Self-improving alignment leveraging large language models (LLMs) to automatically generate synthetic preference data has garnered significant attention as a means of reducing reliance on human labelers. These methods typically employ the LLM-as-a-judge mechanism, where the LLM generates responses and then employs itself to judge which response best aligns with the given prompt for curating the binary self-preferred dataset. However, these methods encounter two major challenges: (1) LLM-as-a-judge often produces error-prone evaluations, resulting in low-quality preference annotation, and (2) their optimization strategies often overlook the strength of preferences within binary pairs, leading to overfitting. This paper proposes a novel method, Preference-Strength-aware Optimization (PSO), to address these issues. Specifically, PSO frames the preference annotation process as a judgment token prediction task using the generative preference model to produce reliable judgments. The predicted judgment token indicates the preferred response and its corresponding probability reflects the disparity between responses, referred to as preference strength. Based on this strength, we introduce a new preference-strength-aware loss to adaptively reweight the impact of different response pairs on optimization, concentrating the model's learning on high-quality response pairs. Our experiments demonstrate that PSO significantly improves performance in preference benchmarks, achieving stronger alignment with human preferences, reducing verbose responses, and mitigating overfitting. Furthermore, PSO exhibits robust generalization and sample efficiency, offering a scalable and promising solution for LLM alignment without relying on human-annotated preferences.

Super-resolution (SR) of remote sensing images (RSIs) has been improved significantly with the development of deep learning. However, better performances usually come from complex network architectures and require a substantial number of parameters. Moreover, many methods can only deal with SR of single and fixed-scale factors. As such, we propose a binary lightweight SR (BLiSR) method to decrease the computation and storage burden and increase the practicality of SR, where we employ a binary neural network (BNN) as the backbone and leverage a binary continuous up-sampling module (BCUM) to achieve arbitrary scale RSI SR. Specifically, we introduce an adaptive binary convolution (ABConv) as the basic unit of BLiSR, which can adaptively adjust the learnable parameters to fit the distribution of full-precision weights and activations. Then, a scalable hyperbolic tangent function is presented to approximate the Sign function in backpropagation and increase the learning capability of BNN. Furthermore, we design a lightweight SR network that considers the full-precision information flow of BNN. The network comprises several basic binary units and a multilayer group fusion block (MGFB), which can extract and fuse the multilevel information from LR images, respectively. Finally, BCUM can predict the pixel values of HR images based on the frequency implicit representation network (IRN) and reconstruct the LR images at arbitrary scales. Extensive experiments on four RSI datasets demonstrate that the proposed BLiSR is superior to several lightweight state-of-the-art (SOTA) methods on both fixed and arbitrary scale SR settings, with a better balance of complexity and performance.

Existing neural architecture search (NAS) methods usually explore a limited feature-transformation-only search space, ignoring other advanced feature operations such as feature self-calibration by attention and dynamic convolutions. This disables the NAS algorithms to discover more advanced network architectures. We address this limitation by additionally exploiting feature self-calibration operations, resulting in a heterogeneous search space. To solve the challenges of operation heterogeneity and significantly larger search space, we formulate a neural operator search (NOS) method. NOS presents a novel heterogeneous residual block for integrating the heterogeneous operations in a unified structure, and an attention guided search strategy for facilitating the search process over a vast space. Extensive experiments show that NOS can search novel cell architectures with highly competitive performance on the CIFAR and ImageNet benchmarks.

Dynamic ridesharing refers to services that arrange one-time shared rides on short notice. It underpins various real-world intelligent transportation applications such as car-pooling, food delivery and last-mile logistics. A core operation in dynamic ridesharing is the “insertion operator”. Given a worker and a feasible route which contains a sequence of origin-destination pairs from previous requests, the insertion operator inserts a new origin-destination pair from a newly arrived request into the current route such that certain objective is optimized. Common optimization objectives include minimizing the maximum/sum flow time of all requests and minimizing the total travel time of the worker. Despite its frequent usage, the insertion operator has a time complexity of$O(n^3)$, where$n$is the number of all requests assigned to the worker. The cubic running time of insertion fundamentally limits the efficiency of urban-scale dynamic ridesharing based applications. In this paper, we propose a novel partition framework and a dynamic programming based insertion with a time complexity of$O(n^2)$. We further improve the time efficiency of the insertion operator to$O(n)$harnessing efficient index structures, such as fenwick tree. Evaluations on two real-world large-scale datasets show that our methods can accelerate insertion by 1.5 to 998.1 times.

