Search

The video topic segmentation (VTS) task segments videos into intelligible, non-overlapping topics, facilitating efficient comprehension of video content and quick access to specific content. VTS is also critical to various downstream video understanding tasks. Traditional VTS methods using shallow features or unsupervised approaches struggle to accurately discern the nuances of topical transitions. Recently, supervised approaches have achieved superior performance on video action or scene segmentation over unsupervised approaches. In this work, we improve supervised VTS by thoroughly exploring multimodal fusion and multimodal coherence modeling. Specifically, (1) we enhance multimodal fusion by exploring different architectures using cross-attention and mixture of experts. (2) To generally strengthen multimodality alignment and fusion, we pre-train and fine-tune the model with multimodal contrastive learning. (3) We propose a new pre-training task tailored for the VTS task, and a novel fine-tuning task for enhancing multimodal coherence modeling for VTS. We evaluate the proposed approaches on educational videos, in the form of lectures, due to the vital role of topic segmentation of educational videos in boosting learning experiences. Additionally, we introduce a large-scale Chinese lecture video dataset to augment the existing English corpus, promoting further research in VTS. Experiments on both English and Chinese lecture datasets demonstrate that our model achieves superior VTS performance compared to competitive unsupervised and supervised baselines.

We consider accelerating black holes in four-dimensional anti-de Sitter spacetime and investigate the extremality relations by examining perturbative corrections to both the entropy of black holes and their extremality bounds. It is shown that the so-called Goon and Penco (univeral) relation is also valid for accelerating black holes. Furthermore, it is found that an appropriate matching condition is necessary between the perturbation parameter of the relation with the perturbative correction to such black holes, and the parameter with information about the conical deficits on the north and south poles with the cosmic string tensions in order to satisfy the extremality relations. This result indicates that the extremality (univeral) relation of a class of accelerating black holes holds exhibit behavior similar to the Weak Gravity Conjecture., Comment: 5 pages, 2 figures, 1 table, typos corrected, version to appear in NPB

Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, compression rate, and efficiency, Palu further encompasses (1) a medium-grained low-rank decomposition scheme, (2) an efficient rank search algorithm, (3) low-rank-aware quantization compatibility enhancements, and (4) optimized GPU kernels with operators fusion. Extensive experiments with popular LLMs show that Palu compresses KV-Cache by 50% while maintaining strong accuracy and delivering up to 1.89x on the RoPE-based attention module. When combined with quantization, Palu's inherent quantization-friendly design yields small to negligible extra accuracy degradation while saving additional memory than quantization-only methods and achieving up to 2.91x speedup for the RoPE-based attention. Moreover, it maintains comparable or even better accuracy (up to 1.19 lower perplexity) compared to quantization-only methods. These results demonstrate Palu's superior capability to effectively address the efficiency and memory challenges of LLM inference posed by KV-Cache. Our code is publicly available at: https://github.com/shadowpa0327/Palu

Recently, with the rise of web images, managing and understanding large-scale image datasets has become increasingly important. Vision Large Language Models (VLLMs) have recently emerged due to their robust vision-understanding capabilities. However, training these models requires vast amounts of data, posing challenges to efficiency, effectiveness, data quality, and privacy. In this paper, we introduce SynthVLM, a novel data synthesis pipeline for VLLMs. Unlike existing methods that generate captions from images, SynthVLM employs advanced diffusion models and high-quality captions to automatically generate and select high-resolution images from captions, creating precisely aligned image-text pairs. Leveraging these pairs, we achieve state-of-the-art (SoTA) performance on various vision question answering tasks, maintaining high alignment quality and preserving advanced language abilities. Moreover, SynthVLM surpasses traditional GPT-4 Vision-based caption generation methods in performance while significantly reducing computational overhead. Crucially, our method's reliance on purely generated data ensures the preservation of privacy, achieving SoTA performance with just 100k data points (only 18% of the official dataset size).

Sufficient dimension reduction (SDR) is a valuable approach for handling high-dimensional data. Outer Product Gradient (OPG) is an popular approach. However, because of focusing the mean regression function, OPG may ignore some directions of central subspace (CS) when the distribution of errors is symmetric about zero. The mode of a distribution can provide an important summary of data. A Local Modal OPG (LMOPG) and its algorithm through mode regression are proposed to estimate the basis of CS with skew errors distribution. The estimator shows the consistent and asymptotic normal distribution under some mild conditions. Monte Carlo simulation is used to evaluate the performance and demonstrate the efficiency and robustness of the proposed method.

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

This paper introduces a Virtual Immunohistochemistry Multiplex staining (VIMs) model designed to generate multiple immunohistochemistry (IHC) stains from a single hematoxylin and eosin (H&E) stained tissue section. IHC stains are crucial in pathology practice for resolving complex diagnostic questions and guiding patient treatment decisions. While commercial laboratories offer a wide array of up to 400 different antibody-based IHC stains, small biopsies often lack sufficient tissue for multiple stains while preserving material for subsequent molecular testing. This highlights the need for virtual IHC staining. Notably, VIMs is the first model to address this need, leveraging a large vision-language single-step diffusion model for virtual IHC multiplexing through text prompts for each IHC marker. VIMs is trained on uniplex paired H&E and IHC images, employing an adversarial training module. Testing of VIMs includes both paired and unpaired image sets. To enhance computational efficiency, VIMs utilizes a pre-trained large latent diffusion model fine-tuned with small, trainable weights through the Low-Rank Adapter (LoRA) approach. Experiments on nuclear and cytoplasmic IHC markers demonstrate that VIMs outperforms the base diffusion model and achieves performance comparable to Pix2Pix, a standard generative model for paired image translation. Multiple evaluation methods, including assessments by two pathologists, are used to determine the performance of VIMs. Additionally, experiments with different prompts highlight the impact of text conditioning. This paper represents the first attempt to accelerate histopathology research by demonstrating the generation of multiple IHC stains from a single H&E input using a single model trained solely on uniplex data., Comment: Accepted to MICCAI Workshop 2024

