论文检索

Cassandra Goldberg

This paper proposes a novel approach for Synthetic Aperture Radar (SAR) image segmentation by incorporating known statistical properties of SAR into deep learning models. We generate synthetic data using the Generalized Gamma distribution, modify the U-Net architecture to encompass statistical moments, and employ stochastic distance losses for improved segmentation performance. Evaluation against traditional methods will reveal the potential of this approach to advance SAR image analysis, with broader applications in environmental monitoring and general image segmentation tasks.

Isaiah Gallardo

Constructing road networks manually is a time consuming and labor-intensive process. This paper proposes a new method to iteratively construct road networks using reinforcement learning from a combined tensor-based representation of satellite image and GPS trajectory data.

Joseph Fatoye

In the pursuit of creating more effective and adaptable robots, the flourishing field of cognitive robotics has arisen to infuse machines with human-like cognitive functions. This paper delves into the significance of cognitive robotics and charts a course for empowering robots with advanced cognitive capabilities. Drawing inspiration from current research in cognitive architectures, the paper underscores the importance of refined perception, language processing, complex decision-making, emotional intelligence, and cognitive synergy. By integrating these cognitive functions into robotic systems, the goal is to equip robots to operate intelligently in dynamic environments, collaborate seamlessly with humans, and adeptly handle diverse tasks. The proposed enhancements mark crucial strides towards the development of more versatile and capable intelligent robots.

Chahana Dahal

This proposal introduces an innovative AI-powered learning system designed to address educational disparities worldwide. Focused on developing countries, the system seamlessly translates educational content between English and native languages, breaking down language barriers. Leveraging advanced natural language processing and machine learning techniques, including transformer models like BERT and GPT-3, the system ensures inclusivity, effectiveness, and engagement. Built on prior research demonstrating AI's efficacy in language translation and personalized learning, the proposed system draws inspiration from successful projects like Duolingo Language Incubator. By providing inclusive and accessible learning experiences, it empowers individuals to overcome language barriers, fostering global participation. The potential impact is significant, with the system poised to accelerate learning, enhance literacy rates, and create a more skilled workforce in developing countries. This research reflects a commitment to revolutionize education through technology, aiming for lasting and transformative contributions to global society. Through AI-driven education, a brighter, more inclusive future is envisioned.

Minghai Chen

Event camera has unique advantages in high temporal resolution and dynamic range and has shown potentials in several computer vision tasks. However, due to the novelty of this hardware, there’s a lack of large benchmark DVS event-stream datasets, including datasets for object recognition. In this work, we proposed an encoder-decoder method to augment event stream dataset from image and optical flow with arbitrary temporal resolution for object recognition task. We believe this proposed method can be generalized well in augmenting event stream vision data for object recognition and will help advance the development of event vision paradigm.

Hanlin Cai

As the most popular low-power communication protocol, cybersecurity research on Bluetooth Low Energy (BLE) has garnered significant attention. Due to BLE’s inherent security limitations and firmware vulnerabilities, spoofing attacks can easily compromise BLE devices and tamper with privacy data. In this paper, we proposed BLEGuard, a hybrid detection mechanism combined cyber-physical features with learning-based techniques. We established a physical network testbed to conduct attack simulations and capture advertising packets. Four different network features were utilized to implement detection and classification algorithms. Preliminary results have verified the feasibility of our proposed methods.

Adam Baji

This study leverages Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to enhance diagnostics and predictions in healthcare. By training on extensive healthcare datasets, this project aims to improve early disease detection and health risk assessments. Evaluation emphasizes accuracy, reliability, and ethical considerations, including bias mitigation. This research promises to bridge AI advancements and clinical applications, offering significant improvements in diagnostic capabilities and healthcare accessibility.

Amy Au

This research explores the discourse surrounding red teaming and aims to identify any themes in the online discussion of potential environmental harms stemming from Large Language Models (LLMs). Focusing on the AI Red Teaming event at DEFCON 31, this study employs reflexive thematic analysis on diverse social networking site sources to extract insights into public discussion of LLM red teaming and its environmental implications. The findings intend to inform future research, highlighting the need for responsible AI development that addresses environmental concerns.

Varun Ananth

Considering that the human brain is the most powerful, generalizable, and energy-efficient computer we know of, it makes the most sense to look to neuroscience for ideas regarding deep learning model improvements. I propose one such idea, augmenting a traditional Advantage-Actor-Critic (A2C) model with additional learning signals akin to those in the brain. Pursuing this direction of research should hopefully result in a new reinforcement learning (RL) control paradigm that can learn from fewer examples, train with greater stability, and possibly consume less energy.

