Search

Accurate lighting estimation is crucial for enhancing realism in virtual environments used in augmented reality, virtual reality, and film production, ensuring seamless integration of virtual objects into real-world scenes. While traditional far-field lighting representations, such as environment maps, face challenges in capturing near-field lighting nuances, recent advancements have leveraged deep learning and inverse rendering methods to predict per-pixel environment maps, volumes, or emitters. These techniques, though effective for tasks like object insertion, often either lack editability for dynamic lighting adjustments, or are hindered by high computational costs and ambiguities between reflection and emission. Here, we explore fast near-field lighting estimation from the perspective of point light position prediction. Specifically, we train a vision transformer as a regressor to predict point light position given a single observed image. We provide two alternatives to over-parameterize the target by representing point lights as rays corresponding to image patches, which is later jointly processed by a diffusion vision transformer, offering an editable and neural network-friendly representation. Our approach is trained and evaluated on a custom dataset derived from OpenRooms, featuring 259 scenes with diverse lighting conditions, to comprehensively assess our method's effectiveness. Quantitative and qualitative experiment results show that our representations outperform naive end-to-end model merely outputing 3D positions. The positions predicted by our models deviate from the ground truth by around 0.35 and 0.38 of the scene scale, in contrast to the naive position prediction method which achieves around 0.60, all trained on the first 200 scenes in our dataset.

Criticality metrics are not only essential for collision avoidance systems but also play a vital role for verification and validation of automated vehicles. With respect to the first application, criticality metrics should be real-time capable and applicable in various traffic situations. For the second application, holistic safety evaluation by criticality metrics is desired. However, existing criticality metrics hardly meet these two requirements. They are either only applicable in post-processing or only assess the safety of maneuvers in longitudinal direction. Therefore, we propose a new acceleration-based criticality metric, which is real-time capable and applicable in both longitudinal and lateral directions. The theory of the proposed criticality metric is introduced and the definition is explained according to different scenarios. A simulation platform is established to validate the criticality metric. The simulation results demonstrate that the proposed criticality metric takes all possible maneuvers into account when meeting a critical situation. Apart from the longitudinal behavior, the lateral behavior of automated vehicles can also be evaluated in real-time. Consequently, it has a wider application scope than other criticality metrics. To demonstrate its contribution to verification and validation of automated vehicles, we apply the criticality metric to a naturalistic driving dataset. The results prove that our criticality metric has a higher precision and recall than Time to Collision. Additionally, it combines the abilities of Time to Collision and Time Head Way to assess the safety of automated vehicles in the longitudinal direction. The proposed criticality metric is real-time capable and is suitable for different situations.

Cheng Wang,1,* Jiaoyang Pan,1,* Shaoqing Chen,2 Lin Qiu,1 Huaanzi Hu,1 Li Ji,3 Jianhao Wang,1 Wenjia Liu,4 Xinye Ni2 1School of Pharmacy, Changzhou University, Changzhou, Jiangsu Province, People’s Republic of China; 2Department of Radiology, The Affiliated Changzhou No. 2 People’s Hospital of Nanjing Medical University, Changzhou, Jiangsu Province, People’s Republic of China; 3Department of Otorhinolaryngology, The Affiliated Changzhou No. 2 People’s Hospital of Nanjing Medical University, Nanjing, Jiangsu Province, People’s Republic of China; 4Department of Gastroenterology, The Affiliated Changzhou No. 2 People’s Hospital of Nanjing Medical University, Changzhou, Jiangsu Province, People’s Republic of China*These authors contributed equally to this workCorrespondence: Wenjia Liu; Xinye Ni, Email 13813016290@126.com; nxy@njmu.edu.cnBackground: The in vivo barriers and multidrug resistance (MDR) are well recognized as great challenges for the fulfillment of antitumor effects of current drugs, which calls for the development of novel therapeutic agents and innovative drug delivery strategies. Nanodrug (ND) combining multiple drugs with distinct modes of action holes the potential to circumvent these challenges, while the introduction of photothermal therapy (PTT) can give further significantly enhanced efficacy in cancer therapy. However, facile preparation of ND which contains dual drugs and photothermal capability with effective cancer treatment ability has rarely been reported.Methods: In this study, we selected curcumin (Cur) and doxorubicin (Dox) as two model drugs for the creation of a cocktail ND (Cur-Dox ND). We utilized polyvinylpyrrolidone (PVP) as a stabilizer and regulator to prepare Cur-Dox ND in a straightforward one-pot method.Results: The size of the resulting Cur-Dox ND can be easily adjusted by tuning the charged ratios. It was noted that both loaded drugs in Cur-Dox ND can realize their functions in the same t

