experiments, comparing it to Dijkstra's algorithm -- the theoretically optimal approach for determining shortest paths in a weighted graph, where weights represent either energy or time cost. The results show that our method achieves a graceful balance between energy and time efficiency, closely resembling the theoretically optimal values for both objectives.

Events are essential components of speech and texts, describing the changes in the state of entities. The event extraction task aims to identify and classify events and find their participants according to event schemas. Manually predefined event schemas have limited coverage and are hard to migrate across domains. Therefore, the researchers propose Liberal Event Extraction (LEE), which aims to extract events and discover event schemas simultaneously. However, existing LEE models rely heavily on external language knowledge bases and require the manual development of numerous rules for noise removal and knowledge alignment, which is complex and laborious. To this end, we propose a Prompt-based Graph Model for Liberal Event Extraction (PGLEE). Specifically, we use a prompt-based model to obtain candidate triggers and arguments, and then build heterogeneous event graphs to encode the structures within and between events. Experimental results prove that our approach achieves excellent performance with or without predefined event schemas, while the automatically detected event schemas are proven high quality.

Events describe the state changes of entities. In a document, multiple events are connected by various relations (e.g., Coreference, Temporal, Causal, and Subevent). Therefore, obtaining the connections between events through Event-Event Relation Extraction (ERE) is critical to understand natural language. There are two main problems in the current ERE works: a. Only embeddings of the event triggers are used for event feature representation, ignoring event arguments (e.g., time, place, person, etc.) and their structure within the event. b. The interconnection between relations (e.g., temporal and causal relations usually interact with each other ) is ignored. To solve the above problems, this paper proposes a jointly multiple ERE framework called GraphERE based on Graph-enhanced Event Embeddings. First, we enrich the event embeddings with event argument and structure features by using static AMR graphs and IE graphs; Then, to jointly extract multiple event relations, we use Node Transformer and construct Task-specific Dynamic Event Graphs for each type of relation. Finally, we used a multi-task learning strategy to train the whole framework. Experimental results on the latest MAVEN-ERE dataset validate that GraphERE significantly outperforms existing methods. Further analyses indicate the effectiveness of the graph-enhanced event embeddings and the joint extraction strategy.

Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance. This paper, not only as an overview of current prompt engineering methods, but also aims to highlight the limitation of designing prompts based on an anthropomorphic assumption that expects LLMs to think like humans. From our review of 50 representative studies, we demonstrate that a goal-oriented prompt formulation, which guides LLMs to follow established human logical thinking, significantly improves the performance of LLMs. Furthermore, We introduce a novel taxonomy that categorizes goal-oriented prompting methods into five interconnected stages and we demonstrate the broad applicability of our framework. With four future directions proposed, we hope to further emphasize the power and potential of goal-oriented prompt engineering in all fields., Comment: An up-to-date resource including papers and tasks is maintained at https://github.com/Alex-HaochenLi/Goal-oriented-Prompt-Engineering

In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the principal challenge of modality misalignment between code snippets and natural language queries, particularly with the demonstrated code generation capabilities of Large Language Models (LLMs). Nevertheless, our preliminary investigations indicate that the improvements conferred by such an LLM-augmented framework are somewhat constrained. This limitation could potentially be ascribed to the fact that the generated codes, albeit functionally accurate, frequently display a pronounced stylistic deviation from the ground truth code in the codebase. In this paper, we extend the foundational GAR framework and propose a simple yet effective method that additionally Rewrites the Code (ReCo) within the codebase for style normalization. Experimental results demonstrate that ReCo significantly boosts retrieval accuracy across sparse (up to 35.7%), zero-shot dense (up to 27.6%), and fine-tuned dense (up to 23.6%) retrieval settings in diverse search scenarios. To further elucidate the advantages of ReCo and stimulate research in code style normalization, we introduce Code Style Similarity, the first metric tailored to quantify stylistic similarities in code. Notably, our empirical findings reveal the inadequacy of existing metrics in capturing stylistic nuances. The source code and data are available at \url{https://github.com/Alex-HaochenLi/ReCo}., Comment: Accepted to ACL 2024