Vehicle reidentification, aiming at identifying vehicles across images, has drawn a lot of attention and has made significant achievements in recent years. However, vehicle reidentification remains a challenging task caused by severe appearance changes due to different orientations. In practice, the result of reidentification is greatly influenced by the pose of vehicles, and we call this influence as a pose barrier problem. One way to address the pose barrier problem is to train a feature representation that is invariant for various vehicle poses. To this end, we present pose robust features (PRFs) that contains two components: 1) pose-invariant features (PIFs) and 2) pose discriminative features (PDFs). On the one hand, PIF is the expert in exploring the overall characteristic of vehicles. When training PIF, we adopt an identity classifier as well as an orientation classifier. In addition, an adversarial loss is deployed in the PIF network. On the other hand, we design a PDF network, which has a similar architecture to the PIF network but can distinguish the difference between local details. The difference between PDF and PIF is that the network of training PDF does not apply the adversarial loss. Finally, by combining PIF and PDF, PRF has the advantages of the two features and can alleviate the influence of the pose barrier problem. Experiments are conducted on the VeRi-776 and VehicleID data sets. We show that PIF and PDF are complementary and that PRF produces competitive performance compared with state-of-the-art approaches.

We consider the task of driver gaze prediction: estimating where the location of the focus of a driver should be, based on a raw video of the outside environment. In practice, we output a probability map that gives the normalized probability of each point in a given scene being the object of the driver attention. Most existing methods (i.e.,Coarse-to-FineandMulti-branch) take an image or a video as input and directly output the fixation map. While successful, these methods can often produce highly scattered predictions, rendering them unreliable for real-world usage. Motivated by this observation, we propose the reinforced attention (RA) model as a regulatory mechanism to increase prediction density. Our method is built directly on top of existing methods, making it complementary to current approaches. Specifically, we first useMulti-branchto obtain an initial fixation map. Then, RA is trained using deep reinforcement learning to learn a location prediction policy, producing a reinforced attention. Finally, in order to obtain the final gaze prediction result, we combine the fixation map and the reinforced attention by a mask-guided multiplication. Experimental results show that our framework improves the accuracy of gaze prediction, and provides state-of-the-art performance on the DR(eye)VE dataset.

In this paper, we focus on the problem of novel view synthesis for vehicles. Some previous works solve the problem of novel view synthesis in a controlled 3D environment by exploiting additional 3D details (i.e., camera viewpoints and underlying 3D models). However, in real scenarios, the 3D details are difficult to obtain. In this case, we find that introducing vehicle pose to represent the views of vehicles is an alternative paradigm to solve the lack of 3D details. In novel view synthesis, preserving local details is one of the most challenging problems. To address this problem, we propose a perspective-aware generative model (PAGM). We are motivated by the prior that vehicles are made of quadrilateral planes. Preserving these rigid planes during image generation ensures that image details are kept. To this end, a classic image transformation method is leveraged,i.e., perspective transformation. In our GAN-based system, the perspective transformation is applied to the encoder feature maps, and the resulting maps are regarded as new conditions for the decoder. This strategy preserves the quadrilateral planes all the way through the network, thus shuttling the texture details from the input image to the generated image. In the experiments, we show that PAGM can generate high-quality vehicle images with fine details. Quantitatively, our method is superior to several competing approaches employing either GAN or the perspective transformation. Code is available at:https://github.com/ilvkai/view-synthesis-for-vehicles

TuX2is a new distributed graph engine that bridges graph computation and distributed machine learning.TuX2inherits the benefits of elegant graph computation model, efficient graph layout, and balanced parallelism to scale to billion-edge graphs, while extended and optimized for distributed machine learning to support heterogeneity in data model, Stale Synchronous Parallel in scheduling, and a new Mini-batch, Exchange, GlobalSync, and Apply (MEGA) model for programming.TuX2further introduces a hybrid vertex-cut graph optimization and supports various consistency models in fault tolerance for machine learning. We have developed a set of representative distributed machine learning algorithms inTuX2, covering both supervised and unsupervised learning. Compared to the implementations on distributed machine learning platforms, writing those algorithms inTuX2takes only about 25 percent of the code: our graph computation model hides the detailed management of data layout, partitioning, and parallelism from developers. The extensive evaluation ofTuX2, using large datasets with up to 64 billion of edges, shows thatTuX2outperforms PowerGraph/PowerLyra, the state-of-the-art distributed graph engines, by an order of magnitude, while beating two state-of-the-art distributed machine learning systems by at least 60 percent.

