With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenarios, during which the domain generalization ability can be seriously degraded. In this paper, we explore fine-tuning stereo matching networks without compromising their robustness to unseen domains. Our motivation stems from comparing Ground Truth (GT) versus Pseudo Label (PL) for fine-tuning: GT degrades, but PL preserves the domain generalization ability. Empirically, we find the difference between GT and PL implies valuable information that can regularize networks during fine-tuning. We also propose a framework to utilize this difference for fine-tuning, consisting of a frozen Teacher, an exponential moving average (EMA) Teacher, and a Student network. The core idea is to utilize the EMA Teacher to measure what the Student has learned and dynamically improve GT and PL for fine-tuning. We integrate our framework with state-of-the-art networks and evaluate its effectiveness on several real-world datasets. Extensive experiments show that our method effectively preserves the domain generalization ability during fine-tuning.
One-bit sampling has emerged as a promising technique in multiple-input multiple-output (MIMO) radar systems due to its ability to significantly reduce data volume and processing requirements. Nevertheless, current detection methods have not adequately addressed the impact of colored noise, which is frequently encountered in real scenarios. In this paper, we present a novel detection method that accounts for colored noise in MIMO radar systems. Specifically, we derive Rao's test by computing the derivative of the likelihood function with respect to the target reflectivity parameter and the Fisher information matrix, resulting in a detector that takes the form of a weighted matched filter. To ensure the constant false alarm rate (CFAR) property, we also consider noise covariance uncertainty and examine its effect on the probability of false alarm. The detection probability is also studied analytically. Simulation results demonstrate that the proposed detector provides considerable performance gains in the presence of colored noise.
Self-supervised contrastive learning strategy has attracted remarkable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of the image that benefit generic object recognition, whereas such coarse-grained features are insufficient for fine-grained visual recognition. In this paper, we present to incorporate the subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework. Specifically, a novel pretext task called Local Discrimination (LoDisc) is proposed to explicitly supervise self-supervised model's focus towards local pivotal regions which are captured by a simple-but-effective location-wise mask sampling strategy. We show that Local Discrimination pretext task can effectively enhance fine-grained clues in important local regions, and the global-local framework further refines the fine-grained feature representations of images. Extensive experimental results on different fine-grained object recognition tasks demonstrate that the proposed method can lead to a decent improvement in different evaluation settings. Meanwhile, the proposed method is also effective in general object recognition tasks.
We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language models, training data and training recipes. Our extensive experiments showed that better quality of data combined with better training recipes, smaller LMMs can consistently achieve on-par performances compared to bigger LMMs. Under our framework, we train a family of small-scale LMMs. Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. We hope our findings can serve as baselines for future research in terms of data scaling, training setups and model selections. Our model weights and codes will be made public.
Energy efficiency (EE) is a challenging task in integrated sensing and communication (ISAC) systems, where high spectral efficiency and low energy consumption appear as conflicting requirements. Although passive reconfigurable intelligent surface (RIS) has emerged as a promising technology for enhancing the EE of the ISAC system, the multiplicative fading feature hinders its effectiveness. This paper proposes the use of active RIS with its amplification gains to assist the ISAC system for EE improvement. Specifically, we formulate an EE optimization problem in an active RIS-aided ISAC system under system power budgets, considering constraints on user communication quality of service and sensing signal-to-noise ratio (SNR). A novel alternating optimization algorithm is developed to address the highly non-convex problem by leveraging a combination of the generalized Rayleigh quotient optimization approach, semidefinite relaxation (SDR), and the majorization-minimization (MM) framework. Furthermore, to accelerate the algorithm and reduce computational complexity, we derive a semi-closed form for eigenvalue determination. Numerical results demonstrate the effectiveness of the proposed approach, showcasing significant improvements in EE compared to both passive RIS and spectrum efficiency optimization cases.
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limitations. In order to address these challenges, researchers have pursued two primary strategies, knowledge editing and retrieval augmentation, to enhance LLMs by incorporating external information from different aspects. Nevertheless, there is still a notable absence of a comprehensive survey. In this paper, we propose a review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications. In addition, we conduct an in-depth analysis of different methods and point out potential research directions in the future. We hope this survey offers the community quick access and a comprehensive overview of this research area, with the intention of inspiring future research endeavors.
