Vision Transformers (ViT) are current high-performance models of choice for various vision applications. Recent developments have given rise to biologically inspired spiking transformers that thrive in ultra-low power operations on neuromorphic hardware, however, without fully unlocking the potential of spiking neural networks. We introduce DS2TA, a Denoising Spiking transformer with attenuated SpatioTemporal Attention, designed specifically for vision applications. DS2TA introduces a new spiking attenuated spatiotemporal attention mechanism that considers input firing correlations occurring in both time and space, thereby fully harnessing the computational power of spiking neurons at the core of the transformer architecture. Importantly, DS2TA facilitates parameter-efficient spatiotemporal attention computation without introducing extra weights. DS2TA employs efficient hashmap-based nonlinear spiking attention denoisers to enhance the robustness and expressive power of spiking attention maps. DS2TA demonstrates state-of-the-art performances on several widely adopted static image and dynamic neuromorphic datasets. Operated over 4 time steps, DS2TA achieves 94.92% top-1 accuracy on CIFAR10 and 77.47% top-1 accuracy on CIFAR100, as well as 79.1% and 94.44% on CIFAR10-DVS and DVS-Gesture using 10 time steps.

Effective internet traffic prediction in smaller ISP networks is challenged by limited data availability. This paper explores this issue using transfer learning and data augmentation techniques with two LSTM-based models, LSTMSeq2Seq and LSTMSeq2SeqAtn, initially trained on a comprehensive dataset provided by Juniper Networks and subsequently applied to smaller datasets. The datasets represent real internet traffic telemetry, offering insights into diverse traffic patterns across different network domains. Our study revealed that while both models performed well in single-step predictions, multi-step forecasts were challenging, particularly in terms of long-term accuracy. In smaller datasets, LSTMSeq2Seq generally outperformed LSTMSeq2SeqAtn, indicating that higher model complexity does not necessarily translate to better performance. The models' effectiveness varied across different network domains, reflecting the influence of distinct traffic characteristics. To address data scarcity, Discrete Wavelet Transform was used for data augmentation, leading to significant improvements in model performance, especially in shorter-term forecasts. Our analysis showed that data augmentation is crucial in scenarios with limited data. Additionally, the study included an analysis of the models' variability and consistency, with attention mechanisms in LSTMSeq2SeqAtn providing better short-term forecasting consistency but greater variability in longer forecasts. The results highlight the benefits and limitations of different modeling approaches in traffic prediction. Overall, this research underscores the importance of transfer learning and data augmentation in enhancing the accuracy of traffic prediction models, particularly in smaller ISP networks with limited data availability.

Generative AI has shown its values for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. AutoVerus uses LLM to automatically generate correctness proof for Rust code. AutoVerus is designed to match the unique features of Verus, a verification tool that can prove the correctness of Rust code using proofs and specifications also written in Rust. AutoVerus consists of a network of LLM agents that are crafted and orchestrated to mimic human experts' three phases of proof construction: preliminary proof generation, proof refinement guided by generic tips, and proof debugging guided by verification errors. To thoroughly evaluate AutoVerus and help foster future research in this direction, we have built a benchmark suite of 150 non-trivial proof tasks, based on existing code-generation benchmarks and verification benchmarks. Our evaluation shows that AutoVerus can automatically generate correct proof for more than 90% of them, with more than half of them tackled in less than 30 seconds or 3 LLM calls.

Since the publication of CLIP, the approach of using InfoNCE loss for contrastive pre-training has become widely popular for bridging two or more modalities. Despite its wide adoption, CLIP's original design choices of L2 normalization and cosine similarity logit have rarely been revisited. We have systematically experimented with alternative geometries and softmax logits for language-image pre-training and identified that variants with intuitive Euclidean geometry, Euclidean CLIP (EuCLIP), match or exceed the performance of CLIP and support hierarchical relationships at least as well as more complicated hyperbolic alternative.

Othering, the act of portraying outgroups as fundamentally different from the ingroup, often escalates into framing them as existential threats--fueling intergroup conflict and justifying exclusion and violence. These dynamics are alarmingly pervasive, spanning from the extreme historical examples of genocides against minorities in Germany and Rwanda to the ongoing violence and rhetoric targeting migrants in the US and Europe. While concepts like hate speech and fear speech have been explored in existing literature, they capture only part of this broader and more nuanced dynamic which can often be harder to detect, particularly in online speech and propaganda. To address this challenge, we introduce a novel computational framework that leverages large language models (LLMs) to quantify othering across diverse contexts, extending beyond traditional linguistic indicators of hostility. Applying the model to real-world data from Telegram war bloggers and political discussions on Gab reveals how othering escalates during conflicts, interacts with moral language, and garners significant attention, particularly during periods of crisis. Our framework, designed to offer deeper insights into othering dynamics, combines with a rapid adaptation process to provide essential tools for mitigating othering's adverse impacts on social cohesion.

