Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason over detailed multimodal information from long inputs. As such, we formulate a novel video question-answering task termed referring reasoning. Specifically, as part of the question, it contains a referring query that references related video contexts, called referred context. The model is then required to reason over relevant video details from the referred context. Following the paradigm of referring reasoning, we curate 6,678 human-annotated multiple-choice questions in 17 fine-grained categories, establishing one of the most comprehensive benchmarks for long-form video understanding. Evaluations suggest that the LongVideoBench presents significant challenges even for the most advanced proprietary models (e.g. GPT-4o, Gemini-1.5-Pro, GPT-4-Turbo), while their open-source counterparts show an even larger performance gap. In addition, our results indicate that model performance on the benchmark improves only when they are capable of processing more frames, positioning LongVideoBench as a valuable benchmark for evaluating future-generation long-context LMMs.

Language agents, built on top of language models (LMs), are systems that can interact with complex environments, such as the open web. In this work, we examine whether such agents can perform realistic and time-consuming tasks on the web, e.g., monitoring real-estate markets or locating relevant nearby businesses. We introduce AssistantBench, a challenging new benchmark consisting of 214 realistic tasks that can be automatically evaluated, covering different scenarios and domains. We find that AssistantBench exposes the limitations of current systems, including language models and retrieval-augmented language models, as no model reaches an accuracy of more than 25 points. While closed-book LMs perform well, they exhibit low precision since they tend to hallucinate facts. State-of-the-art web agents reach a score of near zero. Additionally, we introduce SeePlanAct (SPA), a new web agent that significantly outperforms previous agents, and an ensemble of SPA and closed-book models reaches the best overall performance. Moreover, we analyze failures of current systems and highlight that web navigation remains a major challenge.

This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers' Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated.

Artificial Intelligence (AI) models have reached a very significant level of accuracy. While their superior performance offers considerable benefits, their inherent complexity often decreases human trust, which slows their application in high-risk decision-making domains, such as finance. The field of eXplainable AI (XAI) seeks to bridge this gap, aiming to make AI models more understandable. This survey, focusing on published work from the past five years, categorizes XAI approaches that predict financial time series. In this paper, explainability and interpretability are distinguished, emphasizing the need to treat these concepts separately as they are not applied the same way in practice. Through clear definitions, a rigorous taxonomy of XAI approaches, a complementary characterization, and examples of XAI's application in the finance industry, this paper provides a comprehensive view of XAI's current role in finance. It can also serve as a guide for selecting the most appropriate XAI approach for future applications.

This paper discusses how to generate general graph node embeddings from knowledge graph representations. The embedded space is composed of a number of sub-features to mimic both local affinity and remote structural relevance. These sub-feature dimensions are defined by several indicators that we speculate to catch nodal similarities, such as hop-based topological patterns, the number of overlapping labels, the transitional probabilities (markov-chain probabilities), and the cluster indices computed by our recursive spectral bisection (RSB) algorithm. These measures are flattened over the one dimensional vector space into their respective sub-component ranges such that the entire set of vector similarity functions could be used for finding similar nodes. The error is defined by the sum of pairwise square differences across a randomly selected sample of graph nodes between the assumed embeddings and the ground truth estimates as our novel loss function. The ground truth is estimated to be a combination of pairwise Jaccard similarity and the number of overlapping labels. Finally, we demonstrate a multi-variate stochastic gradient descent (SGD) algorithm to compute the weighing factors among sub-vector spaces to minimize the average error using a random sampling logic.

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical for cutting-edge commercial LLMs. Moreover, prevailing prompting methods depend on external tool feedback and fail to simultaneously lessen toxicity and bias. Motivated by social psychology principles, we propose a novel strategy named \textbf{perspective-taking prompting (\textsc{PeT})} that inspires LLMs to integrate diverse human perspectives and self-regulate their responses. This self-correction mechanism can significantly diminish toxicity (up to $89\%$) and bias (up to $73\%$) in LLMs' responses. Rigorous evaluations and ablation studies are conducted on two commercial LLMs (ChatGPT and GLM) and three open-source LLMs, revealing \textsc{PeT}'s superiority in producing less harmful responses, outperforming five strong baselines.

