Autonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of Web knowledge, large language models (LLMs) have shown potential in human-level intelligence, leading to a surge in research on LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of LLM-based autonomous agents from a holistic perspective. We first discuss the construction of LLM-based autonomous agents, proposing a unified framework that encompasses much of previous work. Then, we present a overview of the diverse applications of LLM-based autonomous agents in social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field.
Spreadsheets are very common for information processing to support decision making by both professional developers and non-technical end users. Moreover, business intelligence and artificial intelligence are increasingly popular in the industry nowadays, where spreadsheets have been used as, or integrated into, intelligent or expert systems in various application domains. However, it has been repeatedly reported that faults often exist in operational spreadsheets, which could severely compromise the quality of conclusions and decisions based on the spreadsheets. With a view to systematically examining this problem via survey of existing work, we have conducted a comprehensive literature review on the quality issues and related techniques of spreadsheets over a 35.5-year period (from January 1987 to June 2022) for target journals and a 10.5-year period (from January 2012 to June 2022) for target conferences. Among other findings, two major ones are: (a) Spreadsheet quality is best addressed throughout the whole spreadsheet life cycle, rather than just focusing on a few specific stages of the life cycle. (b) Relatively more studies focus on spreadsheet testing and debugging (related to fault detection and removal) when compared with spreadsheet specification, modeling, and design (related to development). As prevention is better than cure, more research should be performed on the early stages of the spreadsheet life cycle. Enlightened by our comprehensive review, we have identified the major research gaps as well as highlighted key research directions for future work in the area.
Model-based reinforcement learning is a promising direction to improve the sample efficiency of reinforcement learning with learning a model of the environment. Previous model learning methods aim at fitting the transition data, and commonly employ a supervised learning approach to minimize the distance between the predicted state and the real state. The supervised model learning methods, however, diverge from the ultimate goal of model learning, i.e., optimizing the learned-in-the-model policy. In this work, we investigate how model learning and policy learning can share the same objective of maximizing the expected return in the real environment. We find model learning towards this objective can result in a target of enhancing the similarity between the gradient on generated data and the gradient on the real data. We thus derive the gradient of the model from this target and propose the Model Gradient algorithm (MG) to integrate this novel model learning approach with policy-gradient-based policy optimization. We conduct experiments on multiple locomotion control tasks and find that MG can not only achieve high sample efficiency but also lead to better convergence performance compared to traditional model-based reinforcement learning approaches.
Graphs that are used to model real-world entities with vertices and relationships among entities with edges, have proven to be a powerful tool for describing real-world problems in applications. In most real-world scenarios, entities and their relationships are subject to constant changes. Graphs that record such changes are called dynamic graphs. In recent years, the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics results. As the scale of dynamic graphs becomes larger, higher performance requirements are demanded to dynamic graph processing systems. With the massive parallel processing power and high memory bandwidth, GPUs become mainstream vehicles to accelerate dynamic graph processing tasks. GPU-based dynamic graph processing systems mainly address two challenges: maintaining the graph data when updates occur (i.e., graph updating) and producing analytics results in time (i.e., graph computing). In this paper, we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph computing. To comprehensively discuss existing dynamic graph processing systems on GPUs, we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph computing. In addition, we discuss the challenges and future research directions of dynamic graph processing on GPUs.
Significant progress has been made in machine learning with large amounts of clean labels and static data. However, in many real-world applications, the data often changes with time and it is difficult to obtain massive clean annotations, that is, noisy labels and time series are faced simultaneously. For example, in product-buyer evaluation, each sample records the daily time behavior of users, but the long transaction period brings difficulties to analysis, and salespeople often erroneously annotate the user’s purchase behavior. Such a novel setting, to our best knowledge, has not been thoroughly studied yet, and there is still a lack of effective machine learning methods. In this paper, we present a systematic approach RTS both theoretically and empirically, consisting of two components, Noise-Tolerant Time Series Representation and Purified Oversampling Learning. Specifically, we propose reducing label noise’s destructive impact to obtain robust feature representations and potential clean samples. Then, a novel learning method based on the purified data and time series oversampling is adopted to train an unbiased model. Theoretical analysis proves that our proposal can improve the quality of the noisy data set. Empirical experiments on diverse tasks, such as the house-buyer evaluation task from real-world applications and various benchmark tasks, clearly demonstrate that our new algorithm robustly outperforms many competitive methods.
