Search

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing limited question-answer pairs per image, do not fully exploit visual information to enhance the multimodal mathematical reasoning capabilities of Multimodal LLMs (MLLMs). To bridge this gap, we address the lack of high-quality, diverse multimodal mathematical datasets by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs, creating the MathV360K dataset, which enhances both the breadth and depth of multimodal mathematical questions. We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5, achieving a 19-point increase and comparable performance to GPT-4V on MathVista's minitest split, and yielding leading performance on Math-V and MathVerse. Furthermore, Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark. Our research highlights the importance of dataset diversity and synthesis in advancing MLLMs' mathematical reasoning abilities. The code and data are available at: \url{https://github.com/HZQ950419/Math-LLaVA}., Comment: Accepted at Findings of EMNLP2024

We introduce a novel, multimodal large-scale scene reconstruction benchmark that utilizes newly developed 3D representation approaches: Gaussian Splatting and Neural Radiance Fields (NeRF). Our expansive U-Scene dataset surpasses any previously existing real large-scale outdoor LiDAR and image dataset in both area and point count. GauU-Scene encompasses over 6.5 square kilometers and features a comprehensive RGB dataset coupled with LiDAR ground truth. Additionally, we are the first to propose a LiDAR and image alignment method for a drone-based dataset. Our assessment of GauU-Scene includes a detailed analysis across various novel viewpoints, employing image-based metrics such as SSIM, LPIPS, and PSNR on NeRF and Gaussian Splatting based methods. This analysis reveals contradictory results when applying geometric-based metrics like Chamfer distance. The experimental results on our multimodal dataset highlight the unreliability of current image-based metrics and reveal significant drawbacks in geometric reconstruction using the current Gaussian Splatting-based method, further illustrating the necessity of our dataset for assessing geometry reconstruction tasks. We also provide detailed supplementary information on data collection protocols and make the dataset available on the following anonymous project page

This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design. By harnessing in-context learning and specialized tiered physics-informed neural networks, PE-GPT guides users through text-based dialogues, recommending actionable modulation parameters. The effectiveness of PE-GPT is validated through a practical design case involving dual active bridge converters, supported by hardware experimentation. This research underscores the transformative potential of large language models in power converter modulation design, offering enhanced accessibility, explainability, and efficiency, thereby setting a new paradigm in the field.

Resource allocation in tactical ad-hoc networks presents unique challenges due to their dynamic and multi-hop nature. Accurate prediction of future network connectivity is essential for effective resource allocation in such environments. In this paper, we introduce the Spatial-Temporal Graph Encoder-Decoder (STGED) framework for Tactical Communication Networks that leverages both spatial and temporal features of network states to learn latent tactical behaviors effectively. STGED hierarchically utilizes graph-based attention mechanism to spatially encode a series of communication network states, leverages a recurrent neural network to temporally encode the evolution of states, and a fully-connected feed-forward network to decode the connectivity in the future state. Through extensive experiments, we demonstrate that STGED consistently outperforms baseline models by large margins across different time-steps input, achieving an accuracy of up to 99.2\% for the future state prediction task of tactical communication networks.

Volumetric video has emerged as a prominent medium within the realm of eXtended Reality (XR) with the advancements in computer graphics and depth capture hardware. Users can fully immersive themselves in volumetric video with the ability to switch their viewport in six degree-of-freedom (DOF), including three rotational dimensions (yaw, pitch, roll) and three translational dimensions (X, Y, Z). Different from traditional 2D videos that are composed of pixel matrices, volumetric videos employ point clouds, meshes, or voxels to represent a volumetric scene, resulting in significantly larger data sizes. While previous works have successfully achieved volumetric video streaming in video-on-demand scenarios, the live streaming of volumetric video remains an unresolved challenge due to the limited network bandwidth and stringent latency constraints. In this paper, we for the first time propose a holistic live volumetric video streaming system, LiveVV, which achieves multi-view capture, scene segmentation \& reuse, adaptive transmission, and rendering. LiveVV contains multiple lightweight volumetric video capture modules that are capable of being deployed without prior preparation. To reduce bandwidth consumption, LiveVV processes static and dynamic volumetric content separately by reusing static data with low disparity and decimating data with low visual saliency. Besides, to deal with network fluctuation, LiveVV integrates a volumetric video adaptive bitrate streaming algorithm (VABR) to enable fluent playback with the maximum quality of experience. Extensive real-world experiment shows that LiveVV can achieve live volumetric video streaming at a frame rate of 24 fps with a latency of less than 350ms.