High power conversion efficiency (PCE) and mechanical robustness are prerequisites for wearable applications of organic solar cells (OSCs). However, stretchability of present active systems (i.e., crack-onset strain (COS) < 30%) should be improved. While introducing elastomers into active systems is considered a simple method for improving stretchability, the inclusion of elastomers typically results in a decrease in PCE of the OSC with a limited enhancement in the stretchability due to lack of interconnected electrical and mechanical pathways. In this study, it is developed efficient and intrinsically stretchable (IS)-OSCs with exceptional mechanical robustness, by constructing co-continuous networks of conjugated polymers (D18) and elastomers (SEBS) within active layers. It is demonstrated that the blend film with a specific ratio (40:60 w/w) of D18:SEBS is crucial for forming co-continuous structures, establishing well-connected mechanical and electrical channels. Consequently, D180.4:SEBS0.6/L8-BO OSCs achieve 16-times higher stretchability (COS = 126%) than the OSCs based on D18/L8-BO (COS = 8%), while achieving 4-times higher PCE (12.13%) compared to the OSCs based on SEBS-rich active layers (D180.2:SEBS0.8/L8-BO, PCE = 3.15%). Furthermore, D180.4:SEBS0.6-based IS-OSCs preserve 86 and 90% of original PCEs at 50% strain and after 200 stretching/releasing cycles with 15% strain, respectively, demonstrating the highest mechanical robustness among reported IS-OSCs.

Non-fused ring electron acceptors (NFREAs) potentially have lower synthetic costs than their fused counterparts. However, the low backbone planarity and the presence of bulky substituents adversely affect the crystallinity of NFREAs, impeding charge transport and the formation of bicontinuous morphology in organic solar cells. Here we show that a binary solvent system can individually control the crystallization and phase separation of the donor polymer (for example, D18) and the NFREA (for example, 2BTh-2F-C2). We select solvents such as chloroform and o-xylene that evaporate at different temperatures and rates and have different solubility for D18. Upon evaporation of chloroform, D18 starts to assemble into fibrils. Then, the evaporation of o-xylene induces the rapid formation of a fibril network that phase segregates 2BTh-2F-C2 into pure domains and leads to a bicontinuous morphology. The well-defined interpenetrating network morphology affords an efficiency of 19.02% on small-area cells and 17.28% on 1 cm2 devices.

Yu-Hang Cai,1,&ast; Cheng-Yu Wang,1,&ast; Yu-Bo Fang,1 Hong-Yu Ma,1 Yu-Qing Gao,1 Zhen Wang,2 Junzheng Wu,3 Han Lin,1 Hua-Cheng Liu1 1Department of Anesthesiology and Perioperative Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University; Key Laboratory of Pediatric Anesthesiology, Ministry of Education, Wenzhou Medical University; Key Laboratory of Anesthesiology of Zhejiang Province, Wenzhou Medical University, Wenzhou, Zhejiang, People’s Republic of China; 2Laboratory Medicine Center, Allergy Center, Department of Transfusion Medicine, Zhejiang Provincial People’s Hospital, Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, People’s Republic of China; 3Department of Anesthesiology, Cincinnati Children’s Hospital, Cincinnati, OH, 45229, USA&ast;These authors contributed equally to this workCorrespondence: Hua-Cheng Liu; Han Lin, Department of Anesthesiology and Perioperative Medicine, The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, 109 West Xueyuan Road, Wenzhou, 325000, People’s Republic of China, Tel +86-13957770577, Fax +86-577-88002925, Email huachengliu@163.com; nanlinhannansh@qq.comPurpose: Remimazolam, an ultra-short-acting and fast-metabolized sedative, has only been sporadically investigated in children. This study was performed to determine the beneficial effects of intranasal remimazolam or dexmedetomidine on preoperative anxiety in children undergoing general surgeries.Patients and Methods: Ninety children were randomly and equally assigned to Group R (intranasal remimazolam 1.5mg kg− 1), Group D (intranasal dexmedetomidine 2 mcg kg− 1), and Group C (intranasal distilled water). The primary outcomes were the preoperative anxiety scores using the modified Yale preoperative anxiety scale (m-Ypas). The secondary outcomes included the cooperation behaviour of intranasal drug application, preoperative sedation l

At a particular aquaculture facility in Zhangjiajie in China, the Chinese giant salamander (Andrias davidianus) exhibited analogous clinical manifestations, culminating in sequential mortalities. This study used rigorous aseptic sampling methods to isolate bacteria from the affected liver of salamanders to determine the causative agent behind the decline in amphibians. A bacterial pathogen was isolated from diseased A. davidianus, and the strain was named DN-3. This isolate was subjected to bacterial identification, antibiotic susceptibility assays, reinfection experiments, and biochemical profiling. The isolated bacterial strain was definitively identified as Acinetobacter schindleri using 16S rRNA sequence analysis and biochemical identification. Antibiotic susceptibility testing revealed that this isolate was susceptible to neomycin, macrolides, doxycycline, piperacillin, nitrofurantoin, and carbenicillin. Subsequent reinfection assays, in which varying concentrations of the bacterial inoculum were administered to healthy salamanders, confirmed that the pathogen elicited varying degrees of morbidity or mortality within an eight-day observation period. The median lethal dose (LD50) of A. schindleri DN-3 for A. davidianus was calculated to be 6.25×104 CFU/mL. This result supports the significant pathogenicity of the strain for A. davidianus. The findings of this study provide empirical insights into the clinical management and epidemiological control of diseases affecting A. davidianus.

