Search

Backpropagation is a cornerstone algorithm in training neural networks for supervised learning, which uses a gradient descent method to update network weights by minimizing the discrepancy between actual and desired outputs. Despite its pivotal role in propelling deep learning advancements, the biological plausibility of backpropagation is questioned due to its requirements for weight symmetry, global error computation, and dual-phase training. To address this long-standing challenge, many studies have endeavored to devise biologically plausible training algorithms. However, a fully biologically plausible algorithm for training multilayer neural networks remains elusive, and interpretations of biological plausibility vary among researchers. In this study, we establish criteria for biological plausibility that a desirable learning algorithm should meet. Using these criteria, we evaluate a range of existing algorithms considered to be biologically plausible, including Hebbian learning, spike-timing-dependent plasticity, feedback alignment, target propagation, predictive coding, forward-forward algorithm, perturbation learning, local losses, and energy-based learning. Additionally, we empirically evaluate these algorithms across diverse network architectures and datasets. We compare the feature representations learned by these algorithms with brain activity recorded by non-invasive devices under identical stimuli, aiming to identify which algorithm can most accurately replicate brain activity patterns. We are hopeful that this study could inspire the development of new biologically plausible algorithms for training multilayer networks, thereby fostering progress in both the fields of neuroscience and machine learning.

Time series data are collected in temporal order and are widely used to train systems for prediction, modeling and classification to name a few. These systems require large amounts of data to improve generalization and prevent over-fitting. However there is a comparative lack of time series data due to operational constraints. This situation is alleviated by synthesizing data which have a suitable spread of features yet retain the distinctive features of the original data. These would be its basic statistical properties and overall shape which are important for short time series such as in rehabilitative applications or in quickly changing portions of lengthy data. In our earlier work synthesized surrogate time series were used to augment rehabilitative data. This gave good results in classification but the resulting waveforms did not preserve the original signal shape. To remedy this, we use singular spectrum analysis (SSA) to separate a signal into trends and cycles to describe the shape of the signal and low level components. In a novel way we subject the low level component to randomizing processes then recombine this with the original trend and cycle components to form a synthetic time series. We compare our approach with other methods, using statistical and shape measures and demonstrate its effectiveness in classification., Comment: This version of the paper under the same title, acknowledges the data source and the funding for current research using this data. arXiv admin note: substantial text overlap with arXiv:2404.14211

Employing graph neural networks (GNNs) to learn cohesive and discriminative node representations for clustering has shown promising results in deep graph clustering. However, existing methods disregard the reciprocal relationship between representation learning and structure augmentation. This study suggests that enhancing embedding and structure synergistically becomes imperative for GNNs to unleash their potential in deep graph clustering. A reliable structure promotes obtaining more cohesive node representations, while high-quality node representations can guide the augmentation of the structure, enhancing structural reliability in return. Moreover, the generalization ability of existing GNNs-based models is relatively poor. While they perform well on graphs with high homogeneity, they perform poorly on graphs with low homogeneity. To this end, we propose a graph clustering framework named Synergistic Deep Graph Clustering Network (SynC). In our approach, we design a Transform Input Graph Auto-Encoder (TIGAE) to obtain high-quality embeddings for guiding structure augmentation. Then, we re-capture neighborhood representations on the augmented graph to obtain clustering-friendly embeddings and conduct self-supervised clustering. Notably, representation learning and structure augmentation share weights, significantly reducing the number of model parameters. Additionally, we introduce a structure fine-tuning strategy to improve the model's generalization. Extensive experiments on benchmark datasets demonstrate the superiority and effectiveness of our method. The code is released on GitHub and Code Ocean.

The nature of the interaction between active galactic nuclei (AGNs) and their host galaxies remains an unsolved question. Therefore, conducting an AGN census is valuable to AGN research. Nevertheless, a significant fraction of AGNs are obscured by their environment, which blocks UV and optical emissions due to the dusty torus surrounding the central supermassive black hole (SMBH). To overcome this challenge, mid-infrared (IR) surveys have emerged as a valuable tool for identifying obscured AGNs, as the obscured light is re-emitted in this range. With its high sensitivity, the James Webb Space Telescope (JWST) uncovered more fainter objects than previous telescopes. By applying the SED fitting, this work investigates AGN candidates in JWST Cosmic Evolution Early Release Science (CEERS) fields. We identified 42 candidates, 30 of them are classified as composites ($0.2\leq f_{\rm AGN, IR}< 0.5$), and 12 of them are AGNs ($f_{\rm AGN, IR}\geq 0.5$). We report the AGN luminosity contributions and AGN number fractions as a function of redshift and total infrared luminosity, showing that previously reported increasing relations are not apparent in our sample due to the sample size. We also extend the previous results on ultra-luminous infrared galaxies (ULIRGs, $L_{\rm TIR}\geq 10^{12} L_{\odot}$) to less luminous AGNs, highlighting the power of JWST., Comment: 15 pages, 20 figures, 4 tables. Accepted for publication in MNRAS. The 3 min summary: https://www.youtube.com/watch?v=mWUebbgUOh8

This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making the key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and yet it receives disproportionally low attention from the research community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research., Comment: Preprint

