Jian Liu

Wentong Li, Yuqian Yuan, Jian Liu et al.

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation. However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly. Some recent works have introduced resampler or abstractor to reduce the number of resulting visual tokens. Unfortunately, they fail to capture finer details and undermine the visual reasoning capabilities of MLLMs. In this work, we propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. In specific, we first interpolate the visual features as a low-resolution point query, providing the overall visual representation as the foundation. Then, we introduce a region-to-point injection module that utilizes high-resolution, multi-level region-based cues as fine-grained reference keys and values, allowing them to be fully absorbed within the corresponding local context region. This step effectively updates the coarse point query, transforming it into an enriched one for the subsequent LLM reasoning. Extensive experiments demonstrate that our approach compresses the visual tokens by 75%~89%, while achieves comparable or even better performance across diverse benchmarks with significantly higher efficiency. The source codes can be found at https://github.com/CircleRadon/TokenPacker.

Yong Dai, Jian Liu, Jian Zhang et al.

Sentiment analysis (SA) is an important research area in cognitive computation-thus in-depth studies of patterns of sentiment analysis are necessary. At present, rich resource data-based SA has been well developed, while the more challenging and practical multi-source unsupervised SA (i.e. a target domain SA by transferring from multiple source domains) is seldom studied. The challenges behind this problem mainly locate in the lack of supervision information, the semantic gaps among domains (i.e., domain shifts), and the loss of knowledge. However, existing methods either lack the distinguishable capacity of the semantic gaps among domains or lose private knowledge. To alleviate these problems, we propose a two-stage domain adaptation framework. In the first stage, a multi-task methodology-based shared-private architecture is employed to explicitly model the domain common features and the domain-specific features for the labeled source domains. In the second stage, two elaborate mechanisms are embedded in the shared private architecture to transfer knowledge from multiple source domains. The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain. And the second mechanism is a target-oriented ensemble (TOE) method, in which knowledge is transferred through a well-designed ensemble method. Extensive experiment evaluations verify that the performance of the proposed framework outperforms unsupervised state-of-the-art competitors. What can be concluded from the experiments is that transferring from very different distributed source domains may degrade the target-domain performance, and it is crucial to choose the proper source domains to transfer from.

Yujin Kwon, Jian Liu, Minjeong Kim et al.

Bitcoin uses blockchain technology and proof-of-work (PoW) mechanism where nodes spend computing resources and earn rewards in return for spending these resources. This incentive system has caused power to be significantly biased towards a few nodes, called mining pools. In fact, poor decentralization appears not only in PoW-based coins but also in coins adopting other mechanisms such as proof-of-stake (PoS) and delegated proof-of-stake (DPoS). In this paper, we target this centralization issue. To this end, we first define (m, \varepsilon, δ)-decentralization as a state that satisfies 1) there are at least m participants running a node and 2) the ratio between the total resource power of nodes run by the richest and δ-th percentile participants is less than or equal to 1+\varepsilon. To see if it is possible to achieve good decentralization, we introduce sufficient conditions for the incentive system of a blockchain to reach (m, \varepsilon, δ)-decentralization. When satisfying the conditions, a blockchain system can reach full decentralization with probability 1. However, to achieve this, the blockchain system should be able to assign a positive Sybil cost, where the Sybil cost is defined as the difference between the cost for one participant running multiple nodes and the total cost for multiple participants each running one node. On the other hand, we prove that when there is no Sybil cost, the probability of reaching (m, \varepsilon, δ)-decentralization is upper bounded by a value close to 0, considering a large rich-poor gap. To determine the conditions that each system cannot satisfy, we also analyze protocols of all PoW, PoS, and DPoS coins in the top 100 coins according to our conditions. Finally, we conduct data analysis of these coins to validate our theory.

Yunzhe Tao, Lin Ma, Weizhong Zhang et al.

Time series prediction has been studied in a variety of domains. However, it is still challenging to predict future series given historical observations and past exogenous data. Existing methods either fail to consider the interactions among different components of exogenous variables which may affect the prediction accuracy, or cannot model the correlations between exogenous data and target data. Besides, the inherent temporal dynamics of exogenous data are also related to the target series prediction, and thus should be considered as well. To address these issues, we propose an end-to-end deep learning model, i.e., Hierarchical attention-based Recurrent Highway Network (HRHN), which incorporates spatio-temporal feature extraction of exogenous variables and temporal dynamics modeling of target variables into a single framework. Moreover, by introducing the hierarchical attention mechanism, HRHN can adaptively select the relevant exogenous features in different semantic levels. We carry out comprehensive empirical evaluations with various methods over several datasets, and show that HRHN outperforms the state of the arts in time series prediction, especially in capturing sudden changes and sudden oscillations of time series.

Jian Liu, Wenting Li, Ghassan O. Karame et al.

Motivated by the great success and adoption of Bitcoin, a number of cryptocurrencies such as Litecoin, Dogecoin, and Ethereum are becoming increasingly popular. Although existing blockchain-based cryptocurrency schemes can ensure reasonable security for transactions, they do not consider any notion of fairness. Fair exchange allows two players to exchange digital "items", such as digital signatures, over insecure networks fairly, so that either each player gets the other's item, or neither player does. Given that blockchain participants typically do not trust each other, enabling fairness in existing cryptocurrencies is an essential but insufficiently explored problem. In this paper, we explore the solution space for enabling the fair exchange of a cryptocurrency payment for a receipt. We identify the timeliness of an exchange as an important property especially when one of the parties involved in the exchange is resource-constrained. We introduce the notion of strong timeliness for a fair exchange protocol and propose two fair payment-for-receipt protocol instantiations that leverage functionality of the blockchain to achieve strong timeliness. We implement both and compare their security and efficiency.