Knowledge-based visual question answering (VQA) requires world knowledge beyond the image for accurate answer. Recently, instead of extra knowledge bases, a large language model (LLM) like GPT-3 is activated as an implicit knowledge engine to jointly acquire and reason the necessary knowledge for answering by converting images into textual information (e.g., captions and answer candidates). However, such conversion may introduce irrelevant information, which causes the LLM to misinterpret images and ignore visual details crucial for accurate knowledge. We argue that multimodal large language model (MLLM) is a better implicit knowledge engine than the LLM for its superior capability of visual understanding. Despite this, how to activate the capacity of MLLM as the implicit knowledge engine has not been explored yet. Therefore, we propose GeReA, a generate-reason framework that prompts a MLLM like InstructBLIP with question relevant vision and language information to generate knowledge-relevant descriptions and reasons those descriptions for knowledge-based VQA. Specifically, the question-relevant image regions and question-specific manual prompts are encoded in the MLLM to generate the knowledge relevant descriptions, referred to as question-aware prompt captions. After that, the question-aware prompt captions, image-question pair, and similar samples are sent into the multi-modal reasoning model to learn a joint knowledge-image-question representation for answer prediction. GeReA unlocks the use of MLLM as the implicit knowledge engine, surpassing all previous state-of-the-art methods on OK-VQA and A-OKVQA datasets, with test accuracies of 66.5% and 63.3% respectively. Our code will be released at https://github.com/Upper9527/GeReA.

The Perceiver makes few architectural assumptions about the relationship among its inputs with quadratic scalability on its memory and computation time. Indeed, the Perceiver model outpaces or is competitive with ResNet-50 and ViT in terms of accuracy to some degree. However, the Perceiver does not take predictive uncertainty and calibration into account. The Perceiver also generalizes its performance on three datasets, three models, one evaluation metric, and one hyper-parameter setting. Worst of all, the Perceiver's relative performance improvement against other models is marginal. Furthermore, its reduction of architectural prior is not substantial; is not equivalent to its quality. Thereby, I invented five mutations of the Perceiver, the Uncertainty-Aware Perceivers, that obtain uncertainty estimates and measured their performance on three metrics. Experimented with CIFAR-10 and CIFAR-100, the Uncertainty-Aware Perceivers make considerable performance enhancement compared to the Perceiver.

Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To overcome these limitations, we integrate uncertainty calibration and interpretability into a retrieval pipeline. Specifically, we introduce Bayesian methodologies and multi-perspective retrieval to calibrate uncertainty within a retrieval pipeline. We incorporate techniques such as LIME and SHAP to analyze the behavior of a black-box reranker model. The importance scores derived from these explanation methodologies serve as supplementary relevance scores to enhance the base reranker model. We evaluate the resulting performance enhancements achieved through uncertainty calibration and interpretable reranking on Question Answering and Fact Checking tasks. Our methods demonstrate substantial performance improvements across three KILT datasets.

Agent-based models (ABMs) stand as an essential paradigm for proposing and validating hypothetical solutions or policies aimed at addressing challenges posed by complex systems and achieving various objectives. This process demands labor-intensive endeavors and multidisciplinary expertise. Large language models (LLMs) encapsulating cross-domain knowledge and programming proficiency could potentially alleviate the difficulty of this process. However, LLMs excel in handling sequential information, making it challenging for analyzing the intricate interactions and nonlinear dynamics inherent in ABMs. Additionally, due to the lack of self-evaluation capability of LLMs, relying solely on LLMs is insufficient to effectively accomplish this process. In this paper, we present SAGE, a general solution-oriented ABM generation framework designed for automatic modeling and generating solutions for targeted problems. Unlike approaches reliant on expert handcrafting or resource-intensive neural network training, SAGE establishes a verifier-assisted iterative in-context learning process employing large language models (LLMs) to leverages their inherent cross-domain knowledge for tackling intricate demands from diverse domain scenarios. In SAGE, we introduce an semi-structured conceptual representation expliciting the intricate structures of ABMs and an objective representation to guide LLMs in modeling scenarios and proposing hypothetical solutions through in-context learning. To ensure the model executability and solution feasibility, SAGE devises a two-level verifier with chain-of-thought prompting tailored to the complex interactions and non-linear dynamics of ABMs, driving the iterative generation optimization. Moreover, we construct an evaluation dataset of solution-oriented ABMs from open sources.It contains practical models across various domains.