Streaming feature selection techniques have become essential in processing real-time data streams, as they facilitate the identification of the most relevant attributes from continuously updating information. Despite their performance, current algorithms to streaming feature selection frequently fall short in managing biases and avoiding discrimination that could be perpetuated by sensitive attributes, potentially leading to unfair outcomes in the resulting models. To address this issue, we propose FairSFS, a novel algorithm for Fair Streaming Feature Selection, to uphold fairness in the feature selection process without compromising the ability to handle data in an online manner. FairSFS adapts to incoming feature vectors by dynamically adjusting the feature set and discerns the correlations between classification attributes and sensitive attributes from this revised set, thereby forestalling the propagation of sensitive data. Empirical evaluations show that FairSFS not only maintains accuracy that is on par with leading streaming feature selection methods and existing fair feature techniques but also significantly improves fairness metrics., Comment: 30 pages, 10 figures

It is crucial to utilize events to understand a specific domain. There are lots of research on event extraction in many domains such as news, finance and biology domain. However, scientific domain still lacks event extraction research, including comprehensive datasets and corresponding methods. Compared to other domains, scientific domain presents two characteristics: denser nuggets and more complex events. To solve the above problem, considering these two characteristics, we first construct SciEvents, a large-scale multi-event document-level dataset with a schema tailored for scientific domain. It has 2,508 documents and 24,381 events under refined annotation and quality control. Then, we propose EXCEEDS, a novel end-to-end scientific event extraction framework by storing dense nuggets in a grid matrix and simplifying complex event extraction into a dot construction and connection task. Experimental results demonstrate state-of-the-art performances of EXCEEDS on SciEvents. Additionally, we release SciEvents and EXCEEDS on GitHub., Comment: This paper is working in process

We introduce an evidential model for time-to-event prediction with censored data. In this model, uncertainty on event time is quantified by Gaussian random fuzzy numbers, a newly introduced family of random fuzzy subsets of the real line with associated belief functions, generalizing both Gaussian random variables and Gaussian possibility distributions. Our approach makes minimal assumptions about the underlying time-to-event distribution. The model is fit by minimizing a generalized negative log-likelihood function that accounts for both normal and censored data. Comparative experiments on two real-world datasets demonstrate the very good performance of our model as compared to the state-of-the-art.

Face retouching aims to remove facial blemishes, such as pigmentation and acne, and still retain fine-grain texture details. Nevertheless, existing methods just remove the blemishes but focus little on realism of the intermediate process, limiting their use more to beautifying facial images on social media rather than being effective tools for simulating changes in facial pigmentation and ance. Motivated by this limitation, we propose our Controllable and Gradual Face Retouching (CGFR). Our CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space. Our CGFR offers a user-friendly control over the facial blemishes, achieving realistic and gradual blemishes retouching. Experimental results based on actual clinical data shows that CGFR can realistically simulate the blemishes' gradual recovering process., Comment: 7 pages, 6 figures. The paper has been accepted by the IEEE Conference on Multimedia Expo 2024

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages., Comment: This is a late posting of an old paper as Google Scholar somehow misses indexing the ACL anthology version of the paper

While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt -- significantly outperforms previous metrics such as CLIPScore. In addition, VQAScore can improve generation in a black-box manner (without finetuning) via simply ranking a few (3 to 9) candidate images. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward at improving human alignment ratings for DALL-E 3 and Stable Diffusion, especially on compositional prompts that require advanced visio-linguistic reasoning. We will release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt. Lastly, we discuss promising areas for improvement in VQAScore, such as addressing fine-grained visual details. We will release all human ratings (over 80,000) to facilitate scientific benchmarking of both generative models and automated metrics., Comment: We open-source our dataset, model, and code at: https://linzhiqiu.github.io/papers/genai_bench ; Project page: https://linzhiqiu.github.io/papers/genai_bench ; GenAI-Bench was first introduced in arxiv:2404.01291. This article extends it with an additional GenAI-Rank benchmark.

The remote sensing image intelligence understanding model is undergoing a new profound paradigm shift which has been promoted by multi-modal large language model (MLLM), i.e. from the paradigm learning a domain model (LaDM) shifts to paradigm learning a pre-trained general foundation model followed by an adaptive domain model (LaGD). Under the new LaGD paradigm, the old datasets, which have led to advances in RSI intelligence understanding in the last decade, are no longer suitable for fire-new tasks. We argued that a new dataset must be designed to lighten tasks with the following features: 1) Generalization: training model to learn shared knowledge among tasks and to adapt to different tasks; 2) Understanding complex scenes: training model to understand the fine-grained attribute of the objects of interest, and to be able to describe the scene with natural language; 3) Reasoning: training model to be able to realize high-level visual reasoning. In this paper, we designed a high-quality, diversified, and unified multimodal instruction-following dataset for RSI understanding produced by GPT-4V and existing datasets, which we called RS-GPT4V. To achieve generalization, we used a (Question, Answer) which was deduced from GPT-4V via instruction-following to unify the tasks such as captioning and localization; To achieve complex scene, we proposed a hierarchical instruction description with local strategy in which the fine-grained attributes of the objects and their spatial relationships are described and global strategy in which all the local information are integrated to yield detailed instruction descript; To achieve reasoning, we designed multiple-turn QA pair to provide the reasoning ability for a model. The empirical results show that the fine-tuned MLLMs by RS-GPT4V can describe fine-grained information. The dataset is available at: https://github.com/GeoX-Lab/RS-GPT4V., Comment: 14 pages, 6 figures, 4 tables

Generative artificial intelligence (AI) has brought revolutionary innovations in various fields, including medicine. However, it also exhibits limitations. In response, retrieval-augmented generation (RAG) provides a potential solution, enabling models to generate more accurate contents by leveraging the retrieval of external knowledge. With the rapid advancement of generative AI, RAG can pave the way for connecting this transformative technology with medical applications and is expected to bring innovations in equity, reliability, and personalization to health care.