Diversity, equity, and inclusion (DEI) stands as an integral component of any successful organization. Historically, society has overlooked and underplayed DEI matters, resulting in the underrepresentation of minority groups, including women and people of color. In the past decade, underrepresentation of women and other minority groups in the aviation workforce has received attention and raised concerns among industry stakeholders. To gain insight into the status of women in aviation, the authors analyzed the participation of females in aviation professions between 2016 and 2021. Data used in this study were retrieved from the 2023 U.S. Civil Airmen Statistics published by the Federal Aviation Administration (FAA). Descriptive and inferential statistical methods, including one-way analysis of variance (ANOVA), are used to analyze the trends and features of pilots and instructors holding different types of airmen certificates. The analysis delves into temporal, geographic, and age distributions. The temporal distributions reveal that the number and percentage of women in aviation professions have not significantly changed. From 2007 to 2021, female airline transport pilots (ATPs) marginally increased from 3.7% to 4.7%. Notably, there are statistically significant differences across the eight FAA regions, with the Alaskan region having the highest percentage of female pilots, instructors, and remote pilots, while the Central and Southwest regions exhibit the lowest percentages. In addition, a significant age-related disparity exists among female pilots, with a decline in female representation as the certification level advances. Given that the underrepresentation of women in aviation professions resulted from a mix of social, educational, organizational, and financial factors,; recognition, understanding, embracement, and advocating for DEI issues could ultimately lead to increased equality, and a positive impact on the ongoing workforce shortage in the aviation secto

Fluid antenna system (FAS) represents a new technology able to flexibly and instantaneously change the antenna position for optimizing wireless communication performance. The high-resolution adjustment of the antenna position is what makes FAS powerful in taking full advantage of the fading variation in space. To obtain the benefits of FAS but without the complication of implementing FAS, this letter considers a mobile receiver with several fixed-position antennas and employs a transformer-based signal prediction network to deduce the received signals at other positions. This is possible since the received signals are correlated in space. The outcome is an increased dimension multiple-input multiple-output (MIMO) receiver which can be interpreted as a virtual FAS with imaginary antennas. We evaluate the proposed system in multiuser channels and adopt regularized zeroforcing (RZF) in the virtual FAS to deal with the interference. Simulation results demonstrate that the proposed virtual FAS outperforms significantly the original fixed-position MIMO system. IEEE

Rapid growth in industrial sectors such as automotive and shipbuilding has highlighted the significance of strip casting technology to produce lightweight alloys, particularly aluminum alloys widely used in both industrial production and daily life. Twin-roll casting (TRC), as an economically and environmentally friendly method for slab/strip production and processing, has attracted significant interest from researchers. However, the development of TRC aluminum alloys faces many challenges due to limited understanding of microstructural characteristics and control mechanisms. To further enhance comprehension of TRC aluminum alloys, this article reviews the influencing parameters, control methods, and existing issues related to TRC sub-rapid solidification (SRS) microstructure. It firstly summarizes TRC equipment types and their solidification characteristics, followed by a detailed analysis on key parameters affecting the evolution of TRC microstructure including rolling speed, roll separation force (RSF), and heat transfer coefficient (HTC). Finally, solutions to TRC defects are summarized and evaluated alongside their underlying mechanisms. This article provides a comprehensive review of the characteristics and control mechanisms of TRC microstructure while offering valuable insights for the future production of high-quality TRC aluminum strips.

Criticality metrics are not only essential for collision avoidance systems but also play a vital role for verification and validation of automated vehicles. With respect to the first application, criticality metrics should be real-time capable and applicable in various traffic situations. For the second application, holistic safety evaluation by criticality metrics is desired. However, existing criticality metrics hardly meet these two requirements. They are either only applicable in post-processing or only assess the safety of maneuvers in longitudinal direction. Therefore, we propose a new acceleration-based criticality metric, which is real-time capable and applicable in both longitudinal and lateral directions. The theory of the proposed criticality metric is introduced and the definition is explained according to different scenarios. A simulation platform is established to validate the criticality metric. The simulation results demonstrate that the proposed criticality metric takes all possible maneuvers into account when meeting a critical situation. Apart from the longitudinal behavior, the lateral behavior of automated vehicles can also be evaluated in real-time. Consequently, it has a wider application scope than other criticality metrics. To demonstrate its contribution to verification and validation of automated vehicles, we apply the criticality metric to a naturalistic driving dataset. The results prove that our criticality metric has a higher precision and recall than Time to Collision. Additionally, it combines the abilities of Time to Collision and Time Head Way to assess the safety of automated vehicles in the longitudinal direction. The proposed criticality metric is real-time capable and is suitable for different situations.