Volumetric video, which offers immersive viewing experiences, is gaining increasing prominence. With its six degrees of freedom, it provides viewers with greater immersion and interactivity compared to traditional videos. Despite their potential, volumetric video services poses significant challenges. This survey conducts a comprehensive review of the existing literature on volumetric video. We firstly provide a general framework of volumetric video services, followed by a discussion on prerequisites for volumetric video, encompassing representations, open datasets, and quality assessment metrics. Then we delve into the current methodologies for each stage of the volumetric video service pipeline, detailing capturing, compression, transmission, rendering, and display techniques. Lastly, we explore various applications enabled by this pioneering technology and we present an array of research challenges and opportunities in the domain of volumetric video services. This survey aspires to provide a holistic understanding of this burgeoning field and shed light on potential future research trajectories, aiming to bring the vision of volumetric video to fruition., Comment: Submitted

Volumetric video emerges as a new attractive video paradigm in recent years since it provides an immersive and interactive 3D viewing experience with six degree-of-freedom (DoF). Unlike traditional 2D or panoramic videos, volumetric videos require dense point clouds, voxels, meshes, or huge neural models to depict volumetric scenes, which results in a prohibitively high bandwidth burden for video delivery. Users' behavior analysis, especially the viewport and gaze analysis, then plays a significant role in prioritizing the content streaming within users' viewport and degrading the remaining content to maximize user QoE with limited bandwidth. Although understanding user behavior is crucial, to the best of our best knowledge, there are no available 3D volumetric video viewing datasets containing fine-grained user interactivity features, not to mention further analysis and behavior prediction. In this paper, we for the first time release a volumetric video viewing behavior dataset, with a large scale, multiple dimensions, and diverse conditions. We conduct an in-depth analysis to understand user behaviors when viewing volumetric videos. Interesting findings on user viewport, gaze, and motion preference related to different videos and users are revealed. We finally design a transformer-based viewport prediction model that fuses the features of both gaze and motion, which is able to achieve high accuracy at various conditions. Our prediction model is expected to further benefit volumetric video streaming optimization. Our dataset, along with the corresponding visualization tools is accessible at https://cuhksz-inml.github.io/user-behavior-in-vv-watching/, Comment: Accepted by ACM MM'23

Itinerary recommendation is a complex sequence prediction problem with numerous real-world applications. This task becomes even more challenging when considering the optimization of multiple user queuing times and crowd levels, as well as numerous involved parameters, such as attraction popularity, queuing time, walking time, and operating hours. Existing solutions typically focus on single-person perspectives and fail to address real-world issues resulting from natural crowd behavior, like the Selfish Routing problem. In this paper, we introduce the Strategic and Crowd-Aware Itinerary Recommendation (SCAIR) algorithm, which optimizes group utility in real-world settings. We model the route recommendation strategy as a Markov Decision Process and propose a State Encoding mechanism that enables real-time planning and allocation in linear time. We evaluate our algorithm against various competitive and realistic baselines using a theme park dataset, demonstrating that SCAIR outperforms these baselines in addressing the Selfish Routing problem across four theme parks., Comment: Will be going through major revision

Recent years have witnessed a rapid development of immersive multimedia which bridges the gap between the real world and virtual space. Volumetric videos, as an emerging representative 3D video paradigm that empowers extended reality, stand out to provide unprecedented immersive and interactive video watching experience. Despite the tremendous potential, the research towards 3D volumetric video is still in its infancy, relying on sufficient and complete datasets for further exploration. However, existing related volumetric video datasets mostly only include a single object, lacking details about the scene and the interaction between them. In this paper, we focus on the current most widely used data format, point cloud, and for the first time release a full-scene volumetric video dataset that includes multiple people and their daily activities interacting with the external environments. Comprehensive dataset description and analysis are conducted, with potential usage of this dataset. The dataset and additional tools can be accessed via the following website: https://cuhksz-inml.github.io/full_scene_volumetric_video_dataset/., Comment: Accepted by MMSys'23 Open Dataset and Software Track. The dataset and additional tools can be accessed via https://cuhksz-inml.github.io/full_scene_volumetric_video_dataset/