While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in many real-world classification problems, existing LTSSL algorithms typically assume that the class distributions of labeled and unlabeled data are almost identical. Those LTSSL algorithms built upon the assumption can severely suffer when the class distributions of labeled and unlabeled data are mismatched since they utilize biased pseudo-labels from the model. To alleviate this problem, we propose a new simple method that can effectively utilize unlabeled data from unknown class distributions through Boosting cOnsistency in duAl Training (BOAT). Specifically, we construct the standard and balanced branch to ensure the performance of the head and tail classes, respectively. Throughout the training process, the two branches incrementally converge and interact with each other, eventually resulting in commendable performance across all classes. Despite its simplicity, we show that BOAT achieves state-of-the-art performance on a variety of standard LTSSL benchmarks, e.g., an averaged 2.7% absolute increase in test accuracy against existing algorithms when the class distributions of labeled and unlabeled data are mismatched. Even when the class distributions are identical, BOAT consistently outperforms many sophisticated LTSSL algorithms. We carry out extensive ablation studies to tease apart the factors that are the most important to the success of BOAT. The source code is available at https://github.com/Gank0078/BOAT.

This report presents our team's 'PCIE_EgoHandPose' solution for the EgoExo4D Hand Pose Challenge at CVPR2024. The main goal of the challenge is to accurately estimate hand poses, which involve 21 3D joints, using an RGB egocentric video image provided for the task. This task is particularly challenging due to the subtle movements and occlusions. To handle the complexity of the task, we propose the Hand Pose Vision Transformer (HP-ViT). The HP-ViT comprises a ViT backbone and transformer head to estimate joint positions in 3D, utilizing MPJPE and RLE loss function. Our approach achieved the 1st position in the Hand Pose challenge with 25.51 MPJPE and 8.49 PA-MPJPE. Code is available at https://github.com/KanokphanL/PCIE_EgoHandPose

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This paper investigates alignment techniques, including Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), to mitigate these risks. We conduct an empirical study on refusal patterns across nine LLMs, revealing that models with uniform refusal patterns, such as Claude3, exhibit higher security. Based on these findings, we propose self-distilling and cross-model distilling methods to enhance LLM security. Our results show that these methods significantly improve refusal rates and reduce unsafe content, with cross-model distilling achieving refusal rates close to Claude3's 94.51%. These findings underscore the potential of distillation-based alignment in securing LLMs against toxic prompts.

Conventional federated learning primarily aims to secure the privacy of data distributed across multiple edge devices, with the global model dispatched to edge devices for parameter updates during the learning process. However, the development of large language models (LLMs) requires substantial data and computational resources, rendering them valuable intellectual properties for their developers and owners. To establish a mechanism that protects both data and model privacy in a federated learning context, we introduce a method that just needs to distribute a quantized version of the model's parameters during training. This method enables accurate gradient estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one. Moreover, we combine this quantization strategy with LoRA, a popular and parameter-efficient fine-tuning method, to significantly reduce communication costs in federated learning. The proposed framework, named \textsc{FedLPP}, successfully ensures both data and model privacy in the federated learning context. Additionally, the learned central model exhibits good generalization and can be trained in a resource-efficient manner.

Tandem mass spectrometry has played a pivotal role in advancing proteomics, enabling the high-throughput analysis of protein composition in biological tissues. Many deep learning methods have been developed for \emph{de novo} peptide sequencing task, i.e., predicting the peptide sequence for the observed mass spectrum. However, two key challenges seriously hinder the further advancement of this important task. Firstly, since there is no consensus for the evaluation datasets, the empirical results in different research papers are often not comparable, leading to unfair comparison. Secondly, the current methods are usually limited to amino acid-level or peptide-level precision and recall metrics. In this work, we present the first unified benchmark NovoBench for \emph{de novo} peptide sequencing, which comprises diverse mass spectrum data, integrated models, and comprehensive evaluation metrics. Recent impressive methods, including DeepNovo, PointNovo, Casanovo, InstaNovo, AdaNovo and $\pi$-HelixNovo are integrated into our framework. In addition to amino acid-level and peptide-level precision and recall, we evaluate the models' performance in terms of identifying post-tranlational modifications (PTMs), efficiency and robustness to peptide length, noise peaks and missing fragment ratio, which are important influencing factors while seldom be considered. Leveraging this benchmark, we conduct a large-scale study of current methods, report many insightful findings that open up new possibilities for future development. The benchmark will be open-sourced to facilitate future research and application.