Criticality metrics are not only essential for collision avoidance systems but also play a vital role for verification and validation of automated vehicles. With respect to the first application, criticality metrics should be real-time capable and applicable in various traffic situations. For the second application, holistic safety evaluation by criticality metrics is desired. However, existing criticality metrics hardly meet these two requirements. They are either only applicable in post-processing or only assess the safety of maneuvers in longitudinal direction. Therefore, we propose a new acceleration-based criticality metric, which is real-time capable and applicable in both longitudinal and lateral directions. The theory of the proposed criticality metric is introduced and the definition is explained according to different scenarios. A simulation platform is established to validate the criticality metric. The simulation results demonstrate that the proposed criticality metric takes all possible maneuvers into account when meeting a critical situation. Apart from the longitudinal behavior, the lateral behavior of automated vehicles can also be evaluated in real-time. Consequently, it has a wider application scope than other criticality metrics. To demonstrate its contribution to verification and validation of automated vehicles, we apply the criticality metric to a naturalistic driving dataset. The results prove that our criticality metric has a higher precision and recall than Time to Collision. Additionally, it combines the abilities of Time to Collision and Time Head Way to assess the safety of automated vehicles in the longitudinal direction. The proposed criticality metric is real-time capable and is suitable for different situations.

Shaoqing Chen,1,2 Cheng Wang,3 Yanyan Meng,1– 3 Pengyin Li,1– 3 Yiwen Pan,1– 3 Mu He,1,2 Xinye Ni1,2 1Department of Radiotherapy, the Affiliated Changzhou No. 2 People’s Hospital of Nanjing Medical University, Changzhou Medical Center, Nanjing Medical University, Changzhou, Jiangsu, 213003, People’s Republic of China; 2Jiangsu Province Engineering Research Center of Medical Physics, Changzhou, Jiangsu, 213003, People’s Republic of China; 3School of Pharmacy, Changzhou University, Changzhou, Jiangsu, 213164, People’s Republic of ChinaCorrespondence: Xinye Ni, Email nxy@njmu.edu.cnBackground: Radiation stimulates the secretion of tumor stroma and induces resistance, recurrence, and metastasis of stromal-vascular tumors during radiotherapy. The proliferation and activation of tumor-associated fibroblasts (TAFs) are important reasons for the production of tumor stroma. Telmisartan (Tel) can inhibit the proliferation and activation of TAFs (resting TAFs), which may promote radiosensitization. However, Tel has a poor water solubility.Methods: In this study, self-assembled telmisartan nanoparticles (Tel NPs) were prepared by aqueous solvent diffusion method to solve the insoluble problem of Tel and achieve high drug loading of Tel. Then, erythrocyte membrane (ECM) obtained by hypotonic lysis was coated on the surface of Tel NPs (ECM/Tel) for the achievement of in vivo long circulation and tumor targeting. Immunofluorescence staining, western blot and other biological techniques were used to investigate the effect of ECM/Tel on TAFs activation inhibition (resting effect) and mechanisms involved. The multicellular spheroids (MCSs) model and mouse breast cancer cells (4T1) were constructed to investigate the effect of ECM/Tel on reducing stroma secretion, alleviating hypoxia, and the corresponding promoting radiosensitization effect in vitro. A mouse orthotopic 4T1 breast cancer model was constructed to investigate the radiosensitizing effect of ECM/Tel on inhib

Criticality metrics are not only essential for collision avoidance systems but also play a vital role for verification and validation of automated vehicles. With respect to the first application, criticality metrics should be real-time capable and applicable in various traffic situations. For the second application, holistic safety evaluation by criticality metrics is desired. However, existing criticality metrics hardly meet these two requirements. They are either only applicable in post-processing or only assess the safety of maneuvers in longitudinal direction. Therefore, we propose a new acceleration-based criticality metric, which is real-time capable and applicable in both longitudinal and lateral directions. The theory of the proposed criticality metric is introduced and the definition is explained according to different scenarios. A simulation platform is established to validate the criticality metric. The simulation results demonstrate that the proposed criticality metric takes all possible maneuvers into account when meeting a critical situation. Apart from the longitudinal behavior, the lateral behavior of automated vehicles can also be evaluated in real-time. Consequently, it has a wider application scope than other criticality metrics. To demonstrate its contribution to verification and validation of automated vehicles, we apply the criticality metric to a naturalistic driving dataset. The results prove that our criticality metric has a higher precision and recall than Time to Collision. Additionally, it combines the abilities of Time to Collision and Time Head Way to assess the safety of automated vehicles in the longitudinal direction. The proposed criticality metric is real-time capable and is suitable for different situations.

Large language models (LLMs), in conjunction with various reasoning reinforcement methodologies, have demonstrated remarkable capabilities comparable to humans in fields such as mathematics, law, coding, common sense, and world knowledge. In this paper, we delve into the reasoning abilities of LLMs within complex human systems. We propose a novel reasoning framework, termed ``Mosaic Expert Observation Wall'' (MEOW) exploiting generative-agents-based simulation technique. In the MEOW framework, simulated data are utilized to train an expert model concentrating ``experience'' about a specific task in each independent time of simulation. It is the accumulated ``experience'' through the simulation that makes for an expert on a task in a complex human system. We conduct the experiments within a communication game that mirrors real-world security scenarios. The results indicate that our proposed methodology can cooperate with existing methodologies to enhance the reasoning abilities of LLMs in complex human systems.

Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB, LiDAR, or IMU data. However, solely using these modalities or a combination of them may not be adequate for HPE, particularly for complex and fast movements. For holistic human motion understanding, we present RELI11D, a high-quality multimodal human motion dataset involves LiDAR, IMU system, RGB camera, and Event camera. It records the motions of 10 actors performing 5 sports in 7 scenes, including 3.32 hours of synchronized LiDAR point clouds, IMU measurement data, RGB videos and Event steams. Through extensive experiments, we demonstrate that the RELI11D presents considerable challenges and opportunities as it contains many rapid and complex motions that require precise location. To address the challenge of integrating different modalities, we propose LEIR, a multimodal baseline that effectively utilizes LiDAR Point Cloud, Event stream, and RGB through our cross-attention fusion strategy. We show that LEIR exhibits promising results for rapid motions and daily motions and that utilizing the characteristics of multiple modalities can indeed improve HPE performance. Both the dataset and source code will be released publicly to the research community, fostering collaboration and enabling further exploration in this field., Comment: CVPR2024, Project website: http://www.lidarhumanmotion.net/reli11d

3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e., variations in point density) and incomplete training strategies. In this work, we propose a density-guided translator (DGT), which translates point density between domains, and integrates it into a two-stage self-training pipeline named DGT-ST. First, in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training, we employ the non-learnable DGT to bridge the domain gap at the input level. Second, to provide a well-initialized model for self-training, we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally, by leveraging the designs above, a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR $\rightarrow$ semanticKITTI and SynLiDAR $\rightarrow$ semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods, achieving 9.4$\%$ and 4.3$\%$ mIoU improvements, respectively. Code is available at \url{https://github.com/yuan-zm/DGT-ST}., Comment: CVPR2024

By adopting a more flexible definition of unlearning and adjusting the model distribution to simulate training without the targeted data, approximate machine unlearning provides a less resource-demanding alternative to the more laborious exact unlearning methods. Yet, the unlearning completeness of target samples-even when the approximate algorithms are executed faithfully without external threats-remains largely unexamined, raising questions about those approximate algorithms' ability to fulfill their commitment of unlearning during the lifecycle. In this paper, we introduce the task of Lifecycle Unlearning Commitment Management (LUCM) for approximate unlearning and outline its primary challenges. We propose an efficient metric designed to assess the sample-level unlearning completeness. Our empirical results demonstrate its superiority over membership inference techniques in two key areas: the strong correlation of its measurements with unlearning completeness across various unlearning tasks, and its computational efficiency, making it suitable for real-time applications. Additionally, we show that this metric is able to serve as a tool for monitoring unlearning anomalies throughout the unlearning lifecycle, including both under-unlearning and over-unlearning. We apply this metric to evaluate the unlearning commitments of current approximate algorithms. Our analysis, conducted across multiple unlearning benchmarks, reveals that these algorithms inconsistently fulfill their unlearning commitments due to two main issues: 1) unlearning new data can significantly affect the unlearning utility of previously requested data, and 2) approximate algorithms fail to ensure equitable unlearning utility across different groups. These insights emphasize the crucial importance of LUCM throughout the unlearning lifecycle. We will soon open-source our newly developed benchmark.

With the widespread popularity of internet celebrity marketing all over the world, short video production has gradually become a popular way of presenting products information. However, the traditional video production industry usually includes series of procedures as script writing, video filming in a professional studio, video clipping, special effects rendering, customized post-processing, and so forth. Not to mention that multilingual videos is not accessible for those who could not speak multilingual languages. These complicated procedures usually needs a professional team to complete, and this made short video production costly in both time and money. This paper presents an intelligent system that supports the automatic generation of talking avatar videos, namely Virbo. With simply a user-specified script, Virbo could use a deep generative model to generate a target talking videos. Meanwhile, the system also supports multimodal inputs to customize the video with specified face, specified voice and special effects. This system also integrated a multilingual customization module that supports generate multilingual talking avatar videos in a batch with hundreds of delicate templates and creative special effects. Through a series of user studies and demo tests, we found that Virbo can generate talking avatar videos that maintained a high quality of videos as those from a professional team while reducing the entire production costs significantly. This intelligent system will effectively promote the video production industry and facilitate the internet marketing neglecting of language barriers and cost challenges.

This paper investigates a reconfigurable intelligent surface (RIS)-aided wideband massive multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system with low-resolution analog-to-digital converters (ADCs). Frequency-selective Rician fading channels are considered, and the OFDM data transmission process is presented in time domain. This paper derives the closed-form approximate expression of the uplink achievable rate, based on which the asymptotic system performance is analyzed when the number of the antennas at the base station and the number of reflecting elements at the RIS grow to infinity. Besides, the power scaling laws of the considered system are revealed to provide energy-saving insights. Furthermore, this paper proposes a gradient ascent-based algorithm to design the phase shifts of the RIS for maximizing the minimum user rate. Finally, numerical results are presented to verify the correctness of analytical conclusions and draw insights.

LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals. Previous research has attempted to address this by simulating the noise from rain to improve the robustness of detection models. However, significant disparities exist between simulated and actual rain-impacted data points. In this work, we propose a novel rain simulation method, termed DRET, that unifies Dynamics and Rainy Environment Theory to provide a cost-effective means of expanding the available realistic rain data for 3D detection training. Furthermore, we present a Sunny-to-Rainy Knowledge Distillation (SRKD) approach to enhance 3D detection under rainy conditions. Extensive experiments on the WaymoOpenDataset large-scale dataset show that, when combined with the state-of-the-art DSVT model and other classical 3D detectors, our proposed framework demonstrates significant detection accuracy improvements, without losing efficiency. Remarkably, our framework also improves detection capabilities under sunny conditions, therefore offering a robust solution for 3D detection regardless of whether the weather is rainy or sunny, Comment: Accepted by AAAI2024

Despite numerous completed studies, achieving high fidelity talking face generation with highly synchronized lip movements corresponding to arbitrary audio remains a significant challenge in the field. The shortcomings of published studies continue to confuse many researchers. This paper introduces G4G, a generic framework for high fidelity talking face generation with fine-grained intra-modal alignment. G4G can reenact the high fidelity of original video while producing highly synchronized lip movements regardless of given audio tones or volumes. The key to G4G's success is the use of a diagonal matrix to enhance the ordinary alignment of audio-image intra-modal features, which significantly increases the comparative learning between positive and negative samples. Additionally, a multi-scaled supervision module is introduced to comprehensively reenact the perceptional fidelity of original video across the facial region while emphasizing the synchronization of lip movements and the input audio. A fusion network is then used to further fuse the facial region and the rest. Our experimental results demonstrate significant achievements in reenactment of original video quality as well as highly synchronized talking lips. G4G is an outperforming generic framework that can produce talking videos competitively closer to ground truth level than current state-of-the-art methods.

Based upon two overlapped, body-unfitted meshes, a type of unified-field monolithic fictitious domain-finite element method (UFMFD-FEM) is developed in this paper for moving interface problems of dynamic fluid-structure interactions (FSI) accompanying with high-contrast physical coefficients across the interface and contacting collisions between the structure and fluidic channel wall when the structure is immersed in the fluid. In particular, the proposed novel numerical method consists of a monolithic, stabilized mixed finite element method within the frame of fictitious domain/immersed boundary method (IBM) for generic fluid-structure-contact interaction (FSCI) problems in the Eulerian-updated Lagrangian description, while involving the no-slip type of interface conditions on the fluid-structure interface, and the repulsive contact force on the structural surface when the immersed structure contacts the fluidic channel wall. The developed UFMFD-FEM for FSI or FSCI problems can deal with the structural motion with large rotational and translational displacements and/or large deformation in an accurate and efficient fashion, which are first validated by two benchmark FSI problems and one FSCI model problem, then by experimental results of a realistic FSCI scenario -- the microfluidic deterministic lateral displacement (DLD) problem that is applied to isolate circulating tumor cells (CTCs) from blood cells in the blood fluid through a cascaded filter DLD microchip in practice, where a particulate fluid with the pillar obstacles effect in the fluidic channel, i.e., the effects of fluid-structure interaction and structure collision, play significant roles to sort particles (cells) of different sizes with tilted pillar arrays., Comment: 32 pages, 42 figures, 5 tables, 66 references

Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixture-of-Experts augmented Low-Rank Adaptation for Lifelong Learning. MoRAL combines the multi-tasking abilities of MoE with the fine-tuning abilities of LoRA for effective life-long learning of LLMs. In contrast to the conventional approaches that use factual triplets as inputs MoRAL relies on simple question-answer pairs, which is a more practical and effective strategy for robust and efficient learning. Owing to new data settings, we introduce a new evaluation benchmark namely: Life Long Learning of LLM (5L-bench) encompassing a newly curated dataset of question-answer pairs, and a set of evaluation metrics for rigorous evaluation of MoRAL in open-book and closed-book settings. Experimental evaluation shows (i) LLMs learn fast in open-book settings with up to 30.15% improvement in "RA" for Phi-2-2.7B compared to closed-book (for models fine-tuned with MoRAL); (ii) MoRAL shows higher performance improvement for models with a greater number of parameters; (iii) MoRAL is robust to catastrophic forgetting offering better knowledge retention compared to baselines.

