输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
In the last years, several variants of transformers have emerged. In this paper, we compare different transformer-based models for solving the reverse dictionary task and explore their use in the context of a serious game called The Dictionary Game.
Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM's efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.
Supervised-contrastive loss (SCL) is an alternative to cross-entropy (CE) for classification tasks that makes use of similarities in the embedding space to allow for richer representations. Previous works have used trainable prototypes to help improve test accuracy of SCL when training under imbalance. In this work, we propose the use of fixed prototypes to help engineering the feature geometry when training with SCL. We gain further insights by considering a limiting scenario where the number of prototypes far outnumber the original batch size. Through this, we establish a connection to CE loss with a fixed classifier and normalized embeddings. We validate our findings by conducting a series of experiments with deep neural networks on benchmark vision datasets.
Transcription factors (TFs) play a fundamental role in gene regulation by selectively binding to specific DNA sequences. Understanding the nature and behavior of these TFs is essential for insights into gene regulation dynamics. In this study, we introduce a robust multi-task learning framework specifically tailored to harness both TF-specific annotations and TF-related domain annotations, thereby enhancing the accuracy of TF predictions. Notably, we incorporate cutting-edge language models that have recently garnered attention for their outstanding performance across various fields, particularly in biological computations like protein sequence modeling. Comparative experimental analysis with existing models, DeepTFactor and TFpredict, reveals that our multi-task learning framework achieves an accuracy exceeding 92% across four evaluation metrics on the TF prediction task, surpassing both competitors. Our work marks a significant leap in the domain of TF prediction, enriching our comprehension of gene regulatory mechanisms and paving the way for the discovery of novel regulatory motifs.
The COVID-19 pandemic has exacerbated the challenges faced by healthcare delivery in developing nations, placing additional strain on already fragile infrastructure and healthcare systems. This has prompted an increased reliance on lay healthcare workers (LHWs) to meet the surging demand for services. Due to limited formal training, many LHWs have resorted to using unreliable sources, such as internet searches, to access medical information. Large language models (LLMs) offer a promising opportunity to support LHWs by providing accurate, context-sensitive information for improving healthcare delivery, provided they are appropriately fine-tuned on domain-specific multilingual data. This paper delves into critical issues and presents potential solutions for developing LLM-powered virtual assistants tailored to LHWs serving Telugu and Hindi-speaking populations. Key focal points include the customization of language and content to suit local contexts, the integration of feedback mechanisms to continuously enhance assistance quality, and the delicate balance between automation and human oversight.
The Transformer architecture has seen a lot of attention in recent years also thanks to its ability to scale well and allow massive parallelism during training. This has made possible the development of Language Models (LMs) of increasing size and the discovery of latent abilities that completely outclass traditional methods e.g. rule-based systems. However, they also introduced new issues, like their inability to retain the history of previous interactions due to their stateless nature or the difficulty in controlling their generation. Different attempts have been made to address these issues, e.g. a `brute force' approach to solving the memory issue is to include the full conversation history in the context window, a solution that is limited by the quadratic scalability of Transformers. In this work, we explore computationally practical solutions to the memory problem. We propose to augment the decoder-only architecture of (most) Large LMs with a (relatively small) memory encoder. Its output is prepended to the decoder's input in a similar fashion to recent works in Adapters and the original Transformer architecture. Initial experiments show promising results, however future work is needed to compare with State-of-the-Art methods.
Achieving fairness in Large Language Models (LLMs) continues to pose a persistent challenge, as these models are prone to inheriting biases from their training data, which can subsequently impact their performance in various applications. There is a need to systematically explore whether structured prompting techniques can offer opportunities for debiased text generation by LLMs. In this work, we designed an evaluative framework to test the efficacy of different prompting techniques for debiasing text along different dimensions. We aim to devise a general structured prompting approach to achieve fairness that generalizes well to different texts and LLMs.