Text-to-image generation models often struggle with key element loss or semantic confusion in tasks involving Chinese classical poetry.Addressing this issue through fine-tuning models needs considerable training costs. Additionally, manual prompts for re-diffusion adjustments need professional knowledge. To solve this problem, we propose Poetry2Image, an iterative correction framework for images generated from Chinese classical poetry. Utilizing an external poetry dataset, Poetry2Image establishes an automated feedback and correction loop, which enhances the alignment between poetry and image through image generation models and subsequent re-diffusion modifications suggested by large language models (LLM). Using a test set of 200 sentences of Chinese classical poetry, the proposed method--when integrated with five popular image generation models--achieves an average element completeness of 70.63%, representing an improvement of 25.56% over direct image generation. In tests of semantic correctness, our method attains an average semantic consistency of 80.09%. The study not only promotes the dissemination of ancient poetry culture but also offers a reference for similar non-fine-tuning methods to enhance LLM generation., Comment: 13 pages, 7 figures

In the era of big data, access to abundant data is crucial for driving research forward. However, such data is often inaccessible due to privacy concerns or high costs, particularly in healthcare domain. Generating synthetic (tabular) data can address this, but existing models typically require substantial amounts of data to train effectively, contradicting our objective to solve data scarcity. To address this challenge, we propose a novel framework to generate synthetic tabular data, powered by large language models (LLMs) that emulates the architecture of a Generative Adversarial Network (GAN). By incorporating data generation process as contextual information and utilizing LLM as the optimizer, our approach significantly enhance the quality of synthetic data generation in common scenarios with small sample sizes. Our experimental results on public and private datasets demonstrate that our model outperforms several state-of-art models regarding generating higher quality synthetic data for downstream tasks while keeping privacy of the real data.

We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from multiview image input. L4GM outputs a per-frame 3D Gaussian Splatting representation from video frames sampled at a low fps and then upsamples the representation to a higher fps to achieve temporal smoothness. We add temporal self-attention layers to the base LGM to help it learn consistency across time, and utilize a per-timestep multiview rendering loss to train the model. The representation is upsampled to a higher framerate by training an interpolation model which produces intermediate 3D Gaussian representations. We showcase that L4GM that is only trained on synthetic data generalizes extremely well on in-the-wild videos, producing high quality animated 3D assets., Comment: Project page: https://research.nvidia.com/labs/toronto-ai/l4gm

Text-Attributed Graphs (TAGs) augment graph structures with natural language descriptions, facilitating detailed depictions of data and their interconnections across various real-world settings. However, existing TAG datasets predominantly feature textual information only at the nodes, with edges typically represented by mere binary or categorical attributes. This lack of rich textual edge annotations significantly limits the exploration of contextual relationships between entities, hindering deeper insights into graph-structured data. To address this gap, we introduce Textual-Edge Graphs Datasets and Benchmark (TEG-DB), a comprehensive and diverse collection of benchmark textual-edge datasets featuring rich textual descriptions on nodes and edges. The TEG-DB datasets are large-scale and encompass a wide range of domains, from citation networks to social networks. In addition, we conduct extensive benchmark experiments on TEG-DB to assess the extent to which current techniques, including pre-trained language models, graph neural networks, and their combinations, can utilize textual node and edge information. Our goal is to elicit advancements in textual-edge graph research, specifically in developing methodologies that exploit rich textual node and edge descriptions to enhance graph analysis and provide deeper insights into complex real-world networks. The entire TEG-DB project is publicly accessible as an open-source repository on Github, accessible at https://github.com/Zhuofeng-Li/TEG-Benchmark.

This paper addresses the problem of the optimal $H_2$ controller design for compartmental systems. In other words, we aim to enhance system robustness while maintaining the law of mass conservation. We perform a novel problem transformation and establish that the original problem is equivalent to an new optimization problem with a closed polyhedron constraint. Existing works have developed various first-order methods to tackle inequality constraints. However, the performance of the first-order method is limited in terms of convergence speed and precision, restricting its potential in practical applications. Therefore, developing a novel algorithm with fast speed and high precision is critical. In this paper, we reformulate the problem using log-barrier functions and introduce two separate approaches to address the problem: the first-order interior point method (FIPM) and the second-order interior point method (SIPM). We show they converge to a stationary point of the new problem. In addition, we propose an initialization method to guarantee the interior property of initial values. Finally, we compare FIPM and SIPM through a room temperature control example and show their pros and cons.

Searching for a unified scene representation remains a research challenge in computer graphics. Traditional mesh-based representations are unsuitable for dense, fuzzy elements, and introduce additional complexity for filtering and differentiable rendering. Conversely, voxel-based representations struggle to model hard surfaces and suffer from intensive memory requirement. We propose a general-purpose rendering primitive based on 3D Gaussian distribution for unified scene representation, featuring versatile appearance ranging from glossy surfaces to fuzzy elements, as well as physically based scattering to enable accurate global illumination. We formulate the rendering theory for the primitive based on non-exponential transport and derive efficient rendering operations to be compatible with Monte Carlo path tracing. The new representation can be converted from different sources, including meshes and 3D Gaussian splatting, and further refined via transmittance optimization thanks to its differentiability. We demonstrate the versatility of our representation in various rendering applications such as global illumination and appearance editing, while supporting arbitrary lighting conditions by nature. Additionally, we compare our representation to existing volumetric representations, highlighting its efficiency to reproduce details.