In the present paper, we prove that all the quotient modules in $H^2(\mathbb D^2)$, associated to the finitely generated submodules containing a distinguished homogenous polynomial, are essentially normal, which is the first result on the essential normality of non-algebraic quotient modules in $H^2(\mathbb D^2)$. Moreover, we obtain the equivalence of the essential normality of a quotient module and the Hilbert-Schmidtness of its associated submodule in $H^2(\mathbb D^2)$, in the case that the submodule contains a distinguished homogenous polynomial. As an application, we prove that each finitely generated submodule containing a polynomial is Hilbert-Schmidt, which partially gives an affirmative answer to the conjecture of Yang \cite{Ya3}.

Mixed-frame formulations of radiation-hydrodynamics (RHD), where the radiation quantities are computed in an inertial frame but matter quantities are in a comoving frame, are advantageous because they admit algorithms that conserve energy and momentum to machine precision and combine more naturally with adaptive mesh techniques, since unlike pure comoving-frame methods they do not face the problem that radiation quantities must change frame every time a cell is refined or coarsened. However, implementing multigroup RHD in a mixed-frame formulation presents challenges due to the complexity of handling frequency-dependent interactions and the Doppler shift of radiation boundaries. In this paper, we introduce a novel method for multigroup RHD that integrates a mixed-frame formulation with a piecewise powerlaw approximation for frequency dependence within groups. This approach ensures the exact conservation of total energy and momentum while effectively managing the Lorentz transformation of group boundaries and evaluation of group-averaged opacities. Our method takes advantage of the locality of matter-radiation coupling, allowing the source term for $N_g$ frequency groups to be handled with simple equations with a sparse Jacobian matrix of size $N_g + 1$, which can be inverted with $O(N_g)$ complexity. This results in a computational complexity that scales linearly with $N_g$ and requires no more communication than a pure hydrodynamics update, making it highly efficient for massively parallel and GPU-based systems. We implement our method in the GPU-accelerated RHD code QUOKKA and demonstrate that it passes a wide range of numerical tests. We demonstrate that the piecewise powerlaw method shows significant advantages over traditional opacity averaging methods for handling rapidly variable opacities with modest frequency resolution., Comment: 17 pages, 8 figures, submitted to MNRAS. Comments are welcome. The code described in this article is available at: https://github.com/quokka-astro/quokka

This letter illustrates the opinion of the molecular dynamics (MD) community on the need to adopt a new FAIR paradigm for the use of molecular simulations. It highlights the necessity of a collaborative effort to create, establish, and sustain a database that allows findability, accessibility, interoperability, and reusability of molecular dynamics simulation data. Such a development would democratize the field and significantly improve the impact of MD simulations on life science research. This will transform our working paradigm, pushing the field to a new frontier. We invite you to support our initiative at the MDDB community (https://mddbr.eu/community/)

Motivated by applications in DNA-based data storage, constrained codes have attracted a considerable amount of attention from both academia and industry. We study the maximum cardinality of constrained codes for which the constraints can be characterized by a set of forbidden substrings, where by a substring we mean some consecutive coordinates in a string. For finite-type constrained codes (for which the set of forbidden substrings is finite), one can compute their capacity (code rate) by the ``spectral method'', i.e., by applying the Perron-Frobenious theorem to the de Brujin graph defined by the code. However, there was no systematic method to compute the exact cardinality of these codes. We show that there is a surprisingly powerful method arising from enumerative combinatorics, which is based on the Goulden-Jackson cluster theorem (previously not known to the coding community), that can be used to compute not only the capacity, but also the exact formula for the cardinality of these codes, for each fixed code length. Moreover, this can be done by solving a system of linear equations of size equal to the number of constraints. We also show that the spectral method and the cluster method are inherently related by establishing a direct connection between the spectral radius of the de Brujin graph used in the first method and the convergence radius of the generating function used in the second method. Lastly, to demonstrate the flexibility of the new method, we use it to give an explicit upper bound on the maximum cardinality of variable-length non-overlapping codes, which are a class of constrained codes defined by an infinite number of forbidden substrings., Comment: 21 pages

Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and requirements of product design. The unclear link between text input and image output further complicates their application. This work empirically investigates design space exploration strategies that can successfully yield product images that are feasible, novel, and aesthetic, which are three common goals in product design. Specifically, user actions within the global and local editing modes, including their time spent, prompt length, mono vs. multi-criteria prompts, and goal orientation of prompts, are analyzed. Key findings reveal the pivotal role of mono vs. multi-criteria and goal orientation of prompts in achieving specific design goals over time and prompt length. The study recommends prioritizing the use of multi-criteria prompts for feasibility and novelty during global editing, while favoring mono-criteria prompts for aesthetics during local editing. Overall, this paper underscores the nuanced relationship between the AI-driven text-to-image models and their effectiveness in product design, urging designers to carefully structure prompts during different editing modes to better meet the unique demands of product design., Comment: 12 pages, 7 figures

TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token usage), TaskGen uses StrictJSON that ensures JSON output from the Large Language Model (LLM), along with additional features such as type checking and iterative error correction. Key to the philosophy of TaskGen is the management of information/memory on a need-to-know basis. We empirically evaluate TaskGen on various environments such as 40x40 dynamic maze navigation with changing obstacle locations (100% solve rate), TextWorld escape room solving with dense rewards and detailed goals (96% solve rate), web browsing (69% of actions successful), solving the MATH dataset (71% solve rate over 100 Level-5 problems), Retrieval Augmented Generation on NaturalQuestions dataset (F1 score of 47.03%), Comment: 53 pages

Reconfigurable intelligent surfaces (RISs) have emerged as a promising technology in wireless communications. Simultaneously transmitting and reflecting RIS (STAR-RISs) in particular have garnered significant attention due to their dual capabilities of simultaneous transmission and reflection, underscoring their potential applications in critical scenarios within the forthcoming sixth-generation (6G) technology landscape. Moreover, full-duplex (FD) systems have emerged as a breakthrough research direction in wireless transmission technology due to their high spectral efficiency. This paper explores the application potential of STAR-RIS in FD systems for future wireless communications, presenting an innovative technology that provides robust self-interference cancellation (SIC) capabilities for FD systems. We utilize the refraction functionality of STAR-RIS enhances the transmission capacity of FD systems, while its reflection functionality is used to eliminate self interference within the FD system. We delve into the applications of two different types of STAR-RIS in FD systems and compare their performance through simulations. Furthermore, we discuss the performance differences of STAR-RIS empowered FD systems under various configurations in a case study, and demonstrate the superiority of the proposed deep learning-based optimization algorithm. Finally, we discuss possible future research directions for STAR-RIS empowered FD systems., Comment: Accepted for publication in IEEE Communications Standards Magazine

Virtual try-on methods based on diffusion models achieve realistic try-on effects but often replicate the backbone network as a ReferenceNet or use additional image encoders to process condition inputs, leading to high training and inference costs. In this work, we rethink the necessity of ReferenceNet and image encoders and innovate the interaction between garment and person by proposing CatVTON, a simple and efficient virtual try-on diffusion model. CatVTON facilitates the seamless transfer of in-shop or worn garments of any category to target persons by simply concatenating them in spatial dimensions as inputs. The efficiency of our model is demonstrated in three aspects: (1) Lightweight network: Only the original diffusion modules are used, without additional network modules. The text encoder and cross-attentions for text injection in the backbone are removed, reducing the parameters by 167.02M. (2) Parameter-efficient training: We identified the try-on relevant modules through experiments and achieved high-quality try-on effects by training only 49.57M parameters, approximately 5.51 percent of the backbone network's parameters. (3) Simplified inference: CatVTON eliminates all unnecessary conditions and preprocessing steps, including pose estimation, human parsing, and text input, requiring only a garment reference, target person image, and mask for the virtual try-on process. Extensive experiments demonstrate that CatVTON achieves superior qualitative and quantitative results with fewer prerequisites and trainable parameters than baseline methods. Furthermore, CatVTON shows good generalization in in-the-wild scenarios despite using open-source datasets with only 73K samples., Comment: 10 pages, 9 figures, 4 tables

Deep learning electronic structures from ab initio calculations holds great potential to revolutionize computational materials studies. While existing methods proved success in deep-learning density functional theory (DFT) Hamiltonian matrices, they are limited to DFT programs using localized atomic-like bases and heavily depend on the form of the bases. Here, we propose the DeepH-r method for deep-learning DFT Hamiltonians in real space, facilitating the prediction of DFT Hamiltonian in a basis-independent manner. An equivariant neural network architecture for modeling the real-space DFT potential is developed, targeting a more fundamental quantity in DFT. The real-space potential exhibits simplified principles of equivariance and enhanced nearsightedness, further boosting the performance of deep learning. When applied to evaluate the Hamiltonian matrix, this method significantly improved in accuracy, as exemplified in multiple case studies. Given the abundance of data in the real-space potential, this work may pave a novel pathway for establishing a ``large materials model" with increased accuracy.

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in real-world scenarios, labeled graph data can be limited or scarce. To address this issue, we focus on the problem of semi-supervised graph classification, which involves both supervised and unsupervised models learning from labeled and unlabeled data. In contrast to recent approaches that transfer the entire knowledge from the unsupervised model to the supervised one, we argue that an effective transfer should only retain the relevant semantics that align well with the supervised task. In this paper, we propose a novel framework named DisenSemi, which learns disentangled representation for semi-supervised graph classification. Specifically, a disentangled graph encoder is proposed to generate factor-wise graph representations for both supervised and unsupervised models. Then we train two models via supervised objective and mutual information (MI)-based constraints respectively. To ensure the meaningful transfer of knowledge from the unsupervised encoder to the supervised one, we further define an MI-based disentangled consistency regularization between two models and identify the corresponding rationale that aligns well with the current graph classification task. Experimental results on a range of publicly accessible datasets reveal the effectiveness of our DisenSemi., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS 2024)