A near-field integrated sensing, positioning, and communication (ISPAC) framework is proposed, where a base station (BS) simultaneously serves multiple communication users and carries out target sensing and positioning. A novel double-array structure is proposed to enable the near-field ISPAC at the BS. Specifically, a small-scale assisting transceiver (AT) is attached to the large-scale main transceiver (MT) to empower the communication system with the ability of sensing and positioning. Based on the proposed framework, the joint angle and distance Cram\'er-Rao bound (CRB) is first derived. Then, the CRB is minimized subject to the minimum communication rate requirement in both downlink and uplink ISPAC scenarios: 1) For downlink ISPAC, a downlink target positioning algorithm is proposed and a penalty dual decomposition (PDD)-based double-loop algorithm is developed to tackle the non-convex optimization problem. 2) For uplink ISPAC, an uplink target positioning algorithm is proposed and an efficient alternating optimization algorithm is conceived to solve the non-convex CRB minimization problem with coupled user communication and target probing design. Both proposed optimization algorithms can converge to a stationary point of the CRB minimization problem. Numerical results show that: 1) The proposed ISPAC system can locate the target in both angle and distance domains merely relying on single BS and limited bandwidths; and 2) the positioning performance achieved by the hybrid-analog-and-digital ISPAC approaches that achieved by fully digital ISPAC when the communication rate requirement is not stringent., Comment: 13 pages, 6 figures

Recently, contrastive learning has become a key component in fine-tuning code search models for software development efficiency and effectiveness. It pulls together positive code snippets while pushing negative samples away given search queries. Among contrastive learning, InfoNCE is the most widely used loss function due to its better performance. However, the following problems in negative samples of InfoNCE may deteriorate its representation learning: 1) The existence of false negative samples in large code corpora due to duplications. 2). The failure to explicitly differentiate between the potential relevance of negative samples. As an example, a bubble sorting algorithm example is less ``negative'' than a file saving function for the quick sorting algorithm query. In this paper, we tackle the above problems by proposing a simple yet effective Soft-InfoNCE loss that inserts weight terms into InfoNCE. In our proposed loss function, we apply three methods to estimate the weights of negative pairs and show that the vanilla InfoNCE loss is a special case of Soft-InfoNCE. Theoretically, we analyze the effects of Soft-InfoNCE on controlling the distribution of learnt code representations and on deducing a more precise mutual information estimation. We furthermore discuss the superiority of proposed loss functions with other design alternatives. Extensive experiments demonstrate the effectiveness of Soft-InfoNCE and weights estimation methods under state-of-the-art code search models on a large-scale public dataset consisting of six programming languages. Source code is available at \url{https://github.com/Alex-HaochenLi/Soft-InfoNCE}., Comment: Accepted to EMNLP 2023

Josephson Junctions are important components in superconducting qubits. It introduces anharmonicity to the energy level spacings of the qubit which allow us to identify two unique quantum energy states for computing. It is difficult to fabricate multiple junctions within the same desired parameter range. Characterisation of the junctions is, therefore, a necessary step after fabrication. In particular, the critical current of the junctions is determined by measuring their normal state resistance. This is done via two-point or four-point resistance measurement at a manual probe station which is a time-consuming process, especially for wafer-scale fabrication. This bottleneck can be circumvented by automation with object detection. The base of the automated probe station is a 3D printer modified with multiple Arduino Uno microcontrollers and motorised linear stages. The automation process is achieved via auto-alignment of the probes and an automatic measurement procedure. As a result, the fully automated process will take about 27-29 seconds to measure the resistance of one junction which saves 28-51% of the time compared to the manual probe station and can be unsupervised. Due to the reuse of a commercial 3D printer, the cost of this system is 800 SGD which is much less than comparable commercial solutions.

Reconfigurable intelligent surface (RIS) is a promising candidate technology for the upcoming Sixth Generation (6G) communication system for its ability to manipulate the wireless communication environment by controlling the coefficients of reflection elements (REs). However, since the RIS usually consists of a large number of passive REs, the pilot overhead for channel estimation in the RIS-aided system is prohibitively high. In this paper, the channel estimation problem for a RIS-aided multi-user multiple-input-single-output (MISO) communication system with clustered users is investigated. First, to describe the correlated feature for RIS-user channels, a beam domain channel model is developed for RIS-user channels. Then, a pilot reuse strategy is put forward to reduce the pilot overhead and decompose the channel estimation problem into several subproblems. Finally, by leveraging the correlated nature of RIS-user channels, an eigenspace projection (EP) algorithm is proposed to solve each subproblem respectively. Simulation results show that the proposed EP channel estimation scheme can achieve accurate channel estimation with lower pilot overhead than existing schemes., Comment: 10 pages, 11 figures