Dynamic ridesharing refers to services that arrange one-time shared rides on short notice. It underpins various real-world intelligent transportation applications such as car-pooling, food delivery and last-mile logistics. A core operation in dynamic ridesharing is the "insertion operator". Given a worker and a feasible route which contains a sequence of origin-destination pairs from previous requests, the insertion operator inserts a new origin-destination pair from a newly arrived request into the current route such that certain objective is optimized. Common optimization objectives include minimizing the maximum flow time of all requests and minimizing the total travel time of the worker. Despite its frequent usage, the insertion operator has a time complexity of O(n^3), where n is the number of all requests assigned to the worker. The cubic running time of insertion fundamentally limits the efficiency of urban-scale dynamic ridesharing based applications. In this paper, we propose a novel partition framework and a dynamic programming based insertion with a time complexity of O(n^2). We further improve the time efficiency of the insertion operator to O(n) harnessing efficient index structures, such as fenwick tree. Evaluations on two real-world large-scale datasets show that our methods can accelerate insertion by 1.5 to 998.1 times.

JointCloud computing is a new generation cloud computing model based on collaboration among Cloud Service Providers, making resources from multiple clouds deeply integrated., and supporting customize cloud service. To achieve the data confirmation Right when doing data trading to prevent resell is one of the most important challenges faced by such JointCloud environment. In this paper, we propose the JointCloud Computing Data Trading Architecture (JCDTA), an optimized data trading architecture for cross-stakeholder. Firstly, the announced mechanism is used to extract the data resources summary and the owner information into blockchain. Secondly, the untampering of the blockchain is used to record the data resources information, such as data resources statement information, data resources transaction records and data resources operation records. Finally, the supervision mechanism confirms the declaration of the data sources while the encryption technology ensures the privacy of the data resources. JCDTA guarantees the security and the reliability of data trading in the JointCloud environment and ensures the value invariance of data resources.

The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence (AI), bringing a new wave of AI research and promoting it into the new era of AI 2.0. As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities. Specifically, crowd intelligence provides a novel problem-solving paradigm through gathering the intelligence of crowds to address challenges. In particular, due to the rapid development of the sharing economy, crowd intelligence not only becomes a new approach to solving scientific challenges, but has also been integrated into all kinds of application scenarios in daily life, e.g., online-to-offline (O2O) application, real-time traffic monitoring, and logistics management. In this paper, we survey existing studies of crowd intelligence. First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation. Then, we introduce four categories of representative crowd intelligence platforms. We summarize three core research problems and the state-of-the-art techniques of crowd intelligence. Finally, we discuss promising future research directions of crowd intelligence.

In this paper, we address the problem of heavy occlusion where the negative samples contaminate the translation model. In this setting, we decompose the task of tracking into translation and scale estimations of objects. We use hierarchical convolutional features to estimate target position and update translation model, and we use HOG features for the scale filter. In addition, we evaluate the translation's reliability according to the correlation responses map which is the result of correlation detection. Then we propose a new method to update model according to the reliability. Experiments are performed on 28 benchmark sequences with significant scale variations, it shows that the proposed algorithm performs favorably against state-of-the-art methods in terms of accuracy and robustness.

Sina-Microblog, the earliest and biggest microblogging service in China, has become one of the most popular media in information propagation. In order to gain insights into the topological and information diffusing characteristics of microblogging network in China, we crawled Sina-Microblog for about 3 months and obtain the trace of its topology and topics. Compared with other online social networks, our measurement study shows a number of interesting findings. Our data suggests that Sina-Microblog network has apparent small-world effect and scale-free characteristic, specially, the outdegree distribution appears to have multiple separate power-law regimes with different exponents. We also observe the overlay graph of Sina-Microblog represents assortative mixing pattern and weak correlation of indegree and outdegree. Moreover, by constructing the cascades of different topics, our data suggests that the distribution of cascades size follows a power-law and heavy-tailed property with the slope approximately -2, and the common motifs of cascades with different topics are very similar, above 93% of them are isolated nodes. In order to find the formative motivity of hot cascades, we find that they always evolve to the structures like `star pattern' and `two-polar pattern', which are mainly due to the indegree of participating nodes, and are also correlated with the content of tweet.