Smart contract developers frequently seek solutions to developmental challenges on Q&A platforms such as Stack Overflow (SO). Although community responses often provide viable solutions, the embedded code snippets can also contain hidden vulnerabilities. Integrating such code directly into smart contracts may make them susceptible to malicious attacks. We conducted an online survey and received 74 responses from smart contract developers. The results of this survey indicate that the majority (86.4%) of participants do not sufficiently consider security when reusing SO code snippets. Despite the existence of various tools designed to detect vulnerabilities in smart contracts, these tools are typically developed for analyzing fully-completed smart contracts and thus are ineffective for analyzing typical code snippets as found on SO. We introduce SOChecker, the first tool designed to identify potential vulnerabilities in incomplete SO smart contract code snippets. SOChecker first leverages a fine-tuned Llama2 model for code completion, followed by the application of symbolic execution methods for vulnerability detection. Our experimental results, derived from a dataset comprising 897 code snippets collected from smart contract-related SO posts, demonstrate that SOChecker achieves an F1 score of 68.2%, greatly surpassing GPT-3.5 and GPT-4 (20.9% and 33.2% F1 Scores respectively). Our findings underscore the need to improve the security of code snippets from Q&A websites.

Text-to-video retrieval answers user queries through search by concepts and embeddings. Limited by the size of the concept bank and the amount of training data, answering queries in the wild is not always effective due to the out-of-vocabulary problem. Furthermore, neither concept-based nor embedding-based search can perform reasoning to consolidate the search results for complex queries mixed with logical and spatial constraints. To address these problems, we leverage large language models (LLM) to paraphrase the query by text-to-text (T2T), text-to-image (T2I), and image-to-text (I2T) transformations. These transformations rephrase abstract concepts into simple words to address the out-of-vocabulary problem. Furthermore, the complex relationship in a query can be decoupled into simpler sub-queries, yielding better retrieval performance when fusing the search results of these sub-queries. To address the LLM hallucination problem, this paper also proposes a novel consistency-based verification strategy to filter the paraphrased queries that are factually incorrect. Extensive experiments are conducted for ad-hoc video search and known-item search on the TRECVid datasets. We provide empirical insights into how traditionally difficult-to-answer queries can be resolved by query paraphrasing.

We propose an analytical approximation for the energy spectrum of the scalar induced gravitational waves (SIGWs) generated by a broken power-law power spectrum, and find that both the asymptotic power-law tails and the intermediate peak contribute distinct features to the SIGW spectrum. Moreover, the broken power-law power spectrum has abundant near-peak features and our results can be used as a near-peak approximation that covers a wide range of models. Our analytical approximation is useful in the rapid generation of the SIGW energy spectrum, which is beneficial for gravitational wave data analysis., Comment: 18 pages, 6 figures, first version

Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, including categories, ingredients, recipes, and ingredient-level nutritional information. Uni-Food is designed to provide a more holistic approach to food data analysis, thereby enhancing the performance and capabilities of LMMs in this domain. To mitigate the conflicts arising from multi-task supervision during fine-tuning of LMMs, we introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach. RoDE utilizes a diverse array of experts to address tasks of varying complexity, thereby facilitating the coordination of trainable parameters, i.e., it allocates more parameters for more complex tasks and, conversely, fewer parameters for simpler tasks. RoDE implements linear rectification union to refine the router's functionality, thereby enhancing the efficiency of sparse task allocation. These design choices endow RoDE with features that ensure GPU memory efficiency and ease of optimization. Our experimental results validate the effectiveness of our proposed approach in addressing the inherent challenges of food-related multitasking.

Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fundamentals, and global events)? These factors, which frequently influence trading behaviors, are critical elements in the quest for maximizing investors' profits. Our work attempts to solve this problem through large language model based agents. We have developed a multi-agent AI system called StockAgent, driven by LLMs, designed to simulate investors' trading behaviors in response to the real stock market. The StockAgent allows users to evaluate the impact of different external factors on investor trading and to analyze trading behavior and profitability effects. Additionally, StockAgent avoids the test set leakage issue present in existing trading simulation systems based on AI Agents. Specifically, it prevents the model from leveraging prior knowledge it may have acquired related to the test data. We evaluate different LLMs under the framework of StockAgent in a stock trading environment that closely resembles real-world conditions. The experimental results demonstrate the impact of key external factors on stock market trading, including trading behavior and stock price fluctuation rules. This research explores the study of agents' free trading gaps in the context of no prior knowledge related to market data. The patterns identified through StockAgent simulations provide valuable insights for LLM-based investment advice and stock recommendation. The code is available at https://github.com/MingyuJ666/Stockagent., Comment: 33 pages, 10 figures

We develop a nonparametric test for deciding whether volatility of an asset follows a standard semimartingale process, with paths of finite quadratic variation, or a rough process with paths of infinite quadratic variation. The test utilizes the fact that volatility is rough if and only if volatility increments are negatively autocorrelated at high frequencies. It is based on the sample autocovariance of increments of spot volatility estimates computed from high-frequency asset return data. By showing a feasible CLT for this statistic under the null hypothesis of semimartingale volatility paths, we construct a test with fixed asymptotic size and an asymptotic power equal to one. The test is derived under very general conditions for the data-generating process. In particular, it is robust to jumps with arbitrary activity and to the presence of market microstructure noise. In an application of the test to SPY high-frequency data, we find evidence for rough volatility.