Reconfigurable intelligent surface (RIS) is a promising candidate technology of the upcoming Sixth Generation (6G) communication system for its ability to provide unprecedented spectral and energy efficiency increment through passive beamforming. However, it is challenging to obtain instantaneous channel state information (I-CSI) for RIS, which obliges us to use statistical channel state information (S-CSI) to achieve passive beamforming. In this paper, RIS-aided multiple-input single-output (MISO) multi-user downlink communication system with correlated channels is investigated. Then, we formulate the problem of joint beamforming design at the AP and RIS to maximize the sum ergodic spectral efficiency (ESE) of all users to improve the network capacity. Since it is too hard to compute sum ESE, an ESE approximation is adopted to reformulate the problem into a more tractable form. Then, we present two joint beamforming algorithms, namely the singular value decomposition-gradient descent (SVD-GD) algorithm and the fractional programming-gradient descent (FP-GD) algorithm. Simulation results show the effectiveness of our proposed algorithms and validate that 2-bits quantizer is enough for RIS phase shifts implementation., Comment: 10 pages, 9 figures

In this study, we introduce a physical model inspired by statistical physics for predicting price volatility and expected returns by leveraging Level 3 order book data. By drawing parallels between orders in the limit order book and particles in a physical system, we establish unique measures for the system's kinetic energy and momentum as a way to comprehend and evaluate the state of limit order book. Our model goes beyond examining merely the top layers of the order book by introducing the concept of 'active depth', a computationally-efficient approach for identifying order book levels that have impact on price dynamics. We empirically demonstrate that our model outperforms the benchmarks of traditional approaches and machine learning algorithm. Our model provides a nuanced comprehension of market microstructure and produces more accurate forecasts on volatility and expected returns. By incorporating principles of statistical physics, this research offers valuable insights on understanding the behaviours of market participants and order book dynamics.

We take inspiration from statistical physics to develop a novel conceptual framework for the analysis of financial markets. We model the order book dynamics as a motion of particles and define the momentum measure of the system as a way to summarise and assess the state of the market. Our approach proves useful in capturing salient financial market phenomena: in particular, it helps detect the market manipulation activities called spoofing and layering. We apply our method to identify pathological order book behaviours during the flash crash of the LUNA cryptocurrency, uncovering widespread instances of spoofing and layering in the market. Furthermore, we establish that our technique outperforms the conventional Z-score-based anomaly detection method in identifying market manipulations across both LUNA and Bitcoin cryptocurrency markets.

Recently, simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) have received significant research interest. The employment of large STAR-RIS and high-frequency signaling inevitably make the near-field propagation dominant in wireless communications. In this work, a STAR-RIS aided near-field multiple-input multiple-multiple (MIMO) communication framework is proposed. A weighted sum rate maximization problem for the joint optimization of the active beamforming at the base station (BS) and the transmission/reflection-coefficients (TRCs) at the STAR-RIS is formulated. The non-convex problem is solved by a block coordinate descent (BCD)-based algorithm. In particular, under given STAR-RIS TRCs, the optimal active beamforming matrices are obtained by solving a convex quadratically constrained quadratic program. For given active beamforming matrices, two algorithms are suggested for optimizing the STAR-RIS TRCs: a penalty-based iterative (PEN) algorithm and an element-wise iterative (ELE) algorithm. The latter algorithm is conceived for STAR-RISs with a large number of elements. Numerical results illustrate that: i) near-field beamforming for STAR-RIS aided MIMO communications significantly improves the achieved weighted sum rate compared with far-field beamforming; ii) the near-field channels facilitated by the STAR-RIS provide enhanced degrees-of-freedom and accessibility for the multi-user MIMO system; and iii) the BCD-PEN algorithm achieves better performance than the BCD-ELE algorithm, while the latter has a significantly lower computational complexity., Comment: 30 pages, 9 figures

