Search

Developing quantum algorithms adaptive to specific constraints of near-term devices is an essential step towards practical quantum advantage. In a recent work [Phys. Rev. Lett. 131, 103601(2023)], we show cold atoms in an optical cavity can be built as a universal quantum optimizer with programmable all-to-all interactions, and the effective Hamiltonian for atoms directly encodes number partitioning problems (NPPs). Here, we numerically investigate the performance of quantum annealing (QA) and quantum approximate optimization algorithm (QAOA) to find the solution of NPP that is encoded in the ground state of atomic qubits. We find the success probability of the standard QA decays rapidly with the problem size. The optimized annealing path or inhomogeneous driving fields only lead to mild improvement on the success probability. Similarly, the standard QAOA always gets trapped in a false local minimum, and there is no significant performance improvement as we increase the depth of the quantum circuit. Inspired by the counterdiabatic driving, we propose an adaptive ansatz of QAOA which releases the parameter freedom of the NPP Hamiltonian to match higher-order counterdiabatic terms. Through numerical simulations, we find that our adaptive QAOA can achieve the optimal solution within very small circuit depth. It is thus worth paying the extra optimization cost of additional parameters for improving QAOA performance. Therefore, our adaptive QAOA provides a promising choice for programmable atom-cavity systems to demonstrate competitive computational power within its quantum coherence time.

In the domain of code generation, self-debugging is crucial. It allows LLMs to refine their generated code based on execution feedback. This is particularly important because generating correct solutions in one attempt proves challenging for complex tasks. Prior works on self-debugging mostly focus on prompting methods by providing LLMs with few-shot examples, which work poorly on small open-sourced LLMs. In this work, we propose a training framework that significantly improves self-debugging capability of LLMs. Intuitively, we observe that a chain of explanations on the wrong code followed by code refinement helps LLMs better analyze the wrong code and do refinement. We thus propose an automated pipeline to collect a high-quality dataset for code explanation and refinement by generating a number of explanations and refinement trajectories and filtering via execution verification. We perform supervised fine-tuning (SFT) and further reinforcement learning (RL) on both success and failure trajectories with a novel reward design considering code explanation and refinement quality. SFT improves the pass@1 by up to 15.92% and pass@10 by 9.30% over four benchmarks. RL training brings additional up to 3.54% improvement on pass@1 and 2.55% improvement on pass@10. The trained LLMs show iterative refinement ability, and can keep refining code continuously. Lastly, our human evaluation shows that the LLMs trained with our framework generate more useful code explanations and help developers better understand bugs in source code.

Worldwide geolocalization aims to locate the precise location at the coordinate level of photos taken anywhere on the Earth. It is very challenging due to 1) the difficulty of capturing subtle location-aware visual semantics, and 2) the heterogeneous geographical distribution of image data. As a result, existing studies have clear limitations when scaled to a worldwide context. They may easily confuse distant images with similar visual contents, or cannot adapt to various locations worldwide with different amounts of relevant data. To resolve these limitations, we propose G3, a novel framework based on Retrieval-Augmented Generation (RAG). In particular, G3 consists of three steps, i.e., Geo-alignment, Geo-diversification, and Geo-verification to optimize both retrieval and generation phases of worldwide geolocalization. During Geo-alignment, our solution jointly learns expressive multi-modal representations for images, GPS and textual descriptions, which allows us to capture location-aware semantics for retrieving nearby images for a given query. During Geo-diversification, we leverage a prompt ensembling method that is robust to inconsistent retrieval performance for different image queries. Finally, we combine both retrieved and generated GPS candidates in Geo-verification for location prediction. Experiments on two well-established datasets IM2GPS3k and YFCC4k verify the superiority of G3 compared to other state-of-the-art methods.

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and sentiments simultaneously. However, we argue that joint models are not always superior. Our analysis shows that joint models struggle to align relevant text tokens with image patches, leading to misalignment and ineffective image utilization. In contrast, a pipeline framework first identifies aspects through MATE (Multimodal Aspect Term Extraction) and then aligns these aspects with image patches for sentiment classification (MASC: Multimodal Aspect-Oriented Sentiment Classification). This method is better suited for multimodal scenarios where effective image use is crucial. We present three key observations: (a) MATE and MASC have different feature requirements, with MATE focusing on token-level features and MASC on sequence-level features; (b) the aspect identified by MATE is crucial for effective image utilization; and (c) images play a trivial role in previous MABSA methods due to high noise. Based on these observations, we propose a pipeline framework that first predicts the aspect and then uses translation-based alignment (TBA) to enhance multimodal semantic consistency for better image utilization. Our method achieves state-of-the-art (SOTA) performance on widely used MABSA datasets Twitter-15 and Twitter-17. This demonstrates the effectiveness of the pipeline approach and its potential to provide valuable insights for future MABSA research. For reproducibility, the code and checkpoint will be released., Comment: Code will be released upon publication