Humanity has long sought inspiration from nature to innovate materials and devices. As science advances, nature-inspired materials are becoming part of our lives. Animate materials, characterized by their activity, adaptability, and autonomy, emulate properties of living systems. While only biological materials fully embody these principles, artificial versions are advancing rapidly, promising transformative impacts across various sectors. This roadmap presents authoritative perspectives on animate materials across different disciplines and scales, highlighting their interdisciplinary nature and potential applications in diverse fields including nanotechnology, robotics and the built environment. It underscores the need for concerted efforts to address shared challenges such as complexity management, scalability, evolvability, interdisciplinary collaboration, and ethical and environmental considerations. The framework defined by classifying materials based on their level of animacy can guide this emerging field encouraging cooperation and responsible development. By unravelling the mysteries of living matter and leveraging its principles, we can design materials and systems that will transform our world in a more sustainable manner.

The determination of the direction of a stellar core collapse via its neutrino emission is crucial for the identification of the progenitor for a multimessenger follow-up. A highly effective method of reconstructing supernova directions within the Deep Underground Neutrino Experiment (DUNE) is introduced. The supernova neutrino pointing resolution is studied by simulating and reconstructing electron-neutrino charged-current absorption on $^{40}$Ar and elastic scattering of neutrinos on electrons. Procedures to reconstruct individual interactions, including a newly developed technique called ``brems flipping'', as well as the burst direction from an ensemble of interactions are described. Performance of the burst direction reconstruction is evaluated for supernovae happening at a distance of 10 kpc for a specific supernova burst flux model. The pointing resolution is found to be 3.4 degrees at 68% coverage for a perfect interaction-channel classification and a fiducial mass of 40 kton, and 6.6 degrees for a 10 kton fiducial mass respectively. Assuming a 4% rate of charged-current interactions being misidentified as elastic scattering, DUNE's burst pointing resolution is found to be 4.3 degrees (8.7 degrees) at 68% coverage., Comment: 25 pages, 16 figures

This study sheds light on the imperative need to bolster safety and privacy measures in large language models (LLMs), such as GPT-4 and LLaMA-2, by identifying and mitigating their vulnerabilities through explainable analysis of prompt attacks. We propose Counterfactual Explainable Incremental Prompt Attack (CEIPA), a novel technique where we guide prompts in a specific manner to quantitatively measure attack effectiveness and explore the embedded defense mechanisms in these models. Our approach is distinctive for its capacity to elucidate the reasons behind the generation of harmful responses by LLMs through an incremental counterfactual methodology. By organizing the prompt modification process into four incremental levels: (word, sentence, character, and a combination of character and word) we facilitate a thorough examination of the susceptibilities inherent to LLMs. The findings from our study not only provide counterfactual explanation insight but also demonstrate that our framework significantly enhances the effectiveness of attack prompts., Comment: 23 pages, 6 figures

Person re-identification (ReID), as a crucial technology in the field of security, plays an important role in security detection and people counting. Current security and monitoring systems largely rely on visual information, which may infringe on personal privacy and be susceptible to interference from pedestrian appearances and clothing in certain scenarios. Meanwhile, the widespread use of routers offers new possibilities for ReID. This letter introduces a method using WiFi Channel State Information (CSI), leveraging the multipath propagation characteristics of WiFi signals as a basis for distinguishing different pedestrian features. We propose a two-stream network structure capable of processing variable-length data, which analyzes the amplitude in the time domain and the phase in the frequency domain of WiFi signals, fuses time-frequency information through continuous lateral connections, and employs advanced objective functions for representation and metric learning. Tested on a dataset collected in the real world, our method achieves 93.68% mAP and 98.13% Rank-1.

Shadow removal aims at restoring the image content within shadow regions, pursuing a uniform distribution of illumination that is consistent between shadow and non-shadow regions. {Comparing to other image restoration tasks, there are two unique challenges in shadow removal:} 1) The patterns of shadows are arbitrary, varied, and often have highly complex trace structures, making ``trace-less'' image recovery difficult. 2) The degradation caused by shadows is spatially non-uniform, resulting in inconsistencies in illumination and color between shadow and non-shadow areas. Recent developments in this field are primarily driven by deep learning-based solutions, employing a variety of learning strategies, network architectures, loss functions, and training data. Nevertheless, a thorough and insightful review of deep learning-based shadow removal techniques is still lacking. In this paper, we are the first to provide a comprehensive survey to cover various aspects ranging from technical details to applications. We highlight the major advancements in deep learning-based single-image shadow removal methods, thoroughly review previous research across various categories, and provide insights into the historical progression of these developments. Additionally, we summarize performance comparisons both quantitatively and qualitatively. Beyond the technical aspects of shadow removal methods, we also explore potential future directions for this field., Comment: url: https://github.com/GuoLanqing/Awesome-Shadow-Removal