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a discriminative visual encoder, while ignoring the domain bias in the detection head. Inspired by the high generalization of vision-language models (VLMs), applying a VLM as the robust detection backbone following a domain-aware detection head is a reasonable way to learn the discriminative detector for each domain, rather than reducing the domain bias in traditional methods. To achieve the above issue, we thus propose a novel DAOD framework named Domain-Aware detection head with Prompt tuning (DA-Pro), which applies the learnable domain-adaptive prompt to generate the dynamic detection head for each domain. Formally, the domain-adaptive prompt consists of the domain-invariant tokens, domain-specific tokens, and the domain-related textual description along with the class label. Furthermore, two constraints between the source and target domains are applied to ensure that the domain-adaptive prompt can capture the domains-shared and domain-specific knowledge. A prompt ensemble strategy is also proposed to reduce the effect of prompt disturbance. Comprehensive experiments over multiple cross-domain adaptation tasks demonstrate that using the domain-adaptive prompt can produce an effectively domain-related detection head for boosting domain-adaptive object detection. Our code is available at https://github.com/Therock90421/DA-Pro., Comment: Accepted by NeurIPS 2023

Event Extraction (EE) is one of the essential tasks in information extraction, which aims to detect event mentions from text and find the corresponding argument roles. The EE task can be abstracted as a process of matching the semantic definitions and argument structures of event types with the target text. This paper encodes the semantic features of event types and makes structural matching with target text. Specifically, Semantic Type Embedding (STE) and Dynamic Structure Encoder (DSE) modules are proposed. Also, the Joint Structural Semantic Matching (JSSM) model is built to jointly perform event detection and argument extraction tasks through a bidirectional attention layer. The experimental results on the ACE2005 dataset indicate that our model achieves a significant performance improvement

Data-driven methods are widely used to develop physical models, but there still exist limitations that affect their performance, generalizability and robustness. By combining gene expression programming (GEP) with artificial neural network (ANN), we propose a novel method for symbolic regression called the gene expression programming neural network (GEPNN). In this method, candidate expressions generated by evolutionary algorithms are transformed between the GEP and ANN structures during training iterations, and efficient and robust convergence to accurate models is achieved by combining the GEP's global searching and the ANN's gradient optimization capabilities. In addition, sparsity-enhancing strategies have been introduced to GEPNN to improve the interpretability of the trained models. The GEPNN method has been tested for finding different physical laws, showing improved convergence to models with precise coefficients. Furthermore, for large-eddy simulation of turbulence, the subgrid-scale stress model trained by GEPNN significantly improves the prediction of turbulence statistics and flow structures over traditional models, showing advantages compared to the existing GEP and ANN methods in both a priori and a posteriori tests., Comment: 18 figures, 42 pages

Learning accurate numerical constants when developing algebraic models is a known challenge for evolutionary algorithms, such as Gene Expression Programming (GEP). This paper introduces the concept of adaptive symbols to the GEP framework by Weatheritt and Sandberg (2016) to develop advanced physics closure models. Adaptive symbols utilize gradient information to learn locally optimal numerical constants during model training, for which we investigate two types of nonlinear optimization algorithms. The second contribution of this work is implementing two regularization techniques to incentivize the development of implementable and interpretable closure models. We apply $L_2$ regularization to ensure small magnitude numerical constants and devise a novel complexity metric that supports the development of low complexity models via custom symbol complexities and multi-objective optimization. This extended framework is employed to four use cases, namely rediscovering Sutherland's viscosity law, developing laminar flame speed combustion models and training two types of fluid dynamics turbulence models. The model prediction accuracy and the convergence speed of training are improved significantly across all of the more and less complex use cases, respectively. The two regularization methods are essential for developing implementable closure models and we demonstrate that the developed turbulence models substantially improve simulations over state-of-the-art models.

Code search, which aims at retrieving the most relevant code fragment for a given natural language query, is a common activity in software development practice. Recently, contrastive learning is widely used in code search research, where many data augmentation approaches for source code (e.g., semantic-preserving program transformation) are proposed to learn better representations. However, these augmentations are at the raw-data level, which requires additional code analysis in the preprocessing stage and additional training costs in the training stage. In this paper, we explore augmentation methods that augment data (both code and query) at representation level which does not require additional data processing and training, and based on this we propose a general format of representation-level augmentation that unifies existing methods. Then, we propose three new augmentation methods (linear extrapolation, binary interpolation, and Gaussian scaling) based on the general format. Furthermore, we theoretically analyze the advantages of the proposed augmentation methods over traditional contrastive learning methods on code search. We experimentally evaluate the proposed representation-level augmentation methods with state-of-the-art code search models on a large-scale public dataset consisting of six programming languages. The experimental results show that our approach can consistently boost the performance of the studied code search models. Our source code is available at https://github.com/Alex-HaochenLi/RACS., Comment: Accepted to EMNLP 2022