arXiv subjects

Xiaopeng Li

Publications and source records attributed to Xiaopeng Li.

At least 127 records · Page 7Linked to original sources

arXiv2024

Learning Code Preference via Synthetic Evolution

Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we explore two key questions under the new challenge of code preference learning: (i) How do we train models to predict meaningful preferences for code? and (ii) How do human and LLM preferences align with verifiable code properties and developer code tastes? To this end, we propose CodeFavor, a framework for training pairwise code preference models from synthetic evolution data, including code commits and code critiques. To evaluate code preferences, we introduce CodePrefBench, a benchmark comprising 1364 rigorously curated code preference tasks to cover three verifiable properties-correctness, efficiency, and security-along with human preference. Our evaluation shows that CodeFavor holistically improves the accuracy of model-based code preferences by up to 28.8%. Meanwhile, CodeFavor models can match the performance of models with 6-9x more parameters while being 34x more cost-effective. We also rigorously validate the design choices in CodeFavor via a comprehensive set of controlled experiments. Furthermore, we discover the prohibitive costs and limitations of human-based code preference: despite spending 23.4 person-minutes on each task, 15.1-40.3% of tasks remain unsolved. Compared to model-based preference, human preference tends to be more accurate under the objective of code correctness, while being sub-optimal for non-functional objectives.

cs.LG↗

arXiv2024

Global convergence of gradient descent for phase retrieval

We propose a tensor-based criterion for benign landscape in phase retrieval and establish boundedness of gradient trajectories. This implies that gradient descent will converge to a global minimum for almost every initial point.

math.OC↗

arXiv2024

Complexity enriched dynamical phases for fermions on graphs

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 $D\sim 4^{N^α}$ for regular graphs of $d = 2$ with $0.38\leqα\leq0.59$, 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.

quant-ph↗

arXiv2024

VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving

Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called VLM-MPC, which combines the Model Predictive Controller (MPC) with VLM to evaluate how model-based control could enhance VLM decision-making. The proposed VLM-MPC is structured into two asynchronous components: The upper layer VLM generates driving parameters (e.g., desired speed, desired headway) for lower-level control based on front camera images, ego vehicle state, traffic environment conditions, and reference memory; The lower-level MPC controls the vehicle in real-time using these parameters, considering engine lag and providing state feedback to the entire system. Experiments based on the nuScenes dataset validated the effectiveness of the proposed VLM-MPC across various environments (e.g., night, rain, and intersections). The results demonstrate that the VLM-MPC consistently maintains Post Encroachment Time (PET) above safe thresholds, in contrast to some scenarios where the VLM-based control posed collision risks. Additionally, the VLM-MPC enhances smoothness compared to the real-world trajectories and VLM-based control. By comparing behaviors under different environmental settings, we highlight the VLM-MPC's capability to understand the environment and make reasoned inferences. Moreover, we validate the contributions of two key components, the reference memory and the environment encoder, to the stability of responses through ablation tests.

cs.RO↗

arXiv2024

Physics Enhanced Residual Policy Learning (PERPL) for safety cruising in mixed traffic platooning under actuator and communication delay

Linear control models have gained extensive application in vehicle control due to their simplicity, ease of use, and support for stability analysis. However, these models lack adaptability to the changing environment and multi-objective settings. Reinforcement learning (RL) models, on the other hand, offer adaptability but suffer from a lack of interpretability and generalization capabilities. This paper aims to develop a family of RL-based controllers enhanced by physics-informed policies, leveraging the advantages of both physics-based models (data-efficient and interpretable) and RL methods (flexible to multiple objectives and fast computing). We propose the Physics-Enhanced Residual Policy Learning (PERPL) framework, where the physics component provides model interpretability and stability. The learning-based Residual Policy adjusts the physics-based policy to adapt to the changing environment, thereby refining the decisions of the physics model. We apply our proposed model to decentralized control to mixed traffic platoon of Connected and Automated Vehicles (CAVs) and Human-driven Vehicles (HVs) using a constant time gap (CTG) strategy for cruising and incorporating actuator and communication delays. Experimental results demonstrate that our method achieves smaller headway errors and better oscillation dampening than linear models and RL alone in scenarios with artificially extreme conditions and real preceding vehicle trajectories. At the macroscopic level, overall traffic oscillations are also reduced as the penetration rate of CAVs employing the PERPL scheme increases.