Automated Vehicles (AVs) promise significant advances in transportation. Critical to these improvements is understanding AVs' longitudinal behavior, relying heavily on real-world trajectory data. Existing open-source trajectory datasets of AV, however, often fall short in refinement, reliability, and completeness, hindering effective performance metrics analysis and model development. This study addresses these challenges by creating a Unified Longitudinal TRAjectory dataset for AVs (Ultra-AV) to analyze their microscopic longitudinal driving behaviors. This dataset compiles data from 13 distinct sources, encompassing various AV types, test sites, and experiment scenarios. We established a three-step data processing: 1. extraction of longitudinal trajectory data, 2. general data cleaning, and 3. data-specific cleaning to obtain the longitudinal trajectory data and car-following trajectory data. The validity of the processed data is affirmed through performance evaluations across safety, mobility, stability, and sustainability, along with an analysis of the relationships between variables in car-following models. Our work not only furnishes researchers with standardized data and metrics for longitudinal AV behavior studies but also sets guidelines for data collection and model development., Comment: NA

This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. The performance of the top-5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in RAW Image Super-Resolution., Comment: CVPR 2024 - NTIRE Workshop

Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to many deep learning-based APR methods that assume known bug locations, rely on line-level localization tools, or address bug prediction and fixing in one step, our approach uniquely employs LLMs to predict bug location at the token level and subsequently utilizes them for bug fixing. This methodological separation of bug localization and fixing using different LLMs enables effective integration of diverse contextual information and improved incorporation of inductive biases. We introduce Toggle: Token-Granulated Bug Localization and Repair, a comprehensive program repair framework that integrates a bug localization model, an adjustment unit, and a bug-fixing model. Toggle takes a buggy function as input and generates a complete corrected function. We investigate various styles of prompting to the bug fixing model to identify the most effective prompts that better utilize the inductive bias and significantly outperform others. Toggle achieves the new state-of-the-art (SOTA) performance on the CodeXGLUE code refinement benchmark, and exhibits better and comparable performance on several other widely-used APR datasets, including Defects4J.

Dynamical quantum phase transitions, encompassing phenomena like many-body localization transitions and measurement-induced phase transitions, are often characterized and identified through the analysis of quantum entanglement. Here, we highlight that the dynamical phases defined by entanglement are further enriched by complexity. We investigate both the entanglement and Krylov complexity for fermions on regular graphs, which can be implemented by systems like $^6$Li atoms confined by optical tweezers. Our investigations unveil that while entanglement follows volume laws on both types of regular graphs with degree $d = 2$ and $d = 3$, the Krylov complexity exhibits distinctive behaviors. We analyze both free fermions and interacting fermions models. In the absence of interaction, both numerical results and theoretical analysis confirm that the dimension of the Krylov space scales as $D\sim N$ for regular graphs of degree $d = 2$ with $N$ sites, and we have $D\sim N^2$ for $d = 3$. The qualitative distinction also persists in interacting fermions on regular graphs. For interacting fermions, our theoretical analyses find the dimension scales as $D\sim 4^{N^\alpha}$ for regular graphs of $d = 2$ with $0.38\leq\alpha\leq0.59$, whereas it scales as $D\sim 4^N$ for $d = 3$. The distinction in the complexity of quantum dynamics for fermions on graphs with different connectivity can be probed in experiments by measuring the out-of-time-order correlators.

Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as input may contain redundant information. (2)the insufficient utilization of entity-related information, such as attributes in images. (3)semantic inconsistency between the entity in knowledge base and its representation. To this end, we propose DWE+ for multimodal entity linking. DWE+ could capture finer semantics and dynamically maintain semantic consistency with entities. This is achieved by three aspects: (a)we introduce a method for extracting fine-grained image features by partitioning the image into multiple local objects. Then, hierarchical contrastive learning is used to further align semantics between coarse-grained information(text and image) and fine-grained (mention and visual objects). (b)we explore ways to extract visual attributes from images to enhance fusion feature such as facial features and identity. (c)we leverage Wikipedia and ChatGPT to capture the entity representation, achieving semantic enrichment from both static and dynamic perspectives, which better reflects the real-world entity semantics. Experiments on Wikimel, Richpedia, and Wikidiverse datasets demonstrate the effectiveness of DWE+ in improving MEL performance. Specifically, we optimize these datasets and achieve state-of-the-art performance on the enhanced datasets. The code and enhanced datasets are released on https://github.com/season1blue/DWET, Comment: under review on TOIS. arXiv admin note: substantial text overlap with arXiv:2312.11816

Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the real-world domain gap. In this paper, we propose a domain generalization approach, named V2X-DGW, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Not only in the clean weather does our research aim to ensure favorable multi-agent performance, but also in the unseen adverse weather conditions by learning only on the clean weather data. To advance research in this area, we have simulated the impact of three prevalent adverse weather conditions on two widely-used multi-agent datasets, resulting in the creation of two novel benchmark datasets: OPV2V-w and V2XSet-w. To this end, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weather-invariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). Extensive experimental results demonstrate that our V2X-DGW achieved improvements in the unseen adverse weather conditions.

This paper introduces an online physical enhanced residual learning (PERL) framework for Connected Autonomous Vehicles (CAVs) platoon, aimed at addressing the challenges posed by the dynamic and unpredictable nature of traffic environments. The proposed framework synergistically combines a physical model, represented by Model Predictive Control (MPC), with data-driven online Q-learning. The MPC controller, enhanced for centralized CAV platoons, employs vehicle velocity as a control input and focuses on multi-objective cooperative optimization. The learning-based residual controller enriches the MPC with prior knowledge and corrects residuals caused by traffic disturbances. The PERL framework not only retains the interpretability and transparency of physics-based models but also significantly improves computational efficiency and control accuracy in real-world scenarios. The experimental results present that the online Q-learning PERL controller, in comparison to the MPC controller and PERL controller with a neural network, exhibits significantly reduced position and velocity errors. Specifically, the PERL's cumulative absolute position and velocity errors are, on average, 86.73% and 55.28% lower than the MPC's, and 12.82% and 18.83% lower than the neural network-based PERL's, in four tests with different reference trajectories and errors. The results demonstrate our advanced framework's superior accuracy and quick convergence capabilities, proving its effectiveness in maintaining platoon stability under diverse conditions.

This paper presents a comprehensive review of trajectory data of Advanced Driver Assistance System equipped-vehicle, with the aim of precisely model of Autonomous Vehicles (AVs) behavior. This study emphasizes the importance of trajectory data in the development of AV models, especially in car-following scenarios. We introduce and evaluate several datasets: the OpenACC Dataset, the Connected & Autonomous Transportation Systems Laboratory Open Dataset, the Vanderbilt ACC Dataset, the Central Ohio Dataset, and the Waymo Open Dataset. Each dataset offers unique insights into AV behaviors, yet they share common challenges in terms of data availability, processing, and standardization. After a series of data cleaning, outlier removal and statistical analysis, this paper transforms datasets of varied formats into a uniform standard, thereby improving their applicability for modeling AV car-following behavior. Key contributions of this study include: 1. the transformation of all datasets into a unified standard format, enhancing their utility for broad research applications; 2. a comparative analysis of these datasets, highlighting their distinct characteristics and implications for car-following model development; 3. the provision of guidelines for future data collection projects, along with the open-source release of all processed data and code for use by the research community., Comment: 6 pages, 2 figures

The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updating a small amount of knowledge of LLMs and has attracted much attention. In particular, local editing methods, which directly update model parameters, are more suitable for updating a small amount of knowledge. Local editing methods update weights by computing least squares closed-form solutions and identify edited knowledge by vector-level matching in inference, which achieve promising results. However, these methods still require a lot of time and resources to complete the computation. Moreover, vector-level matching lacks reliability, and such updates disrupt the original organization of the model's parameters. To address these issues, we propose an detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching and adds them to the subject word embeddings in Transformer input. To get these editing embeddings, we propose optimizing then suppressing fusion method, which first optimizes learnable embedding vectors for the editing target and then suppresses the Knowledge Embedding Dimensions (KEDs) to obtain final editing embeddings. We thus propose SWEA$\oplus$OS method for editing factual knowledge in LLMs. We demonstrate the overall state-of-the-art (SOTA) performance of SWEA$\oplus$OS on the \textsc{CounterFact} and zsRE datasets. To further validate the reasoning ability of SWEA$\oplus$OS in editing knowledge, we evaluate it on the more complex \textsc{RippleEdits} benchmark. The results demonstrate that SWEA$\oplus$OS possesses SOTA reasoning ability., Comment: Under review; Our code is available at https://github.com/xpq-tech/SWEA