Uncertainty expressions such as ``probably'' or ``highly unlikely'' are pervasive in human language. While prior work has established that there is population-level agreement in terms of how humans interpret these expressions, there has been little inquiry into the abilities of language models to interpret such expressions. In this paper, we investigate how language models map linguistic expressions of uncertainty to numerical responses. Our approach assesses whether language models can employ theory of mind in this setting: understanding the uncertainty of another agent about a particular statement, independently of the model's own certainty about that statement. We evaluate both humans and 10 popular language models on a task created to assess these abilities. Unexpectedly, we find that 8 out of 10 models are able to map uncertainty expressions to probabilistic responses in a human-like manner. However, we observe systematically different behavior depending on whether a statement is actually true or false. This sensitivity indicates that language models are substantially more susceptible to bias based on their prior knowledge (as compared to humans). These findings raise important questions and have broad implications for human-AI alignment and AI-AI communication.

We observe that the performance of SOTA visual trackers surprisingly strongly varies across different video attributes and datasets. No single tracker remains the best performer across all tracking attributes and datasets. To bridge this gap, for a given video sequence, we predict the "Best of the N Trackers", called the BofN meta-tracker. At its core, a Tracking Performance Prediction Network (TP2N) selects a predicted best performing visual tracker for the given video sequence using only a few initial frames. We also introduce a frame-level BofN meta-tracker which keeps predicting best performer after regular temporal intervals. The TP2N is based on self-supervised learning architectures MocoV2, SwAv, BT, and DINO; experiments show that the DINO with ViT-S as a backbone performs the best. The video-level BofN meta-tracker outperforms, by a large margin, existing SOTA trackers on nine standard benchmarks - LaSOT, TrackingNet, GOT-10K, VOT2019, VOT2021, VOT2022, UAV123, OTB100, and WebUAV-3M. Further improvement is achieved by the frame-level BofN meta-tracker effectively handling variations in the tracking scenarios within long sequences. For instance, on GOT-10k, BofN meta-tracker average overlap is 88.7% and 91.1% with video and frame-level settings respectively. The best performing tracker, RTS, achieves 85.20% AO. On VOT2022, BofN expected average overlap is 67.88% and 70.98% with video and frame level settings, compared to the best performing ARTrack, 64.12%. This work also presents an extensive evaluation of competitive tracking methods on all commonly used benchmarks, following their protocols. The code, the trained models, and the results will soon be made publicly available on https://github.com/BasitAlawode/Best_of_N_Trackers.

Modelling and characterizing emergent behaviour within a swarm can pose significant challenges in terms of assurance. Assurance tasks encompass adherence to standards, certification processes, and the execution of verification and validation (V&V) methods, such as model checking. In this study, we propose a holistic, multi-level modelling approach for formally verifying and validating autonomous robotic swarms, which are defined at the macroscopic formal modelling, low-fidelity simulation, high-fidelity simulation, and real-robot levels. Our formal macroscopic models, used for verification, are characterized by data derived from actual simulations, ensuring both accuracy and traceability across different system models. Furthermore, our work combines formal verification with experimental validation involving real robots. In this way, our corroborative approach for V&V seeks to enhance confidence in the evidence, in contrast to employing these methods separately. We explore our approach through a case study focused on a swarm of robots operating within a public cloakroom. Swarm robotics offers a method for coordinating a large number of robots, inspired by swarm behaviours in nature [1]. The collective behaviours of a swarm are not directly engineered into the system. Rather, they arise due to interactions among individual robots and their environment, called emergent behaviour [2].

The introduction of 6G technology into the Internet of Vehicles (IoV) promises to revolutionize connectivity with ultra-high data rates and seamless network coverage. However, this technological leap also brings significant challenges, particularly for the dynamic and diverse IoV landscape, which must meet the rigorous reliability and security requirements of 6G networks. Furthermore, integrating 6G will likely increase the IoV's susceptibility to a spectrum of emerging cyber threats. Therefore, it is crucial for security mechanisms to dynamically adapt and learn new attack patterns, keeping pace with the rapid evolution and diversification of these threats - a capability currently lacking in existing systems. This paper presents a novel intrusion detection system leveraging the paradigm of life-long (or continual) learning. Our methodology combines class-incremental learning with federated learning, an approach ideally suited to the distributed nature of the IoV. This strategy effectively harnesses the collective intelligence of Connected and Automated Vehicles (CAVs) and edge computing capabilities to train the detection system. To the best of our knowledge, this study is the first to synergize class-incremental learning with federated learning specifically for cyber attack detection. Through comprehensive experiments on a recent network traffic dataset, our system has exhibited a robust adaptability in learning new cyber attack patterns, while effectively retaining knowledge of previously encountered ones. Additionally, it has proven to maintain high accuracy and a low false positive rate.