Crime prediction stands as a pivotal concern within the realm of urban management due to its potential threats to public safety. While prior research has predominantly focused on unraveling the intricate dependencies among urban regions and temporal dynamics, the challenges posed by the scarcity and uncertainty of historical crime data have not been thoroughly investigated. This study introduces an innovative spatial-temporal augmented learning framework for crime prediction, namely STAug. In STAug, we devise a CrimeMix to improve the ability of generalization. Furthermore, we harness a spatial-temporal aggregation to capture and incorporate multiple correlations covering the temporal, spatial, and crime-type aspects. Experiments on two real-world datasets underscore the superiority of STAug over several baselines.
Recently there has been a proliferation of intrinsic motivation (IM) reward shaping methods to learn in complex and sparse-reward environments. These methods can often inadvertently change the set of optimal policies in an environment, leading to suboptimal behavior. Previous work on mitigating the risks of reward shaping, particularly through potential-based reward shaping (PBRS), has not been applicable to many IM methods, as they are often complex, trainable functions themselves, and therefore dependent on a wider set of variables than the traditional reward functions that PBRS was developed for. We present an extension to PBRS that we show preserves the set of optimal policies under a more general set of functions than has been previously demonstrated. We also present Potential-Based Intrinsic Motivation (PBIM), a method for converting IM rewards into a potential-based form that are useable without altering the set of optimal policies. Testing in the MiniGrid DoorKey environment, we demonstrate that PBIM successfully prevents the agent from converging to a suboptimal policy and can speed up training.
Face video stylization aims to convert real face videos into specified reference styles. While one-shot methods perform well in single-image stylization, ensuring continuity between frames and retaining the original facial expressions present challenges in video stylization. To address these issues, our approach employs a personalized diffusion model with pixel-level control. We propose Local Consistency Guidance(LCG) strategy, composed of local-cross attention and local style transfer, to ensure temporal consistency. This framework enables the synthesis of high-quality stylized face videos with excellent temporal continuity.
The maritime industry's continuous commitment to sustainability has led to a dedicated exploration of methods to reduce vessel fuel consumption. This paper undertakes this challenge through a machine learning approach, leveraging a real-world dataset spanning two years of a passenger vessel in west coast Canada. Our focus centers on the creation of a time series forecasting model given the dynamic and static states, actions, and disturbances. This model is designed to predict dynamic states based on the actions provided, subsequently serving as an evaluative tool to assess the proficiency of the vessel's operation under the captain's guidance. Additionally, it lays the foundation for future optimization algorithms, providing valuable feedback on decision-making processes. To facilitate future studies, our code is available at https://github.com/pagand/model_optimze_vessel/tree/AAAI.
Federated Learning is an effective approach for learning from data distributed across multiple institutions. While most existing studies are aimed at improving predictive accuracy of models, little work has been done to explain knowledge differences between institutions and the benefits of collaboration. Understanding these differences is critical in cross-silo federated learning domains, e.g., in healthcare or banking, where each institution or silo has a different underlying distribution and stakeholders want to understand how their institution compares to their partners. We introduce Prototype-Informed Cross-Silo Router (PICSR) which utilizes a mixture of experts approach to combine local models derived from multiple silos. Furthermore, by computing data similarity to prototypical samples from each silo, we are able to ground the router’s predictions in the underlying dataset distributions. Experiments on a real-world heart disease prediction dataset show that PICSR retains high performance while enabling further explanations on the differences among institutions compared to a single black-box model.
The Ramsey problem R(3,8) asks for the smallest n such that every red/blue coloring of the complete graph on n vertices must contain either a blue triangle or a red 8-clique. We provide the first certifiable proof that R(3,8) = 28, automatically generated by a combination of Boolean satisfiability (SAT) solver and a computer algebra system (CAS). This SAT+CAS combination is significantly faster than a SAT-only approach. While the R(3,8) problem was first computationally solved by McKay and Min in 1992, it was not a verifiable proof. The SAT+CAS method that we use for our proof is very general and can be applied to a wide variety of combinatorial problems.
