Recent advancements in in-context segmentation generalists have demonstrated significant success in performing various image segmentation tasks using a limited number of labeled example images. However, real-world applications present challenges due to the variability of support examples, which often exhibit quality issues resulting from various sources and inaccurate labeling. How to extract more robust representations from these examples has always been one of the goals of in-context visual learning. In response, we propose UNICL-SAM, to better model the example distribution and extract robust representations to help in-context segmentation. We incorporate an uncertainty probabilistic module to quantify each example’s reliability during both the training and testing phases. Utilizing this uncertainty estimation, we introduce an uncertainty-guided graph augmentation and feature refinement strategy, aimed at mitigating the impact of high-uncertainty regions to enhance the learning of robust representations. Subsequently, we construct prototypes for each example by aggregating part information, thereby creating reliable in-context instruction that effectively represents fine-grained local semantics. This approach serves as a valuable complement to traditional global pooling features. Experimental results demonstrate the effectiveness of the proposed framework, underscoring its potential for real-world applications.

We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by large language models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on two human-annotated datasets, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulation, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset.

Eliciting reliable human feedback is essential for many machine learning tasks, such as learning from noisy labels and aligning AI systems with human preferences. Peer prediction mechanisms incentivize truthful reporting without ground truth verification by scoring agents based on correlations with peers. Traditional mechanisms, which ensure that truth-telling maximizes the \textbf{expected scores} in equilibrium, can elicit honest information while assuming agents' utilities are \textbf{linear functions} of their scores. However, in practice, non-linear payment rules are usually preferred, or agents' utilities are inherently non-linear. We propose \emph{stochastically dominant truthfulness (SD-truthfulness)} as a stronger guarantee: the score distribution of truth-telling stochastically dominates all other strategies, incentivizing truthful reporting for a wide range of monotone utility functions. Our first observation is that no existing peer prediction mechanism naturally satisfies this criterion without strong assumptions. A simple solution - rounding scores into binary lotteries — can enforce SD-truthfulness, but often degrades \emph{sensitivity}, a key property related to fairness and statistical efficiency. We demonstrate how a more careful application of rounding can better preserve sensitivity. Furthermore, we introduce a new enforced agreement (EA) mechanism that is theoretically guaranteed to be SD-truthful in binary-signal settings and, under mild assumptions, empirically achieves the highest sensitivity among all known SD-truthful mechanisms.

Existing Ciphertext Policy Attribute-Based Encryption (CP-ABE) schemes based on the Ring Learning with Errors (R-LWE) problem have issues such as key escrow, insufficient real-time performance for attribute revocation, high computational cost and high storage overhead, making them unsuitable for use in distributed edge computing scenarios characterised by frequent changes in user attributes and limited terminal computing and storage resources. To address the above issues, we propose a multi-authority CP-ABE scheme with fully outsourced computation and attribute direct revocation based on the R-LWE problem. In our scheme, the use of a multi-authority management mechanism effectively avoids the key escrow problem, the use of a direct attribute revocation mechanism allows flexible revocation of user attributes, and the use of fully outsourced computation significantly reduces user computing costs and storage overhead. Security and experimental analysis have shown that our scheme satisfies indistinguishability under chosen plaintext attacks in the standard model and can significantly reduce the computational cost and storage overhead for users.

In the context of rapid advancements in intelligent transportation technology, secure and efficient cross-domain data sharing imposes higher demands on the reliability and real-time responsiveness of transportation systems. However, the current architectures have limitations such as a lack of data traceability, coarse-grained access control, and high computational complexity, making them inadequate to meet the highly dynamic requirements of vehicular networks. In this paper, we propose Decentralized Secure Vehicular Data Collaboration Paradigm (DSVDCP) – a Vehicular Fog-Cloud cross-domain data sharing paradigm to address above challenges. The DSVDCP combines blockchain with Vehicular-Fog-Cloud Cooperative Computing to ensure the confidentiality and non-deniability in cross-domain data sharing. Furthermore, to enhance the granularity of data access control, we designed an attribute-based encryption scheme, VFC-CPABE, specifically for DSVDCP. This scheme supports multiple authorization authorities, access policy hiding, attribute revocation, and outsourced encryption and decryption, achieving fine-grained access control for cross-domain data. Based on the q-parallel BDHE assumption and detailed parameter selection analysis, we rigorously prove the IND-CPA security of the VFC-CPABE scheme in the standard model. We realized the prototype of DSVDCP, the experimental results show that, while maintaining comparable user-side decryption overhead to the current optimal schemes, VFC-CPABE reduces encryption computation overhead by more than 50% for the same number of attributes, significantly reducing the computational burden on the user side.

The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, whicd limits their potential usage scenarios. To address this issue, we present a new ICLframeworkfor visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental re-sults demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models (LLMs). This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media.

Because high-quality data is like oxygen for AI systems, effectively eliciting information from crowdsourcing workers has become a first-order problem for developing high-performance machine learning algorithms. Two prevalent paradigms, spot-checking and peer prediction, enable the design of mechanisms to evaluate and incentivize high-quality data from human labelers. So far, at least three metrics have been proposed to compare the performances of these techniques \citepzhang2022high,gao2016incentivizing,burrell2021measurement. However, different metrics lead to divergent and even contradictory results in various contexts. In this paper, we harmonize these divergent stories, showing that two of these metrics are actually the same within certain contexts and explain the divergence of the third. Moreover, we unify these different contexts by introducingSpot Check Equivalence, which offers an interpretable metric for the effectiveness of a peer prediction mechanism. Finally, we present two approaches to compute spot check equivalence in various contexts, where simulation results verify the effectiveness of our proposed metric.