cs.AI↗

arXiv2024

An Advanced Microscopic Energy Consumption Model for Automated Vehicle:Development, Calibration, Verification

The automated vehicle (AV) equipped with the Adaptive Cruise Control (ACC) system is expected to reduce the fuel consumption for the intelligent transportation system. This paper presents the Advanced ACC-Micro (AA-Micro) model, a new energy consumption model based on micro trajectory data, calibrated and verified by empirical data. Utilizing a commercial AV equipped with the ACC system as the test platform, experiments were conducted at the Columbus 151 Speedway, capturing data from multiple ACC and Human-Driven (HV) test runs. The calibrated AA-Micro model integrates features from traditional energy consumption models and demonstrates superior goodness of fit, achieving an impressive 90% accuracy in predicting ACC system energy consumption without overfitting. A comprehensive statistical evaluation of the AA-Micro model's applicability and adaptability in predicting energy consumption and vehicle trajectories indicated strong model consistency and reliability for ACC vehicles, evidenced by minimal variance in RMSE values and uniform RSS distributions. Conversely, significant discrepancies were observed when applying the model to HV data, underscoring the necessity for specialized models to accurately predict energy consumption for HV and ACC systems, potentially due to their distinct energy consumption characteristics.

cs.RO↗

arXiv2024

POCKET: Pruning Random Convolution Kernels for Time Series Classification from a Feature Selection Perspective

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 rely on 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 efficiently prune models, this paper eliminates feature groups contributing minimally to the classifier, thereby discarding the associated random kernels without direct evaluation. To this end, we incorporate both group-level ($l_{2,1}$-norm) and element-level ($l_2$-norm) regularizations to the classifier, formulating the pruning challenge as a group elastic net classification problem. An ADMM-based algorithm is initially introduced to solve the problem, but it is computationally intensive. Building on the ADMM-based algorithm, we then propose our core algorithm, POCKET, which significantly speeds up the process by dividing the task into two sequential stages. In Stage 1, POCKET utilizes dynamically varying penalties to efficiently achieve group sparsity within the classifier, removing features associated with zero weights and their corresponding kernels. In Stage 2, the remaining kernels and features are used to refit a $l_2$-regularized classifier for enhanced 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.

cs.LG↗

arXiv2024

DIM: Dynamic Integration of Multimodal Entity Linking with Large Language Model

Our study delves into Multimodal Entity Linking, aligning the mention in multimodal information with entities in knowledge base. Existing methods are still facing challenges like ambiguous entity representations and limited image information utilization. Thus, we propose dynamic entity extraction using ChatGPT, which dynamically extracts entities and enhances datasets. We also propose a method: Dynamically Integrate Multimodal information with knowledge base (DIM), employing the capability of the Large Language Model (LLM) for visual understanding. The LLM, such as BLIP-2, extracts information relevant to entities in the image, which can facilitate improved extraction of entity features and linking them with the dynamic entity representations provided by ChatGPT. The experiments demonstrate that our proposed DIM method outperforms the majority of existing methods on the three original datasets, and achieves state-of-the-art (SOTA) on the dynamically enhanced datasets (Wiki+, Rich+, Diverse+). For reproducibility, our code and collected datasets are released on \url{https://github.com/season1blue/DIM}.

cs.CL↗

arXiv2024

PTA: Enhancing Multimodal Sentiment Analysis through Pipelined Prediction and Translation-based Alignment

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.

cs.CL↗

arXiv2024

Adaptive quantum optimization algorithms for programmable atom-cavity systems

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.

quant-ph↗

arXiv2024

Quantum Force Sensing by Digital Twinning of Atomic Bose-Einstein Condensates

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.

quant-ph↗

arXiv2024

A Deep Dive into Large Language Models for Automated Bug Localization and Repair

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.

cs.SE↗

arXiv2024

Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey

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.

cs.CV↗

arXiv2024

DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking

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

cs.AI↗

arXiv2024

MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion

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.

cs.IR↗

arXiv2024

Pairing from repulsion in a two-dimensional Fermi gas with soft-core interactions

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.

cond-mat.quant-gas↗

arXiv2024

A Physics Enhanced Residual Learning (PERL) Framework for Vehicle Trajectory Prediction

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.

cs.LG↗

arXiv2024

PMET: Precise Model Editing in a Transformer

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.

cs.CL↗