Summary form only given. In software testing, when testing samples contradict the specification of a software system, the best way to locate the error-making commands is logical reasoning; therefore a formal logical reasoning system might be developed for making revision of software systems. In this paper, a formal system, called R-calculus, is introduced in first order languages. It is used to spot those error-making commands which cause the contradiction to the testing example. Therefore, R-calculus helps a great deal to revise the software system. The basic form of R-calculus is a pair in which the first part is a consistent set of formulas specifying the results of the testing samples, while the second part is a specification that contradicts the first part. R-calculus consists of a set of R-rules and each R-rule is designed for one logical connective symbol or one quantifier symbol occurring in the specification. Some examples are given to demonstrate how to use the R-calculus. It is proved that R-calculus is sound and complete. A testing theorem is further proved. The theorem says that R-calculus can deduce formally all possible revisions for a specification that contradicts testing samples. It further says that some software tools can be designed and implemented on computers to revise software systems interactively with the testing engineers.

First-order languages have been introduced to describe beliefs formally and the concept of revision is defined for model as well as proof. A logical inference system named R-calculus is defined to derive all maximal contractions of a base of belief set for its given refutations. The R-calculus consists of the structural rules, an axiom, a cut rule and the rules for logical connectives and quantifiers. Some examples are given to demonstrate how to use the R-calculus. Furthermore, the properties reachability, soundness and completeness of the R-calculus are formally defined and proved.

A first order inference system, named R-calculus, is defined to develop the specifications. This system intends to eliminate the laws which is not consistent with user’s requirements. The R-calculus consists of the structural rules, an axiom, a cut rule, and the rules for logical connectives. Some examples are given to demonstrate the usage of the R-calculus. Furthermore, the properties regarding reachability and completeness of the R-calculus are formally defined and proved.

In this paper we propose a new type of random CSP model, called Model RB, which is a revision to the standard Model B. It is proved that phase transitions from a region where almost all problems are satisfiable to a region where almost all problems are unsatisfiable do exist for Model RB as the number of variables approaches infinity. Moreover, the critical values at which the phase transitions occur are also known exactly. By relating the hardness of Model RB to Model B, it is shown that there exist a lot of hard instances in Model RB.

In Reiter's default logic, the operator in the fixed-point definition of extension is not appropriate to compute extensions by its iterated applications. This paper presents a class of alternative operators, called compatible ones, such that, at least for normal default theories and so-called well-founded, ordered default theories, we can get extensions by iterated applications of them. In addition, we completely answer Etherington's conjectures about both his procedure for generating extensions and a modified version of it. In particular, we give an example of a finite, ordered default theory, for which the original procedure fails to converge, and show that the computation of the modified one is essentially the iteration of a compatible operator and converges for finite, ordered theories.

The concepts of maintenance sequence of a knowledge base and their limits are introduced. Some concepts used in maintenance of knowledge bases, such as new laws, user's rejections, and reconstructions of a base are defined; the related theorems are proposed. Some computational aspects of reconstructions are studied; an R-calculus is given to deduce a reconstruction when a base meets a rejection. Especially, an R-calculus for logic programming is provided and implemented to do it. Finally, the theory is compared with AGM's theory of belief revision.>

The main functions of an interactive consistency maintenance system called Specreviser is introduced; some techniques used in its implementation are discussed. A logical framework of the system is given. Some concepts, such as new law, user's rejection, and reconstruction of a knowledge base are defined; the related theorems are proved. The concepts of a developing process of a knowledge base and the limit of a developing process are further established. A procedure is built to generate processes from a given user's model and a knowledge base. It is proved that all processes generated by the procedure and starting with the knowledge base are convergent, their limit is the truth of the model. The work is compared with AGM's theory of belief revision.

A formal description is presented of the process learning from experience. First-order logic is used as a language to denote knowledge. The theory consists of a first-order logic in Gentzen style, two concepts of counterexample and refutation by facts, and a hypothesis calculus for modifying a theory to match the human's observation and experiments. A comparison with nonmonotonic logic is also made.>