Multi-round competitions often double or triple the points awarded in the final round, calling it a bonus, to maximize spectators’ excitement. In a two-player competition with n rounds, we aim to derive the optimal bonus size to maximize the audience’s overall expected surprise (as defined in [7]). We model the audience’s prior belief over the two players’ ability levels as a beta distribution. Using a novel analysis that clarifies and simplifies the computation, we find that the optimal bonus depends greatly upon the prior belief and obtain solutions of various forms for both the case of a finite number of rounds and the asymptotic case. In an interesting special case, we show that the optimal bonus approximately and asymptotically equals to the “expected lead”, the number of points the weaker player will need to come back in expectation. Moreover, we observe that priors with a higher skewness lead to a higher optimal bonus size, and in the symmetric case, priors with a higher uncertainty also lead to a higher optimal bonus size. This matches our intuition since a highly asymmetric prior leads to a high “expected lead”, and a highly uncertain symmetric prior often leads to a lopsided game, which again benefits from a larger bonus.

Copy-move forgery detection identifies a tampered image by detecting pasted and source regions in the same image. In this paper, we propose a novel two-stage framework specially for copy-move forgery detection. The first stage is a backbone self deep matching network, and the second stage is named as Proposal SuperGlue. In the first stage, atrous convolution and skip matching are incorporated to enrich spatial information and leverage hierarchical features. Spatial attention is built on self-correlation to reinforce the ability to find appearance similar regions. In the second stage, Proposal SuperGlue is proposed to remove false-alarmed regions and remedy incomplete regions. Specifically, a proposal selection strategy is designed to enclose highly suspected regions based on proposal generation and backbone score maps. Then, pairwise matching is conducted among candidate proposals by deep learning based keypoint extraction and matching, i.e., SuperPoint and SuperGlue. Integrated score map generation and refinement methods are designed to integrate results of both stages and obtain optimized results. Our two-stage framework unifies end-to-end deep matching and keypoint matching by obtaining highly suspected proposals, and opens a new gate for deep learning research in copy-move forgery detection. Experiments on publicly available datasets demonstrate the effectiveness of our two-stage framework.

Information flow measures, over the duration of a game, the audience’s belief of who will win, and thus can reflect the amount of surprise in a game. To quantify the relationship between information flow and audiences' perceived quality, we conduct a case study where subjects watch one of the world’s biggest esports events, LOL S10. In addition to eliciting information flow, we also ask subjects to report their rating for each game. We find that the amount of surprise in the end of the game plays a dominant role in predicting the rating. This suggests the importance of incorporating when the surprise occurs, in addition to the amount of surprise, in perceived quality models. For content providers, it implies that everything else being equal, it is better for twists to be more likely to happen toward the end of a show rather than uniformly throughout.

With the continuous exploration of marine resources, underwater artificial intelligent robots play an increasingly important role in the fish industry. However, the detection of underwater objects is a very challenging problem due to the irregular movement of underwater objects, the occlusion of sand and rocks, the diversity of water illumination, and the poor visibility and low color contrast in the underwater environment. In this article, we first propose a real-world underwater object detection dataset (UODD), which covers more than 3K images of the most common aquatic products. Then we propose Channel Sharpening Attention Module (CSAM) as a plug-and-play module to further fuse high-level image information, providing the network with the privilege of selecting feature maps. Fusion of original images through CSAM can improve the accuracy of detecting small and medium objects, thereby improving the overall detection accuracy. We also use Water-Net as a preprocessing method to remove the haze and color cast in complex underwater scenes, which shows a satisfactory detection result on small-sized objects. In addition, we use the class weighted loss as the training loss, which can accurately describe the relationship between classification and precision of bounding boxes of targets, and the loss function converges faster during the training process. Experimental results show that the proposed method reaches a maximum AP of 50.1%, outperforming other traditional and state-of-the-art detectors. In addition, our model only needs an average inference time of 25.4 ms per image, which is quite fast and might suit the real-time scenario.

In this paper, the game theoretical analysis method is presented to provide optimal strategies for anomaly-based intrusion detection systems (A-IDS). A two-stage game model is established to represent the interactions between the attackers and defenders. In the first stage, the players decide to do actions or keep silence, and in the second stage, attack intensity and detection threshold are considered as two important strategic variables for the attackers and defenders, respectively. The existence, uniqueness, and explicit computation of the Nash equilibrium are analyzed and obtained by considering six different scenarios, from which the optimal detection and attack actions are provided. Numerical examples are provided to validate our theoretical results.

A wireless neural signal acquisition system is presented for freely-running test. It consists of low-noise, high input impedance analog processing, radio frequency (RF) transmitter and receiver. Firstly, the weak neural signal is amplified by a variable gain pre-amplifier and then digitalized by a Sigma-delta ADC. Secondly, the digital data is transmitted and received with couple of RF circuits based on IEEE STD802.15 standard and on-off keying (OOK) modulation. Fabricated in SMIC 0.18μm CMOS process, the IC prototype occupies 2.88mm2 and consumes 40mW. It works functionally, which can be a wide solution for wireless neural signal processor.

Effective testing can develop quality software with higher productivity at a lower cost. Redundancy in the test suite increases the execution cost and consumes scarce project resources. Due to time and resource constraints in testing, test suite reduction techniques are required to remove those redundant test cases from the test suite. Since Weighted Set Covering Techniques can be used to resolve the test suite minimization, the paper presents a novel approach, called as Modified Greedy Algorithm, based on the Weighted Set Covering Problem (WSC). The WSC is, given S, for each set s ∈S a weight ws>;0 is also specified, and the goal is to find a set cover C of minimum total weight Σs∈Cws. The research aimed to reduction of the test suite which generated by Student Achievement Retrieval Navigation Model. Through comparing with existing algorithms, our algorithm can not only produce the minimum test suite is the smallest, but also minimum the total cost.