Video understanding is a pivotal task in the digital era, yet the dynamic and multievent nature of videos makes them labor-intensive and computationally demanding to process. Thus, localizing a specific event given a semantic query has gained importance in both user-oriented applications like video search and academic research into video foundation models. A significant limitation in current research is that semantic queries are typically in natural language that depicts the semantics of the target event. This setting overlooks the potential for multimodal semantic queries composed of images and texts. To address this gap, we introduce a new benchmark, ICQ, for localizing events in videos with multimodal queries, along with a new evaluation dataset ICQ-Highlight. Our new benchmark aims to evaluate how well models can localize an event given a multimodal semantic query that consists of a reference image, which depicts the event, and a refinement text to adjust the images' semantics. To systematically benchmark model performance, we include 4 styles of reference images and 5 types of refinement texts, allowing us to explore model performance across different domains. We propose 3 adaptation methods that tailor existing models to our new setting and evaluate 10 SOTA models, ranging from specialized to large-scale foundation models. We believe this benchmark is an initial step toward investigating multimodal queries in video event localization., Comment: 9 pages; fix some typos

Scattering probes the internal structure of quantum systems. We calculate the two-particle elastic scattering phase shift for a short-ranged interaction on a quantum computer. Short-ranged interactions with a large scattering length or shallow bound state describe a universality class that is of interest in atomic, condensed matter, nuclear, and particle physics. The phase shift is calculated by relating the ground state energy of the interacting particles in a harmonic trap. The relaxation method is used as the variational quantum eigensolver for the ground state calculation. Schmidt decomposition is used to reduce quantum circuits nominally requiring tens of qubits to 2-qubit circuits, thus reducing the noise in quantum measurements. Calculations in multi-particle systems with many-body interactions would benefit from this reduction of qubits in noisy quantum processors., Comment: 9 pages, 2 figures, 2 tables

We present EgoExo-Fitness, a new full-body action understanding dataset, featuring fitness sequence videos recorded from synchronized egocentric and fixed exocentric (third-person) cameras. Compared with existing full-body action understanding datasets, EgoExo-Fitness not only contains videos from first-person perspectives, but also provides rich annotations. Specifically, two-level temporal boundaries are provided to localize single action videos along with sub-steps of each action. More importantly, EgoExo-Fitness introduces innovative annotations for interpretable action judgement--including technical keypoint verification, natural language comments on action execution, and action quality scores. Combining all of these, EgoExo-Fitness provides new resources to study egocentric and exocentric full-body action understanding across dimensions of "what", "when", and "how well". To facilitate research on egocentric and exocentric full-body action understanding, we construct benchmarks on a suite of tasks (i.e., action classification, action localization, cross-view sequence verification, cross-view skill determination, and a newly proposed task of guidance-based execution verification), together with detailed analysis. Code and data will be available at https://github.com/iSEE-Laboratory/EgoExo-Fitness/tree/main., Comment: 33 pages, 9 figures

It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream tasks can further improve the similarity. However, it still remains unclear if this similarity can be used to optimize the pre-trained speech models. In this work, we therefore propose to use the brain activations recorded by fMRI to refine the often-used wav2vec2.0 model by aligning model representations toward human neural responses. Experimental results on SUPERB reveal that this operation is beneficial for several downstream tasks, e.g., speaker verification, automatic speech recognition, intent classification.One can then consider the proposed method as a new alternative to improve self-supervised speech models., Comment: accpeted by Interspeech2024

In this paper, we present a method using Deep Convolutional Neural Networks (DCNNs) to detect common glitches in video games. The problem setting consists of an image (800x800 RGB) as input to be classified into one of five defined classes, normal image, or one of four different kinds of glitches (stretched, low resolution, missing and placeholder textures). Using a supervised approach, we train a ShuffleNetV2 using generated data. This work focuses on detecting texture graphical anomalies achieving arguably good performance with an accuracy of 86.8\%, detecting 88\% of the glitches with a false positive rate of 8.7\%, and with the models being able to generalize and detect glitches even in unseen objects. We apply a confidence measure as well to tackle the issue with false positives as well as an effective way of aggregating images to achieve better detection in production. The main use of this work is the partial automatization of graphical testing in the final stages of video game development., Comment: 8 pages, 6 figures, AAIDE conference

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and human perception. In this paper, we focus on altering the voice attributes against machine recognition while retaining human perception. We referred to this as the asynchronous voice anonymization. To this end, a speech generation framework incorporating a speaker disentanglement mechanism is employed to generate the anonymized speech. The speaker attributes are altered through adversarial perturbation applied on the speaker embedding, while human perception is preserved by controlling the intensity of perturbation. Experiments conducted on the LibriSpeech dataset showed that the speaker attributes were obscured with their human perception preserved for 60.71% of the processed utterances., Comment: accpeted by Interspeech2024

Traversability estimation in off-road terrains is an essential procedure for autonomous navigation. However, creating reliable labels for complex interactions between the robot and the surface is still a challenging problem in learning-based costmap generation. To address this, we propose a method that predicts traversability costmaps by leveraging both visual and geometric information of the environment. To quantify the surface properties like roughness and bumpiness, we introduce a novel way of risk-aware labelling with proprioceptive information for network training. We validate our method in costmap prediction and navigation tasks for complex off-road scenarios. Our results demonstrate that our costmap prediction method excels in terms of average accuracy and MSE. The navigation results indicate that using our learned costmaps leads to safer and smoother driving, outperforming previous methods in terms of the highest success rate, lowest normalized trajectory length, lowest time cost, and highest mean stability across two scenarios.

This article studies the control ideas of the optimal backstepping technique, proposing an event-triggered optimal tracking control scheme for a class of strict-feedback nonlinear systems with non-affine and nonlinear faults. A simplified identifier-critic-actor framework is employed in the reinforcement learning algorithm to achieve optimal control. The identifier estimates the unknown dynamic functions, the critic evaluates the system performance, and the actor implements control actions, enabling modeling and control of anonymous systems for achieving optimal control performance. In this paper, a simplified reinforcement learning algorithm is designed by deriving update rules from the negative gradient of a simple positive function related to the Hamilton-Jacobi-Bellman equation, and it also releases the stringent persistent excitation condition. Then, a fault-tolerant control method is developed by applying filtered signals for controller design. Additionally, to address communication resource reduction, an event-triggered mechanism is employed for designing the actual controller. Finally, the proposed scheme's feasibility is validated through theoretical analysis and simulation.