POI-level geo-information of social posts is critical to many location-based applications and services. However, the multi-modality, complexity and diverse nature of social media data and their platforms limit the performance of inferring such fine-grained locations and their subsequent applications. To address this issue, we present a transformer-based general framework, which builds upon pre-trained language models and considers non-textual data, for social post geolocation at the POI level. To this end, inputs are categorized to handle different social data, and an optimal combination strategy is provided for feature representations. Moreover, a uniform representation of hierarchy is proposed to learn temporal information, and a concatenated version of encodings is employed to capture feature-wise positions better. Experimental results on various social datasets demonstrate that three variants of our proposed framework outperform multiple state-of-art baselines by a large margin in terms of accuracy and distance error metrics., Comment: Full papers are 12 pages in length plus additional 4 pages for references (turns to 18 pages in total after submitting to arxiv). One figure and 5 tables are contained. This paper was submitted to ECIR 2023 for review

360{\deg} videos in recent years have experienced booming development. Compared to traditional videos, 360{\deg} videos are featured with uncertain user behaviors, bringing opportunities as well as challenges. Datasets are necessary for researchers and developers to explore new ideas and conduct reproducible analyses for fair comparisons among different solutions. However, existing related datasets mostly focused on users' field of view (FoV), ignoring the more important eye gaze information, not to mention the integrated extraction and analysis of both FoV and eye gaze. Besides, users' behavior patterns are highly related to videos, yet most existing datasets only contained videos with subjective and qualitative classification from video genres, which lack quantitative analysis and fail to characterize the intrinsic properties of a video scene. To this end, we first propose a quantitative taxonomy for 360{\deg} videos that contains three objective technical metrics. Based on this taxonomy, we collect a dataset containing users' head and gaze behaviors simultaneously, which outperforms existing datasets with rich dimensions, large scale, strong diversity, and high frequency. Then we conduct a pilot study on user's behaviors and get some interesting findings such as user's head direction will follow his/her gaze direction with the most possible time interval. A case of application in tile-based 360{\deg} video streaming based on our dataset is later conducted, demonstrating a great performance improvement of existing works by leveraging our provided gaze information. Our dataset is available at https://cuhksz-inml.github.io/head_gaze_dataset/, Comment: Accepted by ACM MM 2022. Dataset is available at https://cuhksz-inml.github.io/head_gaze_dataset

The scientific world is changing at a rapid pace, with new technology being developed and new trends being set at an increasing frequency. This paper presents a framework for conducting scientific analyses of academic publications, which is crucial to monitor research trends and identify potential innovations. This framework adopts and combines various techniques of Natural Language Processing, such as word embedding and topic modelling. Word embedding is used to capture semantic meanings of domain-specific words. We propose two novel scientific publication embedding, i.e., PUB-G and PUB-W, which are capable of learning semantic meanings of general as well as domain-specific words in various research fields. Thereafter, topic modelling is used to identify clusters of research topics within these larger research fields. We curated a publication dataset consisting of two conferences and two journals from 1995 to 2020 from two research domains. Experimental results show that our PUB-G and PUB-W embeddings are superior in comparison to other baseline embeddings by a margin of ~0.18-1.03 based on topic coherence., Comment: Accepted at the 2021 IEEE International Conference on Big Data (BigData2021)

The advent of social media platforms has been a catalyst for the development of digital photography that engendered a boom in vision applications. With this motivation, we introduce a large-scale dataset termed 'Photozilla', which includes over 990k images belonging to 10 different photographic styles. The dataset is then used to train 3 classification models to automatically classify the images into the relevant style which resulted in an accuracy of ~96%. With the rapid evolution of digital photography, we have seen new types of photography styles emerging at an exponential rate. On that account, we present a novel Siamese-based network that uses the trained classification models as the base architecture to adapt and classify unseen styles with only 25 training samples. We report an accuracy of over 68% for identifying 10 other distinct types of photography styles. This dataset can be found at https://trisha025.github.io/Photozilla/, Comment: In the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. (Poster)