Search engines are crucial as they provide an efficient and easy way to access vast amounts of information on the internet for diverse information needs. User queries, even with a specific need, can differ significantly. Prior research has explored the resilience of ranking models against typical query variations like paraphrasing, misspellings, and order changes. Yet, these works overlook how diverse demographics uniquely formulate identical queries. For instance, older individuals tend to construct queries more naturally and in varied order compared to other groups. This demographic diversity necessitates enhancing the adaptability of ranking models to diverse query formulations. To this end, in this paper, we propose a framework that integrates a novel rewriting pipeline that rewrites queries from various demographic perspectives and a novel framework to enhance ranking robustness. To be specific, we use Chain of Thought (CoT) technology to utilize Large Language Models (LLMs) as agents to emulate various demographic profiles, then use them for efficient query rewriting, and we innovate a robust Multi-gate Mixture of Experts (MMoE) architecture coupled with a hybrid loss function, collectively strengthening the ranking models' robustness. Our extensive experimentation on both public and industrial datasets assesses the efficacy of our query rewriting approach and the enhanced accuracy and robustness of the ranking model. The findings highlight the sophistication and effectiveness of our proposed model.

The precise estimation of macroscopic traffic parameters, such as travel time and fuel consumption, is essential for the optimization of traffic management systems. Despite its importance, the comprehensive acquisition of vehicle trajectory data for the calculation of these macroscopic measures presents a challenge. To bridge this gap, this study aims to calibrate car-following models capable of predicting both microscopic measures and macroscopic measures. We conduct a numerical analysis to trace the cumulative process of model prediction errors across various measurements, and our findings indicate that macroscopic measures encapsulate the accumulation of model errors. By incorporating macroscopic measures into vehicle model calibration, we can mitigate the impact of noise on microscopic data measurements. We compare three car-following model calibration methods: MiC (using microscopic measurements), MaC (using macroscopic measurements), and BiC (using both microscopic and macroscopic measurements): utilizing real-world trajectory data. The BiC method emerges as the most successful in reconstructing vehicle trajectories and accurately estimating travel time and fuel consumption, whereas the MiC method leads to overfitting and inaccurate macro-measurement predictions. This study underscores the importance of bi-scale calibration for precise traffic and energy consumption predictions, laying the groundwork for future research aimed at enhancing traffic management strategies.

There has been much recent progress in controlling $p$-orbital degrees of freedom in optical lattices, for example with lattice shaking, sublattice swapping, and lattice potential programming. Here, we present a protocol of preparing lowest Landau level (LLL) states of cold atoms by adiabatically compressing $p$-orbital Bose-Einstein condensates confined in two-dimensional optical lattices. The system starts from a chiral $p+ip$ Bose-Einstein condensate (BEC) state, which acquires finite angular momentum by spontaneous symmetry breaking. Such chiral BEC states have been achieved in recent optical lattice experiments for cold atoms loaded in the $p$-bands. Through an adiabatic adjustment of the lattice potential, we compress the three-dimensional BEC into a two-dimensional system, in which the orbital degrees of freedom continuously morph into LLL states. This process is enforced by the discrete rotation symmetry of the lattice potential. The final quantum state inherits large angular momentum from the original chiral $p+ip$ state, with one quantized unit per particle. We investigate the quantum many-body ground state of interacting bosons in the LLL considering contact repulsion. This leads to an exotic gapped BEC state. Our theory can be readily tested in experiments for the required techniques are all accessible to the current optical lattice experiments.