In a 2016 paper, Straub proved an analogue to Euler's partition identity for partitions with fixed perimeter. Later, Fu and Tang provided a refinement and generalization of Straub's analogue to $d$-distinct partitions as well as a result related to the first Rogers-Ramanujan identity. Motivated by Alder-type partition identities and their generalizations, we build on work of Fu and Tang to establish generalized Alder-type partition inequalities in a fixed perimeter setting, and notably, a reverse Alder-type inequality., Comment: 13 pages

We uncover an underlying bias present in the audio recordings produced from the picture description task of the Pitt corpus, the largest publicly accessible database for Alzheimer's Disease (AD) detection research. Even by solely utilizing the silent segments of these audio recordings, we achieve nearly 100% accuracy in AD detection. However, employing the same methods to other datasets and preprocessed Pitt recordings results in typical levels (approximately 80%) of AD detection accuracy. These results demonstrate a Clever Hans effect in AD detection on the Pitt corpus. Our findings emphasize the crucial importance of maintaining vigilance regarding inherent biases in datasets utilized for training deep learning models, and highlight the necessity for a better understanding of the models' performance., Comment: Accepted by Interspeech 2024

This study employs cutting-edge wearable monitoring technology to conduct high-precision, high-temporal-resolution (1-second interval) cognitive load assessment on electroencephalogram (EEG) data from the FP1 channel and heart rate variability (HRV) data of secondary vocational students. By jointly analyzing these two critical physiological indicators, the research delves into their application value in assessing cognitive load among secondary vocational students and their utility across various tasks. The study designed two experiments to validate the efficacy of the proposed approach: Initially, a random forest classification model, developed using the N-BACK task, enabled the precise decoding of physiological signal characteristics in secondary vocational students under different levels of cognitive load, achieving a classification accuracy of 97%. Subsequently, this classification model was applied in a cross-task experiment involving the National Computer Rank Examination (Level-1), demonstrating the method's significant applicability and cross-task transferability in diverse learning contexts. Conducted with high portability, this research holds substantial theoretical and practical significance for optimizing teaching resource allocation in secondary vocational education, as well as for cognitive load assessment methods and monitoring. Currently, the research findings are undergoing trial implementation in the school.

We discuss the potential of future proton decay experiments on the exploration of the flavour space of grand unification. We focus on an economical SU(5) grand unified model (GUT) with the fermion sector extended by including only one copy of 24-plet. Neutrino masses are generated via type-(I+III) seesaw mechanism with the lightest neutrino massless. Gauge unification requires masses of fermions in the 24-plet to be hierarchical, in particular, the electroweak singlet and triplet heavy leptons to be around the canonical seesaw scale and TeV scale, respectively. We address how extra parameters in the flavour space which cannot be touched in flavour measurements can be tested by a multi-channel analysis in future proton decay measurements., Comment: 21 pages, 8 figures

We propose semidefinite trajectory optimization (STROM), a framework that computes fast and certifiably optimal solutions for nonconvex trajectory optimization problems defined by polynomial objectives and constraints. STROM employs sparse second-order Lasserre's hierarchy to generate semidefinite program (SDP) relaxations of trajectory optimization. Different from existing tools (e.g., YALMIP and SOSTOOLS in Matlab), STROM generates chain-like multiple-block SDPs with only positive semidefinite (PSD) variables. Moreover, STROM does so two orders of magnitude faster. Underpinning STROM is cuADMM, the first ADMM-based SDP solver implemented in CUDA and runs in GPUs. cuADMM builds upon the symmetric Gauss-Seidel ADMM algorithm and leverages GPU parallelization to speedup solving sparse linear systems and projecting onto PSD cones. In five trajectory optimization problems (inverted pendulum, cart-pole, vehicle landing, flying robot, and car back-in), cuADMM computes optimal trajectories (with certified suboptimality below 1%) in minutes (when other solvers take hours or run out of memory) and seconds (when others take minutes). Further, when warmstarted by data-driven initialization in the inverted pendulum problem, cuADMM delivers real-time performance: providing certifiably optimal trajectories in 0.66 seconds despite the SDP has 49,500 variables and 47,351 constraints.

Gamma-ray bursts (GRBs) are typically classified into long and short GRBs based on their durations. However, there is a significant overlapping in the duration distributions of these two categories. In this paper, we apply the unsupervised dimensionality reduction algorithm called t-SNE and UMAP to classify 2061 Fermi GRBs based on four observed quantities: duration, peak energy, fluence, and peak flux. The map results of t-SNE and UMAP show a clear division of these GRBs into two clusters. We mark the two clusters as GRBs-I and GRBs-II, and find that all GRBs associated with supernovae are classified as GRBs-II. It includes the peculiar short GRB 200826A, which was confirmed to originate from the death of a massive star. Furthermore, except for two extreme events GRB 211211A and GRB 230307A, all GRBs associated with kilonovae fall into GRBs-I population. By comparing to the traditional classification of short and long GRBs, the distribution of durations for GRBs-I and GRBs-II do not have a fixed boundary. We find that more than 10% of GRBs-I have a duration greater than 2 seconds, while approximately 1% of GRBs-II have a duration shorter than 2 seconds., Comment: 11 pages, 5 figures, revised version submitted to MNRAS