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate models for different scene types and are impractical when the scene type is unknown in advance. One of the underlying problems is the limited scalability of existing data construction pipelines, which limits the diversity of standard image matching datasets. To address this problem, we propose GIM, a self-training framework for learning a single generalizable model based on any image matching architecture using internet videos, an abundant and diverse data source. Given an architecture, GIM first trains it on standard domain-specific datasets and then combines it with complementary matching methods to create dense labels on nearby frames of novel videos. These labels are filtered by robust fitting, and then enhanced by propagating them to distant frames. The final model is trained on propagated data with strong augmentations. We also propose ZEB, the first zero-shot evaluation benchmark for image matching. By mixing data from diverse domains, ZEB can thoroughly assess the cross-domain generalization performance of different methods. Applying GIM consistently improves the zero-shot performance of 3 state-of-the-art image matching architectures; with 50 hours of YouTube videos, the relative zero-shot performance improves by 8.4%-18.1%. GIM also enables generalization to extreme cross-domain data such as Bird Eye View (BEV) images of projected 3D point clouds (Fig. 1(c)). More importantly, our single zero-shot model consistently outperforms domain-specific baselines when evaluated on downstream tasks inherent to their respective domains. The video presentation is available at https://www.youtube.com/watch?v=FU_MJLD8LeY., Comment: Accepted to ICLR 2024 for spotlight presentation

Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, inscrutable AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a modular framework called SafeX to integrate these contributions, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data consumption. We seek to understand the tradeoffs associated with data selection routines based on (i) expensive-to-compute data-quality estimates, and (ii) maximization of coverage and diversity-based measures in the feature space. Our first technique, Ask-LLM, leverages the zero-shot reasoning capabilities of instruction-tuned LLMs to directly assess the quality of a training example. To target coverage, we propose Density sampling, which models the data distribution to select a diverse sample. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories. Coverage sampling can recover the performance of the full data, while models trained on Ask-LLM data consistently outperform full-data training -- even when we reject 90% of the original dataset, while converging up to 70% faster., Comment: Under review. 44 pages, 30 figures

Command and control (C2) channels are an essential component of many types of cyber attacks, as they enable attackers to remotely control their malware-infected machines and execute harmful actions, such as propagating malicious code across networks, exfiltrating confidential data, or initiating distributed denial of service (DDoS) attacks. Identifying these C2 channels is therefore crucial in helping to mitigate and prevent cyber attacks. However, identifying C2 channels typically involves a manual process, requiring deep knowledge and expertise in cyber operations. In this paper, we propose a reinforcement learning (RL) based approach to automatically emulate C2 attack campaigns using both the normal (public) and the Tor networks. In addition, payload size and network firewalls are configured to simulate real-world attack scenarios. Results on a typical network configuration show that the RL agent can automatically discover resilient C2 attack paths utilizing both Tor-based and conventional communication channels, while also bypassing network firewalls.

The upcoming sixth generation (6G) wireless communication network is envisioned to cover space, air, and maritime areas, in addition to urban-centered terrestrial coverage by the fifth generation (5G) network, to support intelligent Internet of Things (IoT). Towards this end, we investigate structured integration of satellites, unmanned aerial vehicles (UAVs), and terrestrial networks, aiming to serve future universal IoT possibly with a massive number of devices in the coverage holes of current 5G. The hybrid satellite-UAV-terrestrial network usually leads to high system complexity, due to the heterogeneity and dynamics of space/air/ground links. With a systematic thinking, we propose to create and exploit hierarchies for the integrated network. Four basic structures are discussed by learning from the synergies in our human body. To orchestrate multiple heterogeneous basic structures, we further propose a process-oriented on-demand coverage method, which characterizes the system behavior as a series of events over time and is able to tackle the system complexity elaborately. We also outline open issues for promoting the agility and intelligence of structured satellite-UAV-terrestrial networks in the making.

In this paper, we provide a detailed theoretical analysis of the numerical scheme introduced in J. Comput. Phys. 436 (2021) 110253 for the reaction kinetics of a class of chemical reaction networks that satisfies detailed balance condition. In contrast to conventional numerical approximations, which are typically constructed based on ordinary differential equations (ODEs) for the concentrations of all involved species, the scheme is developed using the equations of reaction trajectories, which can be viewed as a generalized gradient flow of physically relevant free energy. The unique solvability, positivity-preserving, and energy-stable properties are proved for the general case involving multiple reactions, under a mild condition on the stoichiometric matrix., Comment: 10 pages, 1 figure

The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Here we demonstrate a hypermultiplexed integrated tensor optical processor (HITOP) that performs trillions of operations per second (TeraOPS) at the energy cost of 25 femtojoule per operation (25 fJ/OP). Based on space-time-wavelength three-dimensional (3D) data streaming, HITOP is built with arrays of wafer-fabricated III/V-based micron-scale lasers (spanning ~1 THz) incorporating thin-film Lithium-Niobate electro-optic (EO) photonics. Multidimensional parallelism allows matrix-matrix multiplications ($N^{3}$ operations) using $O(N)$ devices, facilitating scalable on-chip integration. With each device activating 10 billion parameters per second, the HITOP scalability is validated in machine learning models with 405,000 parameters, which is 25,000 times more than previous integrated optical systems. A combination of high clockrates (10 GS/s), parallel processing and real-time reprogrammability unlocks the full potential of light for next-generation AI accelerators in applications ranging from training with trillions of parameters, real-time decision making in autonomous vehicles and robotics, dynamic optimization in smart manufacturing, to complex simulation for climate modeling and drug discovery.