Abstract--In this article, we propose a multi-agent deep reinforcement learning (MADRL) framework to train a multiple access protocol for downlink low earth orbit (LEO) satellite networks. By improving the existing learned protocol, emergent random access channel (eRACH), our proposed method, coined centralized and compressed emergent signaling for eR-ACH (Ce2RACH), can mitigate inter-satellite interference by exchanging additional signaling messages jointly learned through the MADRL training process. Simulations demonstrate that Ce2RACH achieves up to 36.65% higher network throughput compared to eRACH, while the cost of signaling messages increase linearly with the number of users. Despite the non-stationarity, the orbiting movements of LEO satellites create underlying patterns that exchange additional control signaling messages, inspired by can be discerned through MADRL. In this regard, the emergent protocol learning frameworks that train signaling messages random access channel (eRACH) protocol has recently been for specific environments [3].

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared vocabulary for both text and speech tokens. Then they train a single decoder-only Transformer on a mixture of speech tasks. However, these models rely on the Loss Masking strategy for the ASR task, which ignores the dependency among speech tokens. In this paper, we propose to model speech tokens in an autoregressive way, similar to text. We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach. To address this issue, we propose a novel approach denoted Smoothed Label Distillation (SLD), which applies a KL divergence loss with smoothed labels on speech tokens. Our experiments show that SLD effectively models speech tokens and outperforms Loss Masking for decoder-only Transformers in ASR tasks with different speech discretization methods. The source code can be found here: https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/sld

Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning agent utilizing spatio-temporal abstractions to generalize learned skills in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and hence enables sparse decision-making and focused computation on the relevant parts of the environment. This relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guarantees under appropriate assumptions and establish where our approach is expected to be helpful. Generalization-focused experiments validate Skipper's significant advantage in zero-shot generalization, compared to existing state-of-the-art hierarchical planning methods.

An indictment from the US Department of Justice may have solved the mystery of how disgraced cryptocurrency exchange FTX lost over 400 million in crypto. The indictment, filed last week, alleges that three individuals used a SIM-swapping attack to steal hundreds of millions in virtual currency from an unnamed company. The timing and the amount stolen coincides with FTX's theft. Meanwhile, in a letter obtained by WIRED this week, seven lawmakers have demanded the DOJ stop funding biased and inaccurate predictive policing tools until the agency has a way to ensure law enforcement won't use them in a way that has a "discriminatory impact." In Florida, prosecutors say a 17-year-old named Alan Winston Filion is responsible for hundreds of swatting attacks around the United States.

Digital images and videos play a very important role in everyday life. Nowadays, people have access the affordable mobile devices equipped with advanced integrated cameras and powerful image processing applications. Technological development facilitates not only the generation of multimedia content, but also the intentional modification of it, either with recreational or malicious purposes. This is where forensic techniques to detect manipulation of images and videos become essential. This paper proposes a forensic technique by analysing compression algorithms used by the H.264 coding. The presence of recompression uses information of macroblocks, a characteristic of the H.264-MPEG4 standard, and motion vectors. A Vector Support Machine is used to create the model that allows to accurately detect if a video has been recompressed.

Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. However, most existing early exiting methods only consider local information from an individual test sample to determine their exiting indicators, failing to leverage the global information offered by sample population. This leads to suboptimal estimation of prediction correctness, resulting in erroneous exiting decisions. To bridge the gap, we explore the necessity of effectively combining both local and global information to ensure reliable early exiting during inference. Purposefully, we leverage prototypical networks to learn class prototypes and devise a distance metric between samples and class prototypes. This enables us to utilize global information for estimating the correctness of early predictions. On this basis, we propose a novel Distance-Enhanced Early Exiting framework for BERT (DE$^3$-BERT). DE$^3$-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions. Extensive experiments on the GLUE benchmark demonstrate that DE$^3$-BERT consistently outperforms state-of-the-art models under different speed-up ratios with minimal storage or computational overhead, yielding a better trade-off between model performance and inference efficiency. Additionally, an in-depth analysis further validates the generality and interpretability of our method.