Uncertain Knowledge Graphs (UKGs) are used to characterize the inherent uncertainty of knowledge and have a richer semantic structure than deterministic knowledge graphs. The research on the embedding of UKG has only recently begun, Uncertain Knowledge Graph Embedding (UKGE) model has a certain effect on solving this problem. However, there are still unresolved issues. On the one hand, when reasoning the confidence of unseen relation facts, the introduced probabilistic soft logic cannot be used to combine multi-path and multi-step global information, leading to information loss. On the other hand, the existing UKG embedding model can only model symmetric relation facts, but the embedding problem of asymmetric relation facts has not be addressed. To address the above issues, a Multiplex Uncertain Knowledge Graph Embedding (MUKGE) model is proposed in this paper. First, to combine multiple information and achieve more accurate results in confidence reasoning, the Uncertain ResourceRank (URR) reasoning algorithm is introduced. Second, the asymmetry in the UKG is defined. To embed asymmetric relation facts of UKG, a multi-relation embedding model is proposed. Finally, experiments are carried out on different datasets via 4 tasks to verify the effectiveness of MUKGE. The results of experiments demonstrate that MUKGE can obtain better overall performance than the baselines, and it helps advance the research on UKG embedding.
Container-based virtualization is becoming increasingly popular in cloud computing due to its efficiency and flexibility. Resource isolation is a fundamental property of containers. Existing works have indicated weak resource isolation could cause significant performance degradation for containerized applications and enhanced resource isolation. However, current studies have almost not discussed the isolation problems of page cache which is a key resource for containers. Containers leverage memory cgroup to control page cache usage. Unfortunately, existing policy introduces two major problems in a container-based environment. First, containers can utilize more memory than limited by their cgroup, effectively breaking memory isolation. Second, the OS kernel has to evict page cache to make space for newly-arrived memory requests, slowing down containerized applications. This paper performs an empirical study of these problems and demonstrates the performance impacts on containerized applications. Then we propose pCache (precise control of page cache) to address the problems by dividing page cache into private and shared and controlling both kinds of page cache separately and precisely. To do so, pCache leverages two new technologies: fair account (f-account) and evict on demand (EoD). F-account splits the shared page cache charging based on per-container share to prevent containers from using memory for free, enhancing memory isolation. And EoD reduces unnecessary page cache evictions to avoid the performance impacts. The evaluation results demonstrate that our system can effectively enhance memory isolation for containers and achieve substantial performance improvement over the original page cache management policy.
In this paper, we propose a novel warm restart technique using a new logarithmic step size for the stochastic gradient descent (SGD) approach. For smooth and non-convex functions, we establish an
With the development of information technology and cloud computing, data sharing has become an important part of scientific research. In traditional data sharing, data is stored on a third-party storage platform, which causes the owner to lose control of the data. As a result, there are issues of intentional data leakage and tampering by third parties, and the private information contained in the data may lead to more significant issues. Furthermore, data is frequently maintained on multiple storage platforms, posing significant hurdles in terms of enlisting multiple parties to engage in data sharing while maintaining consistency. In this work, we propose a new architecture for applying blockchains to data sharing and achieve efficient and reliable data sharing among heterogeneous blockchains. We design a new data sharing transaction mechanism based on the system architecture to protect the security of the raw data and the processing process. We also design and implement a hybrid concurrency control protocol to overcome issues caused by the large differences in blockchain performance in our system and to improve the success rate of data sharing transactions. We took Ethereum and Hyperledger Fabric as examples to conduct cross-blockchain data sharing experiments. The results show that our system achieves data sharing across heterogeneous blockchains with reasonable performance and has high scalability.
The sixth-generation (6G) wireless communication system is envisioned be cable of providing highly dependable services by integrating with native reliable and trustworthy functionalities. Zero-trust vehicular networks is one of the typical scenarios for 6G dependable services. Under the technical framework of vehicle-and-roadside collaboration, more and more on-board devices and roadside infrastructures will communicate for information exchange. The reliability and security of the vehicle-and-roadside collaboration will directly affect the transportation safety. Considering a zero-trust vehicular environment, to prevent malicious vehicles from uploading false or invalid information, we propose a malicious vehicle identity disclosure approach based on the Shamir secret sharing scheme. Meanwhile, a two-layer consortium blockchain architecture and smart contracts are designed to protect the identity and privacy of benign vehicles as well as the security of their private data. After that, in order to improve the efficiency of vehicle identity disclosure, we present an inspection policy based on zero-sum game theory and a roadside unit incentive mechanism jointly using contract theory and subjective logic model. We verify the performance of the entire zero-trust solution through extensive simulation experiments. On the premise of protecting the vehicle privacy, our solution is demonstrated to significantly improve the reliability and security of 6G vehicular networks.