In this paper, we provide a theoretical analysis for a preconditioned steepest descent (PSD) iterative solver that improves the computational time of a finite difference numerical scheme for the Cahn-Hilliard equation with Flory-Huggins energy potential. In the numerical design, a convex splitting approach is applied to the chemical potential such that the logarithmic and the surface diffusion terms are treated implicitly while the expansive concave term is treated with an explicit update. The nonlinear and singular nature of the logarithmic energy potential makes the numerical implementation very challenging. However, the positivity-preserving property for the logarithmic arguments, unconditional energy stability, and optimal rate error estimates have been established in a recent work and it has been shown that successful solvers ensure a similar positivity-preserving property at each iteration stage. Therefore, in this work, we will show that the PSD solver ensures a positivity-preserving property at each iteration stage. The PSD solver consists of first computing a search direction (involved with solving a Poisson-like equation) and then takes a one-parameter optimization step over the search direction in which the Newton iteration becomes very powerful. A theoretical analysis is applied to the PSD iteration solver and a geometric convergence rate is proved for the iteration. In particular, the strict separation property of the numerical solution, which indicates a uniform distance between the numerical solution and the singular limit values of $\pm 1$ for the phase variable, plays an essential role in the iteration convergence analysis. A few numerical results are presented to demonstrate the robustness and efficiency of the PSD solver., Comment: 25 pages, 3 figures, 1 table

We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL). This problem is driven by the right to be forgotten and the privacy challenges in FL. We introduce a new framework for exact federated unlearning that meets two essential criteria: \textit{communication efficiency} and \textit{exact unlearning provability}. To our knowledge, this is the first work to tackle both aspects coherently. We start by giving a rigorous definition of \textit{exact} federated unlearning, which guarantees that the unlearned model is statistically indistinguishable from the one trained without the deleted data. We then pinpoint the key property that enables fast exact federated unlearning: total variation (TV) stability, which measures the sensitivity of the model parameters to slight changes in the dataset. Leveraging this insight, we develop a TV-stable FL algorithm called \texttt{FATS}, which modifies the classical \texttt{\underline{F}ed\underline{A}vg} algorithm for \underline{T}V \underline{S}tability and employs local SGD with periodic averaging to lower the communication round. We also design efficient unlearning algorithms for \texttt{FATS} under two settings: client-level and sample-level unlearning. We provide theoretical guarantees for our learning and unlearning algorithms, proving that they achieve exact federated unlearning with reasonable convergence rates for both the original and unlearned models. We empirically validate our framework on 6 benchmark datasets, and show its superiority over state-of-the-art methods in terms of accuracy, communication cost, computation cost, and unlearning efficacy.

In wireless communications, electromagnetic theory and information theory constitute a pair of fundamental theories, bridged by antenna theory and wireless propagation channel modeling theory. Up to the fifth generation (5G) wireless communication networks, these four theories have been developing relatively independently. However, in sixth generation (6G) space-air-ground-sea wireless communication networks, seamless coverage is expected in the three-dimensional (3D) space, potentially necessitating the acquisition of channel state information (CSI) and channel capacity calculation at anywhere and any time. Additionally, the key 6G technologies such as ultra-massive multiple-input multiple-output (MIMO) and holographic MIMO achieves intricate interaction of the antennas and wireless propagation environments, which necessitates the joint modeling of antennas and wireless propagation channels. To address the challenges in 6G, the integration of the above four theories becomes inevitable, leading to the concept of the so-called electromagnetic information theory (EIT). In this article, a suite of 6G key technologies is highlighted. Then, the concepts and relationships of the four theories are unveiled. Finally, the necessity and benefits of integrating them into the EIT are revealed.

As artificial intelligence becomes increasingly prevalent in scientific research, data-driven methodologies appear to overshadow traditional methods in resolving scientific problems. In this Perspective, we revisit a classic classification of scientific problems and rethink the evolution of scientific paradigms from the standpoint of data, algorithms, and computational power. We observe that the strengths of new paradigms have expanded the range of resolvable scientific problems, but the continued advancement of data, algorithms, and computational power is unlikely to bring a new paradigm. To tackle unresolved problems of organised complexity in more intricate systems, we argue that the integration of paradigms is a promising approach. Consequently, we propose behavioural rehearsing, checking what will happen in such systems through multiple times of simulation. One of the methodologies to realise it, sophisticated behavioural simulation (SBS), represents a higher level of paradigms integration based on foundational models to simulate complex social systems involving sophisticated human strategies and behaviours. SBS extends beyond the capabilities of traditional agent-based modelling simulation (ABMS), and therefore, makes behavioural rehearsing a potential solution to problems of organised complexity in complex human systems.