Oluwanifemi Adebayo Moses Adekanye

This paper outlines a proposal exploring the potential use of Large Language Models (LLMs), particularly GPT-4, in crafting realistic synthetic environments for self-driving scenarios. The envisioned approach involves dynamic scene generation within game engines, leveraging LLMs to introduce challenging elements for autonomous vehicles. The proposed evaluation process outlines assessments such as realistic testing, safety metrics, and user interaction, aiming to set the stage for potential improvements in self-driving system performance. The paper aims to contribute to the AI field by discussing how LLMs could be utilized to create valuable testing grounds for autonomous vehicles, potentially fostering the development of more robust self-driving technology. The envisioned impact is the eventual enhancement of road safety and the possible acceleration of the adoption of autonomous vehicles, paving the way for a future with safer and more efficient transportation.

Yujian Zhu, Hao Ding, Zongzhang Zhang

Ad hoc teamwork is a crucial challenge that aims to design an agent capable of effective collaboration with teammates employing diverse strategies without prior coordination. However, current Population-Based Training (PBT) approaches train the ad hoc agent through interaction with diverse teammates from scratch, which suffer from low efficiency. We introduce Multi-Expert Distillation (MED), a novel approach that directly distills diverse strategies through modeling across-episodic sequences. Experiments show that our algorithm achieves more efficient and stable training and has the ability to improve its behavior using historical contexts. Our code is available at https://github.com/LAMDA-RL/MED.

Brian Zhou, Jason Geder, Kamal Viswanath, Alisha Sharma, Julian Lee

Flapping-fin unmanned underwater vehicle (UUV) propulsion systems enable high maneuverability for tasks ranging from station-keeping to surveillance but are often constrained by their limited computational power and battery capacity. Previous research has demonstrated that time-series neural network models can accurately predict the thrust and power of certain fin kinematics based on the specified gait coupled with the fin configuration, but can not fit an inverse neural network that takes a thrust request and tunes the kinematics by weighting thrust generation, smooth movement transitions, and power attributes. We study various combinations of the three weights and fin materials to create different ‘modes’ of movement for a multi-objective UUV, based on controller intent using an inverse neural network. Finally, we implement and validate an enhanced power-aware inverse model by benchmarking on the Raspberry Pi Model 4B system and testing through generated simulated movements.

Chenxu Zhao, Wei Qian, Yucheng Shi, Mengdi Huai, Ninghao Liu

Interpreting deep neural networks through examining neurons offers distinct advantages when it comes to exploring the inner workings of Deep Neural Networks. Previous research has indicated that specific neurons within deep vision networks possess semantic meaning and play pivotal roles in model performance. Nonetheless, the current methods for generating neuron semantics heavily rely on human intervention, which hampers their scalability and applicability. To address this limitation, this paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models, without requiring human intervention or prior knowledge. Experiments are conducted with both qualitative and quantitative analysis to verify the effectiveness of our proposed approach.

Ye Zhang, Yanqi Gao, Yupeng Zhou, Jianan Wang, Minghao Yin

With the abundance of learning resources available on massive open online courses (MOOCs) platforms, the issue of interactive data sparsity has emerged as a significant challenge.This paper introduces MRMLREC, an efficient MOOC video recommendation which consists of two main stages: multi-relational representation and multi-level recommendation, aiming to solve the problem of data sparsity. In the multi-relational representation stage, MRMLREC adopts a tripartite approach, constructing relational graphs based on temporal sequences, courses-videos relation, and knowledge concepts-video relation. These graphs are processed by a Graph Convolution Network (GCN) and two variant Graph Attention Networks (GAT) to derive representations. A variant of the Long Short-Term Memory Network (LSTM) then integrates these multi-dimensional data to enhance the overall representation. The multi-level recommendation stage introduces three prediction tasks at varying levels—courses, knowledge concepts, and videos—to mitigate data sparsity and improve the interpretability of video recommendations. Beam search (BS) is employed to identify top-β items at each level, refining the subsequent level's search space and enhancing recommendation efficiency. Additionally, an optional layer offers both personalization and diversification modes, ensuring variety in recommended videos and maintaining learner engagement. Comprehensive experiments demonstrate the effectiveness of MRMLREC on two real-world instances from Xuetang X.