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), leading to remarkable advancements in text understanding and generation. Nevertheless, alongside these strides, LLMs exhibit a critical tendency to produce hallucinations, resulting in content that is inconsistent with real-world facts or user inputs. This phenomenon poses substantial challenges to their practical deployment and raises concerns over the reliability of LLMs in real-world scenarios, which attracts increasing attention to detect and mitigate these hallucinations. In this survey, we aim to provide a thorough and in-depth overview of recent advances in the field of LLM hallucinations. We begin with an innovative taxonomy of LLM hallucinations, then delve into the factors contributing to hallucinations. Subsequently, we present a comprehensive overview of hallucination detection methods and benchmarks. Additionally, representative approaches designed to mitigate hallucinations are introduced accordingly. Finally, we analyze the challenges that highlight the current limitations and formulate open questions, aiming to delineate pathways for future research on hallucinations in LLMs.
With the availability of extraordinarily huge data sets, solving the problems of distributed statistical methodology and computing for such data sets has become increasingly crucial in the big data area. In this paper, we focus on the distributed sparse penalized linear log-contrast model in massive compositional data. In particular, two distributed optimization techniques under centralized and decentralized topologies are proposed for solving the two different constrained convex optimization problems. Both two proposed algorithms are based on the frameworks of Alternating Direction Method of Multipliers (ADMM) and Coordinate Descent Method of Multipliers(CDMM, Lin et al., 2014, Biometrika). It is worth emphasizing that, in the decentralized topology, we introduce a distributed coordinate-wise descent algorithm based on Group ADMM(GADMM, Elgabli et al., 2020, Journal of Machine Learning Research) for obtaining a communication-efficient regularized estimation. Correspondingly, the convergence theories of the proposed algorithms are rigorously established under some regularity conditions. Numerical experiments on both synthetic and real data are conducted to evaluate our proposed algorithms.
In recent years, two time series classification models, ROCKET and MINIROCKET, have attracted much attention for their low training cost and state-of-the-art accuracy. Utilizing random 1-D convolutional kernels without training, ROCKET and MINIROCKET can rapidly extract features from time series data, allowing for the efficient fitting of linear classifiers. However, to comprehensively capture useful features, a large number of random kernels are required, which is incompatible for resource-constrained devices. Therefore, a heuristic evolutionary algorithm named S-ROCKET is devised to recognize and prune redundant kernels. Nevertheless, the inherent nature of evolutionary algorithms renders the evaluation of kernels within S-ROCKET an unacceptable time-consuming process. In this paper, diverging from S-ROCKET, which directly evaluates random kernels with nonsignificant differences, we remove kernels from a feature selection perspective by eliminating associating connections in the sequential classification layer. To this end, we start by formulating the pruning challenge as a Group Elastic Net classification problem and employ the ADMM method to arrive at a solution. Sequentially, we accelerate the aforementioned time-consuming solving process by bifurcating the $l_{2,1}$ and $l_2$ regularizations into two sequential stages and solve them separately, which ultimately forms our core algorithm, named P-ROCKET. Stage 1 of P-ROCKET employs group-wise regularization similarly to our initial ADMM-based Algorithm, but introduces dynamically varying penalties to greatly accelerate the process. To mitigate overfitting, Stage 2 of P-ROCKET implements element-wise regularization to refit a linear classifier, utilizing the retained features.
We propose a high-rate scheme for discretely-modulated continuous-variable quantum key distribution (DM CVQKD) using quantum machine learning technologies, which divides the whole CVQKD system into three parts, i.e., the initialization part that is used for training and estimating quantum classifier, the prediction part that is used for generating highly correlated raw keys, and the data-postprocessing part that generates the final secret key string shared by Alice and Bob. To this end, a low-complexity quantum k-nearest neighbor (QkNN) classifier is designed for predicting the lossy discretely-modulated coherent states (DMCSs) at Bob's side. The performance of the proposed QkNN-based CVQKD especially in terms of machine learning metrics and complexity is analyzed, and its theoretical security is proved by using semi-definite program (SDP) method. Numerical simulation shows that the secret key rate of our proposed scheme is explicitly superior to the existing DM CVQKD protocols, and it can be further enhanced with the increase of modulation variance.