This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence tasks. We substitute key elements of the attention mechanism in the Transformer with simple feed-forward networks, trained using the original components via knowledge distillation. Our experiments, conducted on the IWSLT2017 dataset, reveal the capacity of these ”attentionless Transformers” to rival the performance of the original architecture. Through rigorous ablation studies, and experimenting with various replacement network types and sizes, we offer insights that support the viability of our approach. This not only sheds light on the adaptability of shallow feed-forward networks in emulating attention mechanisms but also underscores their potential to streamline complex architectures for sequence-to-sequence tasks.
An exoplanet is a planet, which is not a part of our solar system. Whether life exists in one or more of these exoplanets has fascinated humans for centuries. NASA’s Kepler Space Telescope has discovered more than 70% of known exoplanets in our universe. However, manually determining whether a Kepler light curve indicates an exoplanet or not becomes infeasible with the large volume of data. Due to this, we propose a deep learning-based strategy to automatically classify a Kepler light curve. More specifically, we first convert the light curve time series into its corresponding Markov Transition Field (MTF) image and then classify it. Results show that the accuracy of the proposed technique is 99.39%, which is higher than all current state-of-the-art approaches.
It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer model based on the contextual constraints of scene flow. Our method uses the multi-frame point cloud context relationship as a guide to generate a series of token proposals, this priori condition ensures the stability of the point cloud completion. The experimental results show that the method proposed in this paper achieves high accuracy and good stability.
Abstractive text summarization uses the summarizer’s own words to capture the main information of a source document in a summary. While it is more challenging to automate than extractive text summarization, recent advancements in deep learning approaches and pre-trained language models have improved its performance. However, abstractive text summarization still has issues such as unfaithfulness. To address this problem, we propose a new approach that utilizes important Elementary Discourse Units (EDUs) to guide BART-based text summarization. Our approach showed the improvement in truthfulness and source document coverage in comparison to some previous studies.
We consider a platform in a two-sided market with unit-supply sellers and unit-demand buyers. Each buyer can transact with a subset of sellers it knows off platform and another seller that the platform recommends. Given the choice of sellers, transactions and prices form a competitive equilibrium. The platform selects one seller for each buyer, and charges a fixed percentage of prices to all transactions that it recommends. The platform seeks to maximize total revenue. We show that the platform's problem is NP-hard, even when each buyer knows at most two buyers off platform. Finally, when each buyer values all sellers equally and knows only one buyer off platform, we provide a polynomial time algorithm that optimally solves the problem.
Image/video denoising in low-light scenes is an extremely challenging problem due to limited photon count and high noise. In this paper, we propose a novel approach with contrastive learning to address this issue. Inspired by the success of contrastive learning used in some high-level computer vision tasks, we bring in this idea to the low-level denoising task. In order to achieve this goal, we introduce a new denoising contrastive regularization (DCR) to exploit the information of noisy images and clean images. In the feature space, DCR makes the denoised image closer to the clean image and far away from the noisy image. In addition, we build a new feature embedding network called Wnet, which is more effective to extract high-frequency information. We conduct the experiments on a real low-light dataset that captures still images taken on a moonless clear night in 0.6 millilux and videos under starlight (no moon present). The results show that our method can achieve a higher PSNR and better visual quality compared with existing methods.
Graph neural networks (GNNs) have attracted significant interest recently since they can effectively process and analyze graph-structured data commonly found in real-world applications. However, the predicament that GNNs are difficult to train becomes worse as the layers increase. The essence of this problem is that stacking layers will reduce the stability of forward propagation and gradient back-propagation. And as the increasing scale of models (measured by the number of parameters), how to efficiently and effectively adapt it to particular downstream tasks becomes an intriguing research issue. In this work, motivated by the effect of orthogonality constraints, we propose a simple orthogonal training framework to impose the orthogonality constraints on GNNs, which can help models find a solution vector in a specific low dimensional subspace and stabilize the signaling processes at both the forward and backward directions. Specifically, we propose a novel polar decomposition-based orthogonal initialization (PDOI-R) algorithm, which can identify the low intrinsic dimension within the Stiefel Manifold and stabilize the training process. Extensive experiments demonstrate the effectiveness of the proposed method in multiple downstream tasks, showcasing its generality. The simple method can help existing state-of-the-art models achieve better performance.