An important aspect of urban planning is understanding crowd levels at various locations, which typically require the use of physical sensors. Such sensors are potentially costly and time consuming to implement on a large scale. To address this issue, we utilize publicly available social media datasets and use them as the basis for two urban sensing problems, namely event detection and crowd level prediction. One main contribution of this work is our collected dataset from Twitter and Flickr, alongside ground truth events. We demonstrate the usefulness of this dataset with two preliminary supervised learning approaches: firstly, a series of neural network models to determine if a social media post is related to an event and secondly a regression model using social media post counts to predict actual crowd levels. We discuss preliminary results from these tasks and highlight some challenges., Comment: Accepted at the 2020 IEEE International Conference on Big Data (BigData'20), Poster Track

Teaching is about constantly innovating strategies, ways and means to engage diverse students in active and meaningful learning. In line with this, SUTD adopts various student-centric teaching and learning teaching methods and approaches. This means that our graduate/undergraduate instructors have to be ready to teach using these student student-centric teaching and learning pedagogies. In this article, I share my experiences of redesigning this teaching course that is typically conducted face-to-face to a synchronous online course and also invite one of the participant in this course to reflect on his experience as a student.

Since the start of COVID-19, several relevant corpora from various sources are presented in the literature that contain millions of data points. While these corpora are valuable in supporting many analyses on this specific pandemic, researchers require additional benchmark corpora that contain other epidemics to facilitate cross-epidemic pattern recognition and trend analysis tasks. During our other efforts on COVID-19 related work, we discover very little disease related corpora in the literature that are sizable and rich enough to support such cross-epidemic analysis tasks. In this paper, we present EPIC30M, a large-scale epidemic corpus that contains 30 millions micro-blog posts, i.e., tweets crawled from Twitter, from year 2006 to 2020. EPIC30M contains a subset of 26.2 millions tweets related to three general diseases, namely Ebola, Cholera and Swine Flu, and another subset of 4.7 millions tweets of six global epidemic outbreaks, including 2009 H1N1 Swine Flu, 2010 Haiti Cholera, 2012 Middle-East Respiratory Syndrome (MERS), 2013 West African Ebola, 2016 Yemen Cholera and 2018 Kivu Ebola. Furthermore, we explore and discuss the properties of the corpus with statistics of key terms and hashtags and trends analysis for each subset. Finally, we demonstrate the value and impact that EPIC30M could create through a discussion of multiple use cases of cross-epidemic research topics that attract growing interest in recent years. These use cases span multiple research areas, such as epidemiological modeling, pattern recognition, natural language understanding and economical modeling.

Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite crisis such as natural disasters can be predicted by professional institutions, certain events are first signaled by civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often exposes firsthand signals on such crises through high volume information exchange over half a billion tweets posted daily. Prior works proposed various crisis embeddings and classification using conventional Machine Learning and Neural Network models. However, none of the works perform crisis embedding and classification using state of the art attention-based deep neural networks models, such as Transformers and document-level contextual embeddings. This work proposes CrisisBERT, an end-to-end transformer-based model for two crisis classification tasks, namely crisis detection and crisis recognition, which shows promising results across accuracy and f1 scores. The proposed model also demonstrates superior robustness over benchmark, as it shows marginal performance compromise while extending from 6 to 36 events with only 51.4% additional data points. We also proposed Crisis2Vec, an attention-based, document-level contextual embedding architecture for crisis embedding, which achieve better performance than conventional crisis embedding methods such as Word2Vec and GloVe. To the best of our knowledge, our works are first to propose using transformer-based crisis classification and document-level contextual crisis embedding in the literature.

There has been growing interest in utilizing occupational data mining and analysis. In today's job market, occupational data mining and analysis is growing in importance as it enables companies to predict employee turnover, model career trajectories, screen through resumes and perform other human resource tasks. A key requirement to facilitate these tasks is the need for an occupation-related dataset. However, most research use proprietary datasets or do not make their dataset publicly available, thus impeding development in this area. To solve this issue, we present the Industrial and Professional Occupation Dataset (IPOD), which comprises 192k job titles belonging to 56k LinkedIn users. In addition to making IPOD publicly available, we also: (i) manually annotate each job title with its associated level of seniority, domain of work and location; and (ii) provide embedding for job titles and discuss various use cases. This dataset is publicly available at https://github.com/junhua/ipod.