This review paper explores Multimodal Large Language Models (MLLMs), which integrate Large Language Models (LLMs) like GPT-4 to handle multimodal data such as text and vision. MLLMs demonstrate capabilities like generating image narratives and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in processing the semantic gap in multimodality, which may lead to erroneous generation, posing potential risks to society. Choosing the appropriate modality alignment method is crucial, as improper methods might require more parameters with limited performance improvement. This paper aims to explore modality alignment methods for LLMs and their existing capabilities. Implementing modality alignment allows LLMs to address environmental issues and enhance accessibility. The study surveys existing modal alignment methods in MLLMs into four groups: (1) Multimodal Converters that change data into something LLMs can understand; (2) Multimodal Perceivers to improve how LLMs perceive different types of data; (3) Tools Assistance for changing data into one common format, usually text; and (4) Data-Driven methods that teach LLMs to understand specific types of data in a dataset. This field is still in a phase of exploration and experimentation, and we will organize and update various existing research methods for multimodal information alignment.

Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable limitations. Retrieval-based methods often fail to accurately capture search intent, particularly with brief or ambiguous queries. Generation-based methods, utilizing large language models (LLMs), generally lack corpus-specific knowledge and entail high fine-tuning costs. To address these gaps, we propose a novel zero-shot query expansion framework utilizing LLMs for mutual verification. Specifically, we first design a query-query-document generation method, leveraging LLMs' zero-shot reasoning ability to produce diverse sub-queries and corresponding documents. Then, a mutual verification process synergizes generated and retrieved documents for optimal expansion. Our proposed method is fully zero-shot, and extensive experiments on three public benchmark datasets are conducted to demonstrate its effectiveness over existing methods. Our code is available online at https://github.com/Applied-Machine-Learning-Lab/MILL to ease reproduction., Comment: Accepted to NAACL 2024

Automated vehicle (AV) shuttles are emerging mobility technologies that have been widely piloted and deployed. Public attitude is critical to the deployment progress and the overall social benefits of automated vehicle (AV) technologies. The AV shuttle demonstration was regarded as a good way for possible attitude improvements. However, not all existing AV shuttle technologies are mature and reliable enough. Some frustrating uncomfort issues in AV shuttle demonstrations may adversely affect public attitudes of AV technologies. Studying the impact of the comfort of the demonstration on attitudinal change can help us provide guidance for future demonstrations. Thanks to the AV shuttle project piloted at Dunedin, Florida, this paper interviewed 161 people before and after taking an open road AV shuttle ride. In addition to the participant's demographic information, driving-related information and psychological-related information, we collected the AV shuttles' operation status (e.g., abrupt brake). A series of discrete outcome models were employed to estimate the factors influencing people's initial opinions before the AV shuttle ride and people's attitudes change after the ride. The most important finding is that an unsatisfactory riding experience could negatively affect participants' attitudes toward AV shuttles. Particularly, the number of abrupt brakes raises more concerns when the participants are drivers who share the rights of way with the AV shuttle compared to when the participants are pedestrians or AV shuttle riders. Moreover, the participants' attitudes toward sharing public space with AV shuttles as pedestrians and human drivers exhibited more negative changes compared with simply riding on AV shuttles. These results improve our understanding of public attitudes toward the existing AV technologies and help identify new opportunities to improve AV technology adoption.

We investigate a model many-body system of spinless Fermi gas in two dimensions, where the bare two-body interaction is repulsive and takes the form of a soft-core disk potential. We obtain the zero temperature phase diagram of this model by numerical functional renormalization group (FRG), which retains the effective interaction vertices in all channels to provide a detailed picture of how Cooper pairing emerges under the renormalization flow. The repulsion drives the system to a series of superfluid states with higher angular momentum paring, for example in the $f$- and $h$-wave channels instead of the $p$-wave channel. This is in sharp contrast to the original Kohn-Luttinger mechanism where pairing of very large angular momenta and exponentially small transition temperature was predicted. We trace the stabilization and enhancement of $f$- and $h$-wave pairing back to the momentum dependence of the bare interaction. A perturbative calculation is carried out to show that while the second order Kohn-Luttinger diagrams provide a qualitative understanding of the onsets of the various superfluid phases, they are unable to accurately capture the phase boundaries predicted by FRG. Our findings suggest that tuning the shape of the interaction potential offers a promising route to achieve stronger ``pairing glue" and to realize nontrivial superfluid phases in repulsive Fermi gases beyond the scope of the original Kohn-Luttinger analysis., Comment: Published version, with updated title, abstract, and introduction