Hybrid memory systems composed of dynamic random access memory (DRAM) and Non-volatile memory (NVM) often exploit page migration technologies to fully take the advantages of different memory media. Most previous proposals usually migrate data at a granularity of 4 KB pages, and thus waste memory bandwidth and DRAM resource. In this paper, we propose Mocha, a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically, but manages them in a cache/memory hierarchy. Since the commercial NVM device–Intel Optane DC Persistent Memory Modules (DCPMM) actually access the physical media at a granularity of 256 bytes (an Optane block), we manage the DRAM cache at the 256-byte size to adapt to this feature of Optane. This design not only enables fine-grained data migration and management for the DRAM cache, but also avoids write amplification for Intel Optane DCPMM. We also create an Indirect Address Cache (IAC) in Hybrid Memory Controller (HMC) and propose a reverse address mapping table in the DRAM to speed up address translation and cache replacement. Moreover, we exploit a utility-based caching mechanism to filter cold blocks in the NVM, and further improve the efficiency of the DRAM cache. We implement Mocha in an architectural simulator. Experimental results show that Mocha can improve application performance by 8.2% on average (up to 24.6%), reduce 6.9% energy consumption and 25.9% data migration traffic on average, compared with a typical hybrid memory architecture–HSCC.
A great many practical applications have observed knowledge evolution, i.e., continuous born of new knowledge, with its formation influenced by the structure of historical knowledge. This observation gives rise to evolving knowledge graphs whose structure temporally grows over time. However, both the modal characterization and the algorithmic implementation of evolving knowledge graphs remain unexplored. To this end, we propose EvolveKG – a general framework that enables algorithms in the static knowledge graphs to learn the evolving ones. EvolveKG quantifies the influence of a historical fact on a current one, called the effectiveness of the fact, and makes knowledge prediction by leveraging all the cross-time knowledge interaction. The novelty of EvolveKG lies in Derivative Graph – a weighted snapshot of evolution at a certain time. Particularly, each weight quantifies knowledge effectiveness through a temporarily decaying function of consistency and attenuation, two proposed factors depicting whether or not the effectiveness of a fact fades away with time. Besides, considering both knowledge creation and loss, we obtain higher prediction accuracy when the effectiveness of all the facts increases with time or remains unchanged. Under four real datasets, the superiority of EvolveKG is confirmed in prediction accuracy.
Deterministic databases are able to reduce coordination costs in a replication. This property has fostered a significant interest in the design of efficient deterministic concurrency control protocols. However, the state-of-the-art deterministic concurrency control protocol Aria has three issues. First, it is impractical to configure a suitable batch size when the read-write set is unknown. Second, Aria running in low-concurrency scenarios, e.g., a single-thread scenario, suffers from the same conflicts as running in high-concurrency scenarios. Third, the single-version schema brings write-after-write conflicts.
To address these issues, we propose Gria, an efficient deterministic concurrency control protocol. Gria has the following properties. First, the batch size of Gria is auto-scaling. Second, Gria’s conflict probability in low-concurrency scenarios is lower than that in high-concurrency scenarios. Third, Gria has no write-after-write conflicts by adopting a multi-version structure. To further reduce conflicts, we propose two optimizations: a reordering mechanism as well as a rechecking strategy. The evaluation result on two popular benchmarks shows that Gria outperforms Aria by 13x.