At the International Joint Conference on Artificial Intelligence (IJCAI) 2023, I had the opportunity to interview Jerry Tan from Lattel Robotics, a company dedicated to promoting AI-focused robotics education and training. They work closely with the RoboCup@Home Education initiative, supporting schools and institutions in introducing AI and service robot development to students. Their goal is to equip learners with practical AI application skills in computer vision, autonomous navigation, object manipulation and speech interactions. Through their AI robotics and AI applications workshops, Lattel Robotics offers an introduction to robot operating system (ROS)-based AI applications development in service robotics. As a hardware partner for the RoboCup@Home Education initiative, they assist schools and institutions in competing in AI robotic challenges by developing applications that address real-world problems.

Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and there always appears the situation that some modalities are missing. For example, video, audio, or text data is missing due to sensor failure or network bandwidth problems, which presents a great challenge to MER research. Traditional methods extract useful information from the complete modalities and reconstruct the missing modalities to learn robust multimodal joint representation. These methods have laid a solid foundation for research in this field, and to a certain extent, alleviated the difficulty of multimodal emotion recognition under missing modalities. However, relying solely on internal reconstruction and multimodal joint learning has its limitations, especially when the missing information is critical for emotion recognition. To address this challenge, we propose a novel framework of Retrieval Augment for Missing Modality Multimodal Emotion Recognition (RAMER), which introduces similar multimodal emotion data to enhance the performance of emotion recognition under missing modalities. By leveraging databases, that contain related multimodal emotion data, we can retrieve similar multimodal emotion information to fill in the gaps left by missing modalities. Various experimental results demonstrate that our framework is superior to existing state-of-the-art approaches in missing modality MER tasks. Our whole project is publicly available on https://github.com/WooyoohL/Retrieval_Augment_MER.

The United Nations 2030 Agenda for Sustainable Development outlines 17 goals to address global challenges. However, progress has been slower than expected and, consequently, there is a need to investigate the reasons behind this fact. In this study, we used a novel data-driven methodology to analyze data from 107 countries (2000$-$2022) using unsupervised machine learning techniques. Our analysis reveals strong positive and negative correlations between certain SDGs. The findings show that progress toward the SDGs is heavily influenced by geographical, cultural and socioeconomic factors, with no country on track to achieve all goals by 2030. This highlights the need for a region specific, systemic approach to sustainable development that acknowledges the complex interdependencies of the goals and the diverse capacities of nations. Our approach provides a robust framework for developing efficient and data-informed strategies, to promote cooperative and targeted initiatives for sustainable progress.

Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization with the help of salient information identified by the extractive model. Previous works that adopt this paradigm train the extractor and abstractor separately and introduce extra parameters to highlight the extracted salients to the abstractor, which results in error accumulation and additional training costs. In this paper, we first introduce a parameter-free highlight method into the encoder-decoder framework: replacing the encoder attention mask with a saliency mask in the cross-attention module to force the decoder to focus only on salient parts of the input. A preliminary analysis compares different highlight methods, demonstrating the effectiveness of our saliency mask. We further propose the novel extract-and-abstract paradigm, ExtAbs, which jointly and seamlessly performs Extractive and Abstractive summarization tasks within single encoder-decoder model to reduce error accumulation. In ExtAbs, the vanilla encoder is augmented to extract salients, and the vanilla decoder is modified with the proposed saliency mask to generate summaries. Built upon BART and PEGASUS, experiments on three datasets show that ExtAbs can achieve superior performance than baselines on the extractive task and performs comparable, or even better than the vanilla models on the abstractive task.

Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary associations between sounds and visual representations$\unicode{x2013}$known as sound symbolism$\unicode{x2013}$which is also observed in humans. We developed a specialized dataset with synthesized images and audio samples and assessed these models using a non-parametric approach in a zero-shot setting. Our findings reveal a significant correlation between the models' outputs and established patterns of sound symbolism, particularly in models trained on speech data. These results suggest that such models can capture sound-meaning connections akin to human language processing, providing insights into both cognitive architectures and machine learning strategies.