Text-to-image generative models have increasingly been used to assist designers during concept generation in various creative domains, such as graphic design, user interface design, and fashion design. However, their applications in engineering design remain limited due to the models' challenges in generating images of feasible designs concepts. To address this issue, this paper introduces a method that improves the design feasibility by prompting the generation with feasible CAD images. In this work, the usefulness of this method is investigated through a case study with a bike design task using an off-the-shelf text-to-image model, Stable Diffusion 2.1. A diverse set of bike designs are produced in seven different generation settings with varying CAD image prompting weights, and these designs are evaluated on their perceived feasibility and novelty. Results demonstrate that the CAD image prompting successfully helps text-to-image models like Stable Diffusion 2.1 create visibly more feasible design images. While a general tradeoff is observed between feasibility and novelty, when the prompting weight is kept low around 0.35, the design feasibility is significantly improved while its novelty remains on par with those generated by text prompts alone. The insights from this case study offer some guidelines for selecting the appropriate CAD image prompting weight for different stages of the engineering design process. When utilized effectively, our CAD image prompting method opens doors to a wider range of applications of text-to-image models in engineering design., Comment: 11 pages, 3 figures, 4 tables

The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. However, although artificial intelligence technology has been widely used in many aspects of life, its application in social media content creation is still blank. To solve this problem, we propose a new prompt word generation framework based on multi-modal information fusion, which combines multiple tasks including topic classification, sentiment analysis, scene recognition and keyword extraction to generate more comprehensive prompt words. Subsequently, we use a template containing a set of prompt words to guide ChatGPT to generate high-quality tweets. Furthermore, in the absence of effective and objective evaluation criteria in the field of content generation, we use the ChatGPT tool to evaluate the results generated by the algorithm, making large-scale evaluation of content generation algorithms possible. Evaluation results on extensive content generation demonstrate that our cue word generation framework generates higher quality content compared to manual methods and other cueing techniques, while topic classification, sentiment analysis, and scene recognition significantly enhance content clarity and its consistency with the image., Comment: 8 pages, 5 figures

Object pose estimation plays a vital role in mixed-reality interactions when users manipulate tangible objects as controllers. Traditional vision-based object pose estimation methods leverage 3D reconstruction to synthesize training data. However, these methods are designed for static objects with diffuse colors and do not work well for objects that change their appearance during manipulation, such as deformable objects like plush toys, transparent objects like chemical flasks, reflective objects like metal pitchers, and articulated objects like scissors. To address this limitation, we propose Rocap, a robotic pipeline that emulates human manipulation of target objects while generating data labeled with ground truth pose information. The user first gives the target object to a robotic arm, and the system captures many pictures of the object in various 6D configurations. The system trains a model by using captured images and their ground truth pose information automatically calculated from the joint angles of the robotic arm. We showcase pose estimation for appearance-changing objects by training simple deep-learning models using the collected data and comparing the results with a model trained with synthetic data based on 3D reconstruction via quantitative and qualitative evaluation. The findings underscore the promising capabilities of Rocap.

The purpose of the study was to find the true comfort of the wearer by conceptualizing, formulating, and proving the relation between physiological and emotional parameters with clothing fit and fabric. A mixed-method research design was used, and the findings showed that physiological indicators such as heart rate are closely linked with user comfort. However, a significant change in emotional response indicated a definite relationship between different fabric and fit types. The research was conducted to discover the relation between true comfort parameters and clothing, which is unique to the field. The findings help us understand how fabric types and clothing fit types can affect physiological and emotional responses, providing the consumer with satisfactory clothing with the suitable properties needed.

Terahertz (THz) communications, ranging from 100 GHz to 10 THz, are envisioned as a promising technology for 6G and beyond wireless systems. As foundation of designing THz communications, channel modeling and characterization are crucial to scrutinize the potential of the new spectrum. However, current channel modeling and standardization heavily rely on measurements, which are both time-consuming and costly to obtain in the THz band. Here, we propose a Transfer learning enabled Transformer based Generative Adversarial Network (TT-GAN) for THz channel modeling. Specifically, as a fundamental building block, a GAN is exploited to generate channel parameters, which can substitute measurements. To greatly improve the accuracy, the first T, i.e., a transformer structure with a self-attention mechanism is incorporated in GAN. Still incurring errors compared with ground-truth measurement, the second T, i.e., a transfer learning is designed to solve the mismatch between the formulated network and measurement. The proposed TT-GAN can achieve high accuracy in channel modeling, while requiring only rather limited amount of measurement, which is a promising complementary of channel standardization that fundamentally differs from the current techniques that heavily rely on measurement., Comment: arXiv admin note: text overlap with arXiv:2306.06902

We investigate correlation-enhanced low temperature quantum thermometry. Recent studies have revealed that bath-induced correlations can enhance the low-temperature estimation precision even starting from an uncorrelated state. However, a comprehensive understanding of this enhancement remains elusive. Using the Ramsey interferometry protocol, we illustrate that the estimation precision of $N$ thermometers sparsely coupled to a common low-temperature bath can achieve the Heisenberg scaling in the low-temperature regime with only a $\pi/2$ rotation of the measurement axis, in contrast to the standard Ramsey scheme. This result is based on the assumption that interthermometer correlations are induced exclusively by low-frequency noise in the common bath, a condition achievable in practical experimental scenarios. The underlying physical mechanism is clarified, revealing that the Heisenberg scaling arises from the intrinsic nature of the temperature, which is associated solely with the fluctuation of thermal noise. In contrast to the paradigm of independent thermometers, our proposed scheme demonstrates a significant enhancement in precision for low-temperature measurement, making it suitable for precisely measuring the temperature of ultracold systems., Comment: 7 pages, 2 figures

Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current approaches can increase the diversity. Nevertheless, such sampling method could undermine the factuality in dialogue generation. In this study, to discover a solution for advancing creativity without relying on questionable randomness and to subtly reconcile the factuality and diversity within the source-grounded paradigm, a novel method named DoGe is proposed. DoGe can dynamically alternate between the utilization of internal parameter knowledge and external source knowledge based on the model's factual confidence. Extensive experiments on three widely-used datasets show that DoGe can not only enhance response diversity but also maintain factuality, and it significantly surpasses other various decoding strategy baselines.

Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement can be naturally fulfilled by leveraging transformer-based segmentation architecture due to its inherent ability to capture long-range dependencies and flexibility in handling different modalities. However, the inherent training issues of transformer-based methods, such as the low efficacy of cross-attention and unstable bipartite matching, can be amplified in AVS, particularly when the learned audio query does not provide a clear semantic clue. In this paper, we address these two issues with the new Class-conditional Prompting Machine (CPM). CPM improves the bipartite matching with a learning strategy combining class-agnostic queries with class-conditional queries. The efficacy of cross-modal attention is upgraded with new learning objectives for the audio, visual and joint modalities. We conduct experiments on AVS benchmarks, demonstrating that our method achieves state-of-the-art (SOTA) segmentation accuracy.

Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks: (1) The internal structures of spans are neglected, thus only the boundary tokens of spans are used for relation prediction and span recognition, thus hindering the model's expressiveness; (2) Long spans occupy a significant proportion in the SSA datasets, which further exacerbates the problem of internal structure neglect. In this paper, we treat the SSA task as a dependency parsing task on partially-observed dependency trees, regarding flat spans without determined tree annotations as latent subtrees to consider internal structures of spans. We propose a two-stage parsing method and leverage TreeCRFs with a novel constrained inside algorithm to model latent structures explicitly, which also takes advantages of joint scoring graph arcs and headed spans for global optimization and inference. Results of extensive experiments on five benchmark datasets reveal that our method performs significantly better than all previous bi-lexical methods, achieving new state-of-the-art.

This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice excels in multi-lingual voice generation, zero-shot in-context learning, cross-lingual voice cloning, and instruction-following capabilities. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub. By integrating these models with LLMs, FunAudioLLM enables applications such as speech-to-speech translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thereby pushing the boundaries of voice interaction technology. Demos are available at https://fun-audio-llm.github.io, and the code can be accessed at https://github.com/FunAudioLLM., Comment: Work in progress. Authors are listed in alphabetical order by family name

In this paper, we establish the existence of one solution for a Schr\"{o}dinger equation with jumping nonlinearities: $-\Delta u+V(x)u=f(x,u)$, $x\in \mathbb {R}^N$, and $u(x)\to 0$, $|x|\to +\infty$, where $V$ is a potential function on which we make hypotheses, and in particular allow $V$ which is unbounded below, and $f(x,u)=au^-+bu^++g(x,u)$. No restriction on $b$ is required, which implies that $f(x,s)s^{-1}$ may interfere with the essential spectrum of $ -\Delta+V$ for $s\to +\infty$. Using the truncation method and the Morse theory, we can compute critical groups of the corresponding functional at zero and infinity, then prove the existence of one negative solution.

Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important. Video Large Language Models (VideoLLMs) have emerged in recent years due to their strong video understanding capabilities. However, training and inference processes for VideoLLMs demand vast amounts of data, presenting significant challenges to data management, particularly regarding efficiency, robustness, and effectiveness. In this work, we present KeyVideoLLM, a text-video frame similarity-based keyframe selection method designed to manage VideoLLM data efficiently, robustly, and effectively. Specifically, KeyVideoLLM achieves a remarkable data compression rate of up to 60.9 times, substantially lowering disk space requirements, which proves its high efficiency. Additionally, it maintains a 100% selection success rate across all video formats and scales, enhances processing speed by up to 200 times compared to existing keyframe selection methods, and does not require hyperparameter tuning. Beyond its outstanding efficiency and robustness, KeyVideoLLM further improves model performance in video question-answering tasks during both training and inference stages. Notably, it consistently achieved the state-of-the-art (SoTA) experimental results on diverse datasets.

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video.

Python's dynamic typing system offers flexibility and expressiveness but can lead to type-related errors, prompting the need for automated type inference to enhance type hinting. While existing learning-based approaches show promising inference accuracy, they struggle with practical challenges in comprehensively handling various types, including complex generic types and (unseen) user-defined types. In this paper, we introduce TIGER, a two-stage generating-then-ranking (GTR) framework, designed to effectively handle Python's diverse type categories. TIGER leverages fine-tuned pre-trained code models to train a generative model with a span masking objective and a similarity model with a contrastive training objective. This approach allows TIGER to generate a wide range of type candidates, including complex generics in the generating stage, and accurately rank them with user-defined types in the ranking stage. Our evaluation on the ManyTypes4Py dataset shows TIGER's advantage over existing methods in various type categories, notably improving accuracy in inferring user-defined and unseen types by 11.2% and 20.1% respectively in Top-5 Exact Match. Moreover, the experimental results not only demonstrate TIGER's superior performance and efficiency, but also underscore the significance of its generating and ranking stages in enhancing automated type inference., Comment: Accepted by ICSE'25