Federated learning (FL) has emerged to break data-silo and protect clients’ privacy in the field of artificial intelligence. However, deep leakage from gradient (DLG) attack can fully reconstruct clients’ data from the submitted gradient, which threatens the fundamental privacy of FL. Although cryptology and differential privacy prevent privacy leakage from gradient, they bring negative effect on communication overhead or model performance. Moreover, the original distribution of local gradient has been changed in these schemes, which makes it difficult to defend against adversarial attack. In this paper, we propose a novel federated learning framework with model decomposition, aggregation and assembling (FedDAA), along with a training algorithm, to train federated model, where local gradient is decomposed into multiple blocks and sent to different proxy servers to complete aggregation. To bring better privacy protection performance to FedDAA, an indicator is designed based on image structural similarity to measure privacy leakage under DLG attack and an optimization method is given to protect privacy with the least proxy servers. In addition, we give defense schemes against adversarial attack in FedDAA and design an algorithm to verify the correctness of aggregated results. Experimental results demonstrate that FedDAA can reduce the structural similarity between the reconstructed image and the original image to 0.014 and remain model convergence accuracy as 0.952, thus having the best privacy protection performance and model training effect. More importantly, defense schemes against adversarial attack are compatible with privacy protection in FedDAA and the defense effects are not weaker than those in the traditional FL. Moreover, verification algorithm of aggregation results brings about negligible overhead to FedDAA.
Recently advancements in deep learning models have significantly facilitated the development of sequential recommender systems (SRS). However, the current deep model structures are limited in their ability to learn high-quality embeddings with insufficient data. Meanwhile, highly skewed long-tail distribution is very common in recommender systems. Therefore, in this paper, we focus on enhancing the representation of tail items to improve sequential recommendation performance. Through empirical studies on benchmarks, we surprisingly observe that both the ranking performance and training procedure are greatly hindered by the poorly optimized tail item embeddings. To address this issue, we propose a sequential recommendation framework named TailRec that enables contextual information of tail item well-leveraged and greatly improves its corresponding representation. Given the characteristics of the sequential recommendation task, the surrounding interaction records of each tail item are regarded as contextual information without leveraging any additional side information. This approach allows for the mining of contextual information from cross-sequence behaviors to boost the performance of sequential recommendations. Such a light contextual filtering component is plug-and-play for a series of SRS models. To verify the effectiveness of the proposed TailRec, we conduct extensive experiments over several popular benchmark recommenders. The experimental results demonstrate that TailRec can greatly improve the recommendation results and speed up the training process. The codes of our methods have been available
See github.com/Mingyue-Cheng/TailRec website.
.
Recent years have seen the wide application of natural language processing (NLP) models in crucial areas such as finance, medical treatment, and news media, raising concerns about the model robustness and vulnerabilities. We find that prompt paradigm can probe special robust defects of pre-trained language models. Malicious prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via mask-filling. Experimental results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym substitution. Then, we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization framework. Experiments on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application portability. Among the existing deep learning compilers, TVM is well known for its efficiency in code generation and optimization across diverse hardware devices. In the meanwhile, the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning workloads. This paper combines the trends in these two directions. Specifically, we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as Sunway. In addition, we leverage the architecture features during the compilation such as core group for massive parallelism, DMA for high bandwidth memory transfer and local device memory for data locality, in order to generate efficient codes for deep learning workloads on Sunway. The experiment results show that the codes generated by swTVM achieve 1.79
BERT is a representative pre-trained language model that has drawn extensive attention for significant improvements in downstream Natural Language Processing (NLP) tasks. The complex architecture and massive parameters bring BERT competitive performance but also result in slow speed at model inference time. To speed up BERT inference, FastBERT realizes adaptive inference with an acceptable drop in accuracy based on knowledge distillation and the early-exit technique. However, many factors may limit the performance of FastBERT, such as the teacher classifier that is not knowledgeable enough, the batch size shrinkage and the redundant computation of student classifiers. To overcome these limitations, we propose a new BERT inference method with GPU-Efficient Exit Prediction (GEEP). GEEP leverages the shared exit loss to simplify the training process of FastBERT from two steps into only one step and makes the teacher classifier more knowledgeable by feeding diverse Transformer outputs to the teacher classifier. In addition, the exit layer prediction technique is proposed to utilize a GPU hash table to handle the token-level exit layer distribution and to sort test samples by predicted exit layers. In this way, GEEP can avoid batch size shrinkage and redundant computation of student classifiers. Experimental results on twelve public English and Chinese NLP datasets prove the effectiveness of the proposed approach. The source codes of GEEP will be released to the public upon paper acceptance.