In vehicle trajectory prediction, physics models and data-driven models are two predominant methodologies. However, each approach presents its own set of challenges: physics models fall short in predictability, while data-driven models lack interpretability. Addressing these identified shortcomings, this paper proposes a novel framework, the Physics-Enhanced Residual Learning (PERL) model. PERL integrates the strengths of physics-based and data-driven methods for traffic state prediction. PERL contains a physics model and a residual learning model. Its prediction is the sum of the physics model result and a predicted residual as a correction to it. It preserves the interpretability inherent to physics-based models and has reduced data requirements compared to data-driven methods. Experiments were conducted using a real-world vehicle trajectory dataset. We proposed a PERL model, with the Intelligent Driver Model (IDM) as its physics car-following model and Long Short-Term Memory (LSTM) as its residual learning model. We compare this PERL model with the physics car-following model, data-driven model, and other physics-informed neural network (PINN) models. The result reveals that PERL achieves better prediction with a small dataset, compared to the physics model, data-driven model, and PINN model. Second, the PERL model showed faster convergence during training, offering comparable performance with fewer training samples than the data-driven model and PINN model. Sensitivity analysis also proves comparable performance of PERL using another residual learning model and a physics car-following model.

In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accuracy. However, they require a large number of random 1-D convolutional kernels to comprehensively capture features, which is incompatible with resource-constrained devices. Despite the development of heuristic algorithms designed to recognize and prune redundant kernels, the inherent time-consuming nature of evolutionary algorithms hinders efficient evaluation. To effectively prune models, this paper removes redundant random kernels from a feature selection perspective by eliminating associating connections in the sequential classifier. Two innovative algorithms are proposed, where the first ADMM-based algorithm formulates the pruning challenge as a group elastic net classification problem, and the second core algorithm named POCKET greatly accelerates the first one by bifurcating the problem into two sequential stages. Stage 1 of POCKET introduces dynamically varying penalties to efficiently implement group-level regularization to delete redundant kernels, and Stage 2 employs element-level regularization on the remaining features to refit a linear classifier for better performance. Experimental results on diverse time series datasets show that POCKET prunes up to 60% of kernels without a significant reduction in accuracy and performs 11 times faster than its counterparts. Our code is publicly available at https://github.com/ShaowuChen/POCKET.

Multi-Domain Recommendation (MDR) has gained significant attention in recent years, which leverages data from multiple domains to enhance their performance concurrently.However, current MDR models are confronted with two limitations. Firstly, the majority of these models adopt an approach that explicitly shares parameters between domains, leading to mutual interference among them. Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains. To address these challenges, we propose a novel model Hyper Adapter for Multi-Domain Recommendation (HAMUR). Specifically, HAMUR consists of two components: (1). Domain-specific adapter, designed as a pluggable module that can be seamlessly integrated into various existing multi-domain backbone models, and (2). Domain-shared hyper-network, which implicitly captures shared information among domains and dynamically generates the parameters for the adapter. We conduct extensive experiments on two public datasets using various backbone networks. The experimental results validate the effectiveness and scalability of the proposed model., Comment: Accepted by CIKM'2023

Click-Through Rate (CTR) prediction is a fundamental technique in recommendation and advertising systems. Recent studies have shown that implementing multi-scenario recommendations contributes to strengthening information sharing and improving overall performance. However, existing multi-scenario models only consider coarse-grained explicit scenario modeling that depends on pre-defined scenario identification from manual prior rules, which is biased and sub-optimal. To address these limitations, we propose a Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendations (HierRec), which perceives implicit patterns adaptively and conducts explicit and implicit scenario modeling jointly. In particular, HierRec designs a basic scenario-oriented module based on the dynamic weight to capture scenario-specific information. Then the hierarchical explicit and implicit scenario-aware modules are proposed to model hybrid-grained scenario information. The multi-head implicit modeling design contributes to perceiving distinctive patterns from different perspectives. Our experiments on two public datasets and real-world industrial applications on a mainstream online advertising platform demonstrate that our HierRec outperforms existing models significantly.