Motion-based controllable text-to-video generation involves motions to control the video generation. Previous methods typically require the training of models to encode motion cues or the fine-tuning of video diffusion models. However, these approaches often result in suboptimal motion generation when applied outside the trained domain. In this work, we propose MotionClone, a training-free framework that enables motion cloning from a reference video to control text-to-video generation. We employ temporal attention in video inversion to represent the motions in the reference video and introduce primary temporal-attention guidance to mitigate the influence of noisy or very subtle motions within the attention weights. Furthermore, to assist the generation model in synthesizing reasonable spatial relationships and enhance its prompt-following capability, we propose a location-aware semantic guidance mechanism that leverages the coarse location of the foreground from the reference video and original classifier-free guidance features to guide the video generation. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency., Comment: 17 pages, 12 figures, https://bujiazi.github.io/motionclone.github.io/

Large language models (LLMs) are possessed of numerous beneficial capabilities, yet their potential inclination harbors unpredictable risks that may materialize in the future. We hence propose CRiskEval, a Chinese dataset meticulously designed for gauging the risk proclivities inherent in LLMs such as resource acquisition and malicious coordination, as part of efforts for proactive preparedness. To curate CRiskEval, we define a new risk taxonomy with 7 types of frontier risks and 4 safety levels, including extremely hazardous,moderately hazardous, neutral and safe. We follow the philosophy of tendency evaluation to empirically measure the stated desire of LLMs via fine-grained multiple-choice question answering. The dataset consists of 14,888 questions that simulate scenarios related to predefined 7 types of frontier risks. Each question is accompanied with 4 answer choices that state opinions or behavioral tendencies corresponding to the question. All answer choices are manually annotated with one of the defined risk levels so that we can easily build a fine-grained frontier risk profile for each assessed LLM. Extensive evaluation with CRiskEval on a spectrum of prevalent Chinese LLMs has unveiled a striking revelation: most models exhibit risk tendencies of more than 40% (weighted tendency to the four risk levels). Furthermore, a subtle increase in the model's inclination toward urgent self-sustainability, power seeking and other dangerous goals becomes evident as the size of models increase. To promote further research on the frontier risk evaluation of LLMs, we publicly release our dataset at https://github.com/lingshi6565/Risk_eval., Comment: 28 pages, 5 figures

Patients with mental disorders often exhibit risky abnormal actions, such as climbing walls or hitting windows, necessitating intelligent video behavior monitoring for smart healthcare with the rising Internet of Things (IoT) technology. However, the development of vision-based Human Action Recognition (HAR) for these actions is hindered by the lack of specialized algorithms and datasets. In this paper, we innovatively propose to build a vision-based HAR dataset including abnormal actions often occurring in the mental disorder group and then introduce a novel Scene-Motion-aware Action Recognition Technology framework, named SMART, consisting of two technical modules. First, we propose a scene perception module to extract human motion trajectory and human-scene interaction features, which introduces additional scene information for a supplementary semantic representation of the above actions. Second, the multi-stage fusion module fuses the skeleton motion, motion trajectory, and human-scene interaction features, enhancing the semantic association between the skeleton motion and the above supplementary representation, thus generating a comprehensive representation with both human motion and scene information. The effectiveness of our proposed method has been validated on our self-collected HAR dataset (MentalHAD), achieving 94.9% and 93.1% accuracy in un-seen subjects and scenes and outperforming state-of-the-art approaches by 6.5% and 13.2%, respectively. The demonstrated subject- and scene- generalizability makes it possible for SMART's migration to practical deployment in smart healthcare systems for mental disorder patients in medical settings. The code and dataset will be released publicly for further research: https://github.com/Inowlzy/SMART.git.

The purpose of this study is to utilize the Chebyshev spectral method neural network(CSNN) model to solve differential equations. This approach employs a single-layer neural network wherein Chebyshev spectral methods are used to construct neurons satisfying boundary conditions. The study uses a feedforward neural network model and error backpropagation principles, utilizing automatic differentiation (AD) to compute the loss function. This method avoids the need to solve non-sparse linear systems, making it convenient for algorithm implementation and solving high-dimensional problems. The unique sampling method and neuron architecture significantly enhance the training efficiency and accuracy of the neural network. Furthermore, multiple networks enables the Chebyshev spectral method to handle equations on more complex domains. The numerical efficiency and accuracy of the CSNN model are investigated through testing on elliptic partial differential equations, and it is compared with the well-known Physics-Informed Neural Network(PINN) method.