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math., Comment: Work in progress

The electronic density of states (DOS) provides information regarding the distribution of electronic energy levels in a material, and can be used to approximate its optical and electronic properties and therefore guide computational material design. Given its usefulness and relative simplicity, it has been one of the first electronic properties used as target for machine-learning approaches going beyond interatomic potentials. A subtle but important point, well-appreciated in the condensed matter community but usually overlooked in the construction of data-driven models, is that for bulk configurations the absolute energy reference of single-particle energy levels is ill-defined. Only energy differences matter, and quantities derived from the DOS are typically independent on the absolute alignment. We introduce an adaptive scheme that optimizes the energy reference of each structure as part of the training process, and show that it consistently improves the quality of ML models compared to traditional choices of energy reference, for different classes of materials and different model architectures. On a practical level, we trace the improved performance to the ability of this self-aligning scheme to match the most prominent features in the DOS. More broadly, we believe that this work highlights the importance of incorporating insights into the nature of the physical target into the definition of the architecture and of the appropriate figures of merit for machine-learning models, that translate in better transferability and overall performance.

We propose a functional stochastic block model whose vertices involve functional data information. This new model extends the classic stochastic block model with vector-valued nodal information, and finds applications in real-world networks whose nodal information could be functional curves. Examples include international trade data in which a network vertex (country) is associated with the annual or quarterly GDP over certain time period, and MyFitnessPal data in which a network vertex (MyFitnessPal user) is associated with daily calorie information measured over certain time period. Two statistical tasks will be jointly executed. First, we will detect community structures of the network vertices assisted by the functional nodal information. Second, we propose computationally efficient variational test to examine the significance of the functional nodal information. We show that the community detection algorithms achieve weak and strong consistency, and the variational test is asymptotically chi-square with diverging degrees of freedom. As a byproduct, we propose pointwise confidence intervals for the slop function of the functional nodal information. Our methods are examined through both simulated and real datasets.

Deep learning models for medical image segmentation and object detection are becoming increasingly available as clinical products. However, as details are rarely provided about the training data, models may unexpectedly fail when cases differ from those in the training distribution. An approach allowing potential users to independently test the robustness of a model, treating it as a black box and using only a few cases from their own site, is key for adoption. To address this, a method to test the robustness of these models against CT image quality variation is presented. In this work we present this framework by demonstrating that given the same training data, the model architecture and data pre processing greatly affect the robustness of several frequently used segmentation and object detection methods to simulated CT imaging artifacts and degradation. Our framework also addresses the concern about the sustainability of deep learning models in clinical use, by considering future shifts in image quality due to scanner deterioration or imaging protocol changes which are not reflected in a limited local test dataset.

Observations of large amount of massive galaxies with relatively old populations found at high redshifts are challenging galaxy formation scenarios within standard cosmology. Precise determinations of the average age of these galaxies would be useful for the discussion of this problem. Here we carry out a better constraint of the age of 200 V-shaped SED non-AGN galaxies at redshifts $22.5$, we do not see a significant evolution of their average age, with all average ages of galaxies mostly remaining between 1 and 2 Gyr. Our research find that most massive galaxies ($\sim 10^{10} M_\odot$ ) are older (typically $>\sim 1$ Gyr old) and formed earlier than less massive galaxies in our sample., Comment: 8 pages, 8 figures, 1 table, accepted for publication in ApJ

In this paper, we derive decay estimates near isolated singularities of 3-dimensional (3d) Yang-Mills-Higgs fields defined on a fiber bundle, where the fiber space is a compact Riemannian manifold and the structure group is a connected compact Lie group. As an application, we obtain removable singularity theorems for 3d Yang-Mills-Higgs fields under different types of energy conditions, which generalizes classical removable singularity theorems for 3d Yang-Mills fields~\cite{S84,SS84} and 3d harmonic maps~\cite{L85}.

Document-level event extraction aims to extract structured event information from unstructured text. However, a single document often contains limited event information and the roles of different event arguments may be biased due to the influence of the information source. This paper addresses the limitations of traditional document-level event extraction by proposing the task of cross-document event extraction (CDEE) to integrate event information from multiple documents and provide a comprehensive perspective on events. We construct a novel cross-document event extraction dataset, namely CLES, which contains 20,059 documents and 37,688 mention-level events, where over 70% of them are cross-document. To build a benchmark, we propose a CDEE pipeline that includes 5 steps, namely event extraction, coreference resolution, entity normalization, role normalization and entity-role resolution. Our CDEE pipeline achieves about 72% F1 in end-to-end cross-document event extraction, suggesting the challenge of this task. Our work builds a new line of information extraction research and will attract new research attention., Comment: ACL2024(Findings)

Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This shortcoming leads to their underwhelming performance in determining coreference for the events where their argument information relies on long-distance dependencies. In light of these limitations, we propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. Subsequently, cross-document heterogeneous graphs are constructed and GAT is utilized to learn the representations of events. Finally, a pair scorer calculates the similarity between each pair of events and co-referred events can be recognized using standard clustering algorithm. Additionally, as the existing cross-document event coreference datasets are limited to English, we have developed a large-scale Chinese cross-document event coreference dataset to fill this gap, which comprises 53,066 event mentions and 4,476 clusters. After applying our model on the English and Chinese datasets respectively, it outperforms all baselines by large margins.