Sensen Zhang, Xun Liang, Simin Niu, Xuan Zhang, Chen Feng, Yuefeng Ma

Researchers have applied knowledge graph embedding (KGE) techniques with advanced neural network techniques, such as capsule networks, for predicting drug-drug interactions (DDIs) and achieved remarkable results. However, most ignore molecular structure and position features between drug pairs. They cannot model the biomedical field's significant relational mapping properties (RMPs,1-N, N-1, N-N) relation. To solve these problems, we innovatively propose CDHse that consists of two crucial modules: 1) Entity embedding module, we obtain position feature obtained by PubMedBERT and Convolutional Neural Network (CNN), obtain molecular structure feature with Graphic Nuaral Network (GNN), obtain entity embedding feature of drug pairs, and then incorporate these features into one synthetic feature. 2) Knowledge graph embedding module, the synthetic feature is Householder projections and then embedded in the complex vector space for training. In this paper, we have selected several advanced models for the DDIs task and performed experiments on three standard BioKG to validate the effectiveness of CDHse.

Jienan Zhang, Jie Liu, Zhangtao Cheng, Xovee Xu, Fang Liu, Ting Zhong, Kunpeng Zhang

Social media popularity prediction of multimodal user-generated content (UGC) is a crucial task for many real-world applications. However, existing efforts are often limited by missing inter-instance correlations and UGC temporal patterns. To address these issues, we propose a novel time-aware hypergraph Transformer framework, THGFormer. It fully represents inter-instance and intra-instance relations by hypergraphs, captures the temporal dependencies with a time encoder, and enhances UGC's representations via a neighborhood knowledge aggregation. Extensive experiments conducted on two real-world datasets demonstrate that THGFormer outperforms state-of-the-art popularity prediction models across several settings.

Wenhuan Zeng, Daniel H. Huson

DNA methylation is an epigenetic mechanism for regulating gene expression, and it plays an important role in many biological processes. While methylation sites can be identified using laboratory techniques, much work is being done on developing computational approaches using machine learning. Here, we present a deep-learning algorithm for determining the 5-methylcytosine status of a DNA sequence. We propose an ensemble framework that treats the self-attention score as an explicit feature that is added to the encoder layer generated by fine-tuned language models. We evaluate the performance of the model under different data distribution scenarios.

Liu Yu, Ludie Guo, Ping Kuang, Fan Zhou

Pre-trained language models (PLMs) have greatly transformed various downstream tasks, yet frequently display social biases from training data, raising fairness concerns. Recent efforts to debias PLMs come with limitations: they either fine-tune the entire parameters in PLMs, which is time-consuming and disregards the expressiveness of PLMs, or ignore the reintroducing biases from downstream tasks when applying debiased models to them. Hence, we propose a two-stage pipeline to mitigate biases from both internal and downstream contexts while preserving expressiveness in language models. Specifically, for the debiasing procedure, we resort to continuous prefix-tuning, not fully fine-tuning the PLM, in which we design a debiasing term for optimization and an alignment term to keep words’ relative distances and ensure the model's expressiveness. For downstream tasks, we perform causal intervention across different demographic groups for invariant predictions. Results on three GLUE tasks show our method alleviates biases from internal and downstream contexts, while keeping PLM expressiveness intact.

Liu Yu, Fenghui Tian, Ping Kuang, Fan Zhou

Conventional commonsense knowledge graph completion (CKGC) methods provide inadequate sequence when fine-tuning or generating stages and incorporate full fine-tuning, which fail to align with the autoregressive model's pre-training patterns and have insufficient parameter efficiency. Moreover, decoding through beam or greedy search produces low diversity and high similarity in generated tail entities. Hence, we resort to prefix-tuning and propose a lightweight, effective pipeline to enhance the quality and diversity of extracted commonsense knowledge. Precisely, we measure head entity similarity to yield and then concatenate top-k tuples before each target tuple for prefix-tuning the source LM, thereby improving the efficiency and speed for pretrained models; then, we design a penalty-tailored diverse beam search (p-DBS) for decoding tail entities, producing a greater quantity and diversity of generated commonsense tuples; besides, a filter strategy is utilized to filter out invalid commonsense knowledge. Through extensive automatic evaluations, including ChatGPT scoring, our method can extract diverse, novel, and accurate commonsense knowledge (CK).

Wenxue Ye, Shichong Li, Zhangtao Cheng, Xovee Xu, Ting Zhong, Bei Hui, Fan Zhou

Information diffusion prediction is a critical task for many social network applications. However, current methods are mainly limited by the following aspects: user relationships behind resharing behaviors are complex and entangled. To address these issues, we propose MHGFormer, a novel multi-channel hypergraph transformer framework, to better decouple complex user relations and obtain fine-grained user representations. First, we employ designed triangular motifs to decouple user relations into three different level hypergraphs. Second, a position-aware hypergraph transformer is used to refine user relation and obtain high-quality user representations. Extensive experiments conducted on two social datasets demonstrate that MHGFormer outperforms state-of-the-art diffusion models across several settings.