A large body of research effort has been dedicated to automated issue classification for Issue Tracking Systems (ITSs). Although the existing approaches have shown promising performance, the different design choices, including the different textual fields, feature representation methods and machine learning algorithms adopted by existing approaches, have not been comprehensively compared and analyzed. To fill this gap, we perform the first extensive study of automated issue classification on 9 state-of-the-art issue classification approaches. Our experimental results on the widely studied dataset reveal multiple practical guidelines for automated issue classification, including: (1) Training separate models for the issue titles and descriptions and then combining these two models tend to achieve better performance for issue classification; (2) Word embedding with Long Short-Term Memory (LSTM) can better extract features from the textual fields in the issues, and hence, lead to better issue classification models; (3) There exist certain terms in the textual fields that are helpful for building more discriminating classifiers between bug and non-bug issues; (4) The performance of the issue classification model is not sensitive to the choices of ML algorithms. Based on our study outcomes, we further propose an advanced issue classification approach, DEEPLABEL, which can achieve better performance compared with the existing issue classification approaches.
The use of all samples in the optimization process does not produce robust results in datasets with label noise. Because the gradients calculated according to the losses of the noisy samples cause the optimization process to go in the wrong direction. In this paper, we recommend using samples with loss less than a threshold determined during the optimization, instead of using all samples in the mini-batch. Our proposed method, Adaptive-k, aims to exclude label noise samples from the optimization process and make the process robust. On noisy datasets, we found that using a threshold-based approach, such as Adaptive-k, produces better results than using all samples or a fixed number of low-loss samples in the mini-batch. On the basis of our theoretical analysis and experimental results, we show that the Adaptive-k method is closest to the performance of the Oracle, in which noisy samples are entirely removed from the dataset. Adaptive-k is a simple but effective method. It does not require prior knowledge of the noise ratio of the dataset, does not require additional model training, and does not increase training time significantly. In the experiments, we also show that Adaptive-k is compatible with different optimizers such as SGD, SGDM, and Adam. The code for Adaptive-k is available at GitHub.
Entity alignment (EA) is an important technique aiming to find the same real entity between two different source knowledge graphs (KGs). Current methods typically learn the embedding of entities for EA from the structure of KGs for EA. Most EA models are designed for rich-resource languages, requiring sufficient resources such as a parallel corpus and pre-trained language models. However, low-resource language KGs have received less attention, and current models demonstrate poor performance on those low-resource KGs. Recently, researchers have fused relation information and attributes for entity representations to enhance the entity alignment performance, but the relation semantics are often ignored. To address these issues, we propose a novel Semantic-aware Graph Neural Network (SGNN) for entity alignment. First, we generate pseudo sentences according to the relation triples and produce representations using pre-trained models. Second, our approach explores semantic information from the connected relations by a graph neural network. Our model captures expanded feature information from KGs. Experimental results using three low-resource languages demonstrate that our proposed SGNN approach out performs better than state-of-the-art alignment methods on three proposed datasets and three public datasets.
In crowdsourcing scenarios, we can obtain each instance’s multiple noisy labels from different crowd workers and then infer its integrated label via label aggregation. In spite of the effectiveness of label aggregation methods, there still remains a certain level of noise in the integrated labels. Thus, some noise correction methods have been proposed to reduce the impact of noise in recent years. However, to the best of our knowledge, existing methods rarely consider an instance’s information from both its features and multiple noisy labels simultaneously when identifying a noise instance. In this study, we argue that the more distinguishable an instance’s features but the noisier its multiple noisy labels, the more likely it is a noise instance. Based on this premise, we propose a label distribution similarity-based noise correction (LDSNC) method. To measure whether an instance’s features are distinguishable, we obtain each instance’s predicted label distribution by building multiple classifiers using instances’ features and their integrated labels. To measure whether an instance’s multiple noisy labels are noisy, we obtain each instance’s multiple noisy label distribution using its multiple noisy labels. Then, we use the Kullback-Leibler (KL) divergence to calculate the similarity between the predicted label distribution and multiple noisy label distribution and define the instance with the lower similarity as a noise instance. The extensive experimental results on 34 simulated and four real-world crowdsourced datasets validate the effectiveness of our method.
With the recent demonstration of quantum computers, interests in the field of reversible logic synthesis and optimization have taken a different turn. As every quantum operation is inherently reversible, there is an immense motivation for exploring reversible circuit design and optimization. When it comes to faults in circuits, the parity-preserving feature donates to the detection of permanent and temporary faults. In the context of reversible circuits, the parity-preserving property ensures that the input and output parities are equal. In this paper we suggest six parity-preserving reversible blocks (Z, F, A, T, S, and L) with improved quantum cost. The reversible blocks are synthesized using an existing synthesis method that generates a netlist of multiple-control Toffoli (MCT) gates. Various optimization rules are applied at the reversible circuit level, followed by transformation into a netlist of elementary quantum gates from the NCV library. The designs of full-adder and unsigned and signed multipliers are proposed using the functional blocks that possess parity-preserving properties. The proposed designs are compared with state-of-the-art methods and found to be better in terms of cost of realization. Average savings of 25.04%, 20.89%, 21.17%, and 51.03%, and 18.59%, 13.82%, 13.82%, and 27.65% respectively, are observed for 4-bit unsigned and 5-bit signed multipliers in terms of quantum cost, garbage output, constant input, and gate count as compared to recent works.
Protein acetylation refers to a process of adding acetyl groups (CH3CO-) to lysine residues on protein chains. As one of the most commonly used protein post-translational modifications, lysine acetylation plays an important role in different organisms. In our study, we developed a human-specific method which uses a cascade classifier of complex-valued polynomial model (CVPM), combined with sequence and structural feature descriptors to solve the problem of imbalance between positive and negative samples. Complex-valued gene expression programming and differential evolution are utilized to search the optimal CVPM model. We also made a systematic and comprehensive analysis of the acetylation data and the prediction results. The performances of our proposed method are 79.15% in Sp, 78.17% in Sn, 78.66% in ACC 78.76% in F1, and 0.5733 in MCC, which performs better than other state-of-the-art methods.
Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion recognition. Existing approaches use directional pairwise attention or a message hub to fuse language, visual, and audio modalities. However, these fusion methods are often quadratic in complexity with respect to the modal sequence length, bring redundant information and are not efficient. In this paper, we propose an efficient neural network to learn modality-fused representations with CB-Transformer (LMR-CBT) for multimodal emotion recognition from unaligned multi-modal sequences. Specifically, we first perform feature extraction for the three modalities respectively to obtain the local structure of the sequences. Then, we design an innovative asymmetric transformer with cross-modal blocks (CB-Transformer) that enables complementary learning of different modalities, mainly divided into local temporal learning, cross-modal feature fusion and global self-attention representations. In addition, we splice the fused features with the original features to classify the emotions of the sequences. Finally, we conduct word-aligned and unaligned experiments on three challenging datasets, IEMOCAP, CMU-MOSI, and CMU-MOSEI. The experimental results show the superiority and efficiency of our proposed method in both settings. Compared with the mainstream methods, our approach reaches the state-of-the-art with a minimum number of parameters.
Estimating rigid transformation using noisy correspondences is critical to feature-based point cloud registration. Recently, a series of studies have attempted to combine traditional robust model fitting with deep learning. Among them, DHVR proposed a hough voting-based method, achieving new state-of-the-art performance. However, we find voting on rotation and translation simultaneously hinders achieving better performance. Therefore, we proposed a new hough voting-based method, which decouples rotation and translation space. Specifically, we first utilize hough voting and a neural network to estimate rotation. Then based on good initialization on rotation, we can easily obtain accurate rigid transformation. Extensive experiments on 3DMatch and 3DLoMatch datasets show that our method achieves comparable performances over the state-of-the-art methods. We further demonstrate the generalization of our method by experimenting on KITTI dataset.
The rapid development of ISAs has brought the issue of software compatibility to the forefront in the embedded field. To address this challenge, one of the promising solutions is the adoption of a multiple-ISA processor that supports multiple different ISAs. However, due to constraints in cost and performance, the architecture of a multiple-ISA processor must be carefully optimized to meet the specific requirements of embedded systems. By exploring the RISC-V and ARM Thumb ISAs, this paper proposes RVAM16, which is an optimized multiple-ISA processor microarchitecture for embedded devices based on hardware binary translation technique. The results show that, when running non-native ARM Thumb programs, RVAM16 achieves a significant speedup of over 2.73× with less area and energy consumption compared to using hardware binary translation alone, reaching more than 70% of the performance of native RISC-V programs.