Predicting vehicle trajectories is crucial for ensuring automated vehicle operation efficiency and safety, particularly on congested multi-lane highways. In such dynamic environments, a vehicle's motion is determined by its historical behaviors as well as interactions with surrounding vehicles. These intricate interactions arise from unpredictable motion patterns, leading to a wide range of driving behaviors that warrant in-depth investigation. This study presents the Graph-based Interaction-aware Multi-modal Trajectory Prediction (GIMTP) framework, designed to probabilistically predict future vehicle trajectories by effectively capturing these interactions. Within this framework, vehicles' motions are conceptualized as nodes in a time-varying graph, and the traffic interactions are represented by a dynamic adjacency matrix. To holistically capture both spatial and temporal dependencies embedded in this dynamic adjacency matrix, the methodology incorporates the Diffusion Graph Convolutional Network (DGCN), thereby providing a graph embedding of both historical states and future states. Furthermore, we employ a driving intention-specific feature fusion, enabling the adaptive integration of historical and future embeddings for enhanced intention recognition and trajectory prediction. This model gives two-dimensional predictions for each mode of longitudinal and lateral driving behaviors and offers probabilistic future paths with corresponding probabilities, addressing the challenges of complex vehicle interactions and multi-modality of driving behaviors. Validation using real-world trajectory datasets demonstrates the efficiency and potential.

Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of key-value memories of the Feed-Forward Network (FFN). They usually optimize the TL hidden states to memorize target knowledge and use it to update the weights of the FFN in LLMs. However, the information flow of TL hidden states comes from three parts: Multi-Head Self-Attention (MHSA), FFN, and residual connections. Existing methods neglect the fact that the TL hidden states contains information not specifically required for FFN. Consequently, the performance of model editing decreases. To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns. This implies that MHSA weights do not require updating when new knowledge is introduced. Based on above findings, we introduce PMET, which simultaneously optimizes Transformer Component (TC, namely MHSA and FFN) hidden states, while only using the optimized TC hidden states of FFN to precisely update FFN weights. Our experiments demonstrate that PMET exhibits state-of-the-art performance on both the COUNTERFACT and zsRE datasets. Our ablation experiments substantiate the effectiveness of our enhancements, further reinforcing the finding that the MHSA encodes certain general knowledge extraction patterns and indicating its storage of a small amount of factual knowledge. Our code is available at https://github.com/xpq-tech/PMET., Comment: AAAI24

As a hybrid of artificial intelligence and quantum computing, quantum neural networks (QNNs) have gained significant attention as a promising application on near-term, noisy intermediate-scale quantum (NISQ) devices. Conventional QNNs are described by parametrized quantum circuits, which perform unitary operations and measurements on quantum states. In this work, we propose a novel approach to enhance the expressivity of QNNs by incorporating randomness into quantum circuits. Specifically, we introduce a random layer, which contains single-qubit gates sampled from an trainable ensemble pooling. The prediction of QNN is then represented by an ensemble average over a classical function of measurement outcomes. We prove that our approach can accurately approximate arbitrary target operators using Uhlmann's theorem for majorization, which enables observable learning. Our proposal is demonstrated with extensive numerical experiments, including observable learning, R\'enyi entropy measurement, and image recognition. We find the expressivity of QNNs is enhanced by introducing randomness for multiple learning tasks, which could have broad application in quantum machine learning., Comment: 6 pages, 4 figures

We propose a new length formula that governs the iterates of the momentum method when minimizing differentiable semialgebraic functions with locally Lipschitz gradients. It enables us to establish local convergence, global convergence, and convergence to local minimizers without assuming global Lipschitz continuity of the gradient, coercivity, and a global growth condition, as is done in the literature. As a result, we provide the first convergence guarantee of the momentum method starting from arbitrary initial points when applied to principal component analysis, matrix sensing, and linear neural networks., Comment: 33 pages. Accepted for publication at SIAM Journal on Optimization

Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains underexplored in the code domain. In this paper, we introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement, with different input and output programming languages. Next, on our CodeTask-CL benchmark, we compare popular CL techniques from NLP and Vision domains. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism caused by stark distribution shifts in coding tasks. We address this issue with our proposed method, Prompt Pooling with Teacher Forcing (PP-TF), that stabilizes training by enforcing constraints on the prompt selection mechanism and leads to a 21.54% improvement over Prompt Pooling. Along with the benchmark, we establish a training pipeline that can be used for CL on code models, which we believe can motivate further development of CL methods for code models. Our code is available at https://github.com/amazon-science/codetaskcl-pptf, Comment: ACL 2023