Primary and secondary education is a crucial stage to build a strong foundation before diving deep into specialised subjects in colleges and universities. To excel in the current education system, students are required to have a deep understanding of knowledge according to standardized curriculums and syllabus, and exam-related problem solving skills. In current school settings, this learning normally occurs in large classes of 30-40 students per class. Such a ``one size fits all'' approach may not be effective, as different students proceed on their learning in different ways and pace. To address this problem, we propose the Self-Evolving Adaptive Learning (SEAL) system for personalized education at scale.

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN., Comment: 8 pages, 4 figures

Occupational data mining and analysis is an important task in understanding today's industry and job market. Various machine learning techniques are proposed and gradually deployed to improve companies' operations for upstream tasks, such as employee churn prediction, career trajectory modelling and automated interview. Job titles analysis and embedding, as the fundamental building blocks, are crucial upstream tasks to address these occupational data mining and analysis problems. In this work, we present the Industrial and Professional Occupations Dataset (IPOD), which consists of over 190,000 job titles crawled from over 56,000 profiles from Linkedin. We also illustrate the usefulness of IPOD by addressing two challenging upstream tasks, including: (i) proposing Title2vec, a contextual job title vector representation using a bidirectional Language Model (biLM) approach; and (ii) addressing the important occupational Named Entity Recognition problem using Conditional Random Fields (CRF) and bidirectional Long Short-Term Memory with CRF (LSTM-CRF). Both CRF and LSTM-CRF outperform human and baselines in both exact-match accuracy and F1 scores. The dataset and pre-trained embeddings are available at https://www.github.com/junhua/ipod.

There is a rapidly growing demand for itinerary planning in tourism but this task remains complex and difficult, especially when considering the need to optimize for queuing time and crowd levels for multiple users. This difficulty is further complicated by the large amount of parameters involved, i.e., attraction popularity, queuing time, walking time, operating hours, etc. Many recent works propose solutions based on the single-person perspective, but otherwise do not address real-world problems resulting from natural crowd behavior, such as the Selfish Routing problem, which describes the consequence of ineffective network and sub-optimal social outcome by leaving agents to decide freely. In this work, we propose the Strategic and Crowd-Aware Itinerary Recommendation (SCAIR) algorithm which optimizes social welfare in real-world situations. We formulate the strategy of route recommendation as Markov chains which enables our simulations to be carried out in poly-time. We then evaluate our proposed algorithm against various competitive and realistic baselines using a theme park dataset. Our simulation results highlight the existence of the Selfish Routing problem and show that SCAIR outperforms the baselines in handling this issue.

Recent advances on quantum computing hardware have pushed quantum computing to the verge of quantum supremacy. Random quantum circuits are outstanding candidates to demonstrate quantum supremacy, which could be implemented on a quantum device that supports nearest-neighbour gate operations on a two-dimensional configuration. Here we show that using the Projected Entangled-Pair States algorithm, a tool to study two-dimensional strongly interacting many-body quantum systems, we can realize an effective general-purpose simulator of quantum algorithms. This technique allows to quantify precisely the memory usage and the time requirements of random quantum circuits, thus showing the frontier of quantum supremacy. With this approach we can compute the full wave-function of the system, from which single amplitudes can be sampled with unit fidelity. Applying this general quantum circuit simulator we measured amplitudes for a $7\times 7$ lattice of qubits with depth $1+40+1$ and double-precision numbers in 31 minutes using less than $93$ TB memory on the Tianhe-2 supercomputer., Comment: 10 pages, 6 figures, 1 table

Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through lexcially-constrained beam search in the decoding phase. Unfortunately, these lexically-constrained beam search methods suffer two fatal disadvantages: high computational complexity and hard beam search which generates unexpected translations. In this paper, we propose to learn the ability of lexically-constrained translation with external memory, which can overcome the above mentioned disadvantages. For the training process, automatically extracted phrase pairs are extracted from alignment and sentence parsing, then further be encoded into an external memory. This memory is then used to provide lexically-constrained information for training through a memory-attention machanism. Various experiments are conducted on WMT Chinese to English and English to German tasks. All the results can demonstrate the effectiveness of our method.

This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement., Comment: 5 pages, 8 tabels