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbers. To address these limitations, we propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion to precisely follow complex textual semantics by manipulating and composing the attention maps of denoising networks spatially and temporally. Moreover, we propose an enhanced video data preprocessing to enhance the training data regarding motion dynamics and prompt understanding, equipped with a new reference frame attention mechanism to improve the consistency of auto-regressive video generation. Extensive experiments demonstrate that our VideoTetris achieves impressive qualitative and quantitative results in compositional T2V generation. Code is available at: https://github.com/YangLing0818/VideoTetris, Comment: Code: https://github.com/YangLing0818/VideoTetris

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Notably, we find that our Llama3-8B+BoT has the potential to surpass Llama3-70B model. Our project is available at: https://github.com/YangLing0818/buffer-of-thought-llm, Comment: Project: https://github.com/YangLing0818/buffer-of-thought-llm

We present a novel multimodal neural network for classifying astronomical sources in multiband ground-based observations, from optical to near infrared, to separate sources in stars, galaxies and quasars. Our approach combines a convolutional neural network branch for learning morphological features from $r$-band images with an artificial neural network branch for extracting spectral energy distribution (SED) information. Specifically, we have used 9-band optical ($ugri$) and NIR ($ZYHJK_s$) data from the Kilo-Degree Survey (KiDS) Data Release 5. The two branches of the network are concatenated and feed into fully-connected layers for final classification. We train the network on a spectroscopically confirmed sample from the Sloan Digital Sky Survey cross-matched with KiDS. The trained model achieves 98.76\% overall accuracy on an independent testing dataset, with F1 scores exceeding 95\% for each class. Raising the output probability threshold, we obtain higher purity at the cost of a lower completeness. We have also validated the network using external catalogs cross-matched with KiDS, correctly classifying 99.74\% of a pure star sample selected from Gaia parallaxes and proper motions, and 99.74\% of an external galaxy sample from the Galaxy and Mass Assembly survey, adjusted for low-redshift contamination. We apply the trained network to 27,334,751 KiDS DR5 sources with $r \leqslant 23$ mag to generate a new classification catalog. This multimodal neural network successfully leverages both morphological and SED information to enable efficient and robust classification of stars, quasars, and galaxies in large photometric surveys., Comment: 18 pages, 12 figures, 2 tables, Submitted to ApJS

To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines., Comment: ACL2024 Findings

Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain representation and resulting in performance degradation on unseen domains. Besides, abundant data from multiple domains are needed. To address these issues, in this work, we propose prompt-based visual alignment (PVA), a robust framework to mitigate the detrimental domain bias in the image for zero-shot policy transfer. Inspired that Visual-Language Model (VLM) can serve as a bridge to connect both text space and image space, we leverage the semantic information contained in a text sequence as an explicit constraint to train a visual aligner. Thus, the visual aligner can map images from multiple domains to a unified domain and achieve good generalization performance. To better depict semantic information, prompt tuning is applied to learn a sequence of learnable tokens. With explicit constraints of semantic information, PVA can learn unified cross-domain representation under limited access to cross-domain data and achieves great zero-shot generalization ability in unseen domains. We verify PVA on a vision-based autonomous driving task with CARLA simulator. Experiments show that the agent generalizes well on unseen domains under limited access to multi-domain data., Comment: This paper has been accepted by ICML2024

The combination of double rotated serpentine springs (RSS) and vertical comb-drive is a suitbale solution for the development of torsional micromirror with high fill factor, low fabrication difficulty and good performance. However, the alignment error between upper and lower comb set caused by fabrication can induce force with unexpected direction. And the cross-axis coupled spring constants in double rotated serpentine springs (DRSSs) makes micromirror more susceptible to this alignment error. Herein, in order to minimize the unexpected deflection caused by alignment error of vertical-comb-driven micromirror, this paper, for the first time, studies the effect of layout (centrosymmetrically-arranged and axisymmetrically-arranged) of DRSSs on cross-axis coupled spring constants. Both of theoretical analysis and finite element analysis (FEA) simulation are conducted to reveal this phenomenon. With an example, centrosymmetrically-arranged DRSSs are proved to be more resistant to pull-in of two comb sets. Finally, the relationship between key structure parameters and cross-axis coupled spring constants of centrosymmetrically -arranged DRSSs are presented.

Predicting genetic mutations from whole slide images is indispensable for cancer diagnosis. However, existing work training multiple binary classification models faces two challenges: (a) Training multiple binary classifiers is inefficient and would inevitably lead to a class imbalance problem. (b) The biological relationships among genes are overlooked, which limits the prediction performance. To tackle these challenges, we innovatively design a Biological-knowledge enhanced PathGenomic multi-label Transformer to improve genetic mutation prediction performances. BPGT first establishes a novel gene encoder that constructs gene priors by two carefully designed modules: (a) A gene graph whose node features are the genes' linguistic descriptions and the cancer phenotype, with edges modeled by genes' pathway associations and mutation consistencies. (b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations. BPGT then designs a label decoder that finally performs genetic mutation prediction by two tailored modules: (a) A modality fusion module that firstly fuses the gene priors with critical regions in WSIs and obtains gene-wise mutation logits. (b) A comparative multi-label loss that emphasizes the inherent comparisons among mutation status to enhance the discrimination capabilities. Sufficient experiments on The Cancer Genome Atlas benchmark demonstrate that BPGT outperforms the state-of-the-art., Comment: 16 pages, 8 figures, and 3 tables

The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage speech BWE model named MS-BWE, which can handle a set of source and target sampling rate pairs and achieve flexible extensions of frequency bandwidth. The proposed MS-BWE model comprises a cascade of BWE blocks, with each block featuring a dual-stream architecture to realize amplitude and phase extension, progressively painting the speech frequency bands stage by stage. The teacher-forcing strategy is employed to mitigate the discrepancy between training and inference. Experimental results demonstrate that our proposed MS-BWE is comparable to state-of-the-art speech BWE methods in speech quality. Regarding generation efficiency, the one-stage generation of MS-BWE can achieve over one thousand times real-time on GPU and about sixty times on CPU., Comment: Accepted by Interspeech 2024