High sensitivity detection plays a vital role in science discoveries and technological applications. While intriguing methods utilizing collective many-body correlations and quantum entanglements have been developed in physics to enhance sensitivity, their practical implementation remains challenging due to rigorous technological requirements. Here, we propose an entirely data-driven approach that harnesses the capabilities of machine learning, to significantly augment weak-signal detection sensitivity. In an atomic force sensor, our method combines a digital replica of force-free data with anomaly detection technique, devoid of any prior knowledge about the physical system or assumptions regarding the sensing process. Our findings demonstrate a significant advancement in sensitivity, achieving an order of magnitude improvement over conventional protocols in detecting a weak force of approximately $10^{-25}~\mathrm{N}$. The resulting sensitivity reaches $1.7(4) \times 10^{-25}~\mathrm{N}/\sqrt{\mathrm{Hz}}$. Our machine learning-based signal processing approach does not rely on system-specific details or processed signals, rendering it highly applicable to sensing technologies across various domains., Comment: 10 pages,4 figures

Cold atoms in an optical cavity have been widely used for quantum simulations of many-body physics, where the quantum control capability has been advancing rapidly in recent years. Here, we show the atom cavity system is universal for quantum optimization with arbitrary connectivity. We consider a single-mode cavity and develop a Raman coupling scheme by which the engineered quantum Hamiltonian for atoms directly encodes number partition problems (NPPs). The programmability is introduced by placing the atoms at different positions in the cavity with optical tweezers. The NPP solution is encoded in the ground state of atomic qubits coupled through a photonic cavity mode, that can be reached by adiabatic quantum computing (AQC). We construct an explicit mapping for the 3-SAT and vertex cover problems to be efficiently encoded by the cavity system, which costs linear overhead in the number of atomic qubits. The atom cavity encoding is further extended to quadratic unconstrained binary optimization (QUBO) problems. The encoding protocol is optimal in the cost of atom number scaling with the number of binary degrees of freedom of the computation problem. Our theory implies the atom cavity system is a promising quantum optimization platform searching for practical quantum advantage., Comment: 13 pages, 2 figures

Large language models trained on code have shown great potential to increase productivity of software developers. Several execution-based benchmarks have been proposed to evaluate functional correctness of model-generated code on simple programming problems. Nevertheless, it is expensive to perform the same evaluation on complex real-world projects considering the execution cost. On the contrary, static analysis tools such as linters, which can detect errors without running the program, haven't been well explored for evaluating code generation models. In this work, we propose a static evaluation framework to quantify static errors in Python code completions, by leveraging Abstract Syntax Trees. Compared with execution-based evaluation, our method is not only more efficient, but also applicable to code in the wild. For experiments, we collect code context from open source repos to generate one million function bodies using public models. Our static analysis reveals that Undefined Name and Unused Variable are the most common errors among others made by language models. Through extensive studies, we also show the impact of sampling temperature, model size, and context on static errors in code completions., Comment: Accepted by ACL 2023 industry track

Amidst the rapid advancements in experimental technology, noise-intermediate-scale quantum (NISQ) devices have become increasingly programmable, offering versatile opportunities to leverage quantum computational advantage. Here we explore the intricate dynamics of programmable NISQ devices for quantum reservoir computing. Using a genetic algorithm to configure the quantum reservoir dynamics, we systematically enhance the learning performance. Remarkably, a single configured quantum reservoir can simultaneously learn multiple tasks, including a synthetic oscillatory network of transcriptional regulators, chaotic motifs in gene regulatory networks, and the fractional-order Chua's circuit. Our configured quantum reservoir computing yields highly precise predictions for these learning tasks, outperforming classical reservoir computing. We also test the configured quantum reservoir computing in foreign exchange (FX) market applications and demonstrate its capability to capture the stochastic evolution of the exchange rates with significantly greater accuracy than classical reservoir computing approaches. Through comparison with classical reservoir computing, we highlight the unique role of quantum coherence in the quantum reservoir, which underpins its exceptional learning performance. Our findings suggest the exciting potential of configured quantum reservoir computing for exploiting the quantum computation power of NISQ devices in developing artificial general intelligence.

ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well., Comment: 10 pages, 7 figures, 10 tables

When searching for global optima of nonconvex unconstrained optimization problems, it is desirable that every local minimum be a global minimum. This property of having no spurious local minima is true in various problems of interest nowadays, including principal component analysis, matrix sensing, and linear neural networks. However, since these problems are non-coercive, they may yet have spurious local minima at infinity. The classical tools used to analyze the optimization landscape, namely the gradient and the Hessian, are incapable of detecting spurious local minima at infinity. In this paper, we identify conditions that certify the absence of spurious local minima at infinity, one of which is having bounded subgradient trajectories. We check that they hold in several applications of interest., Comment: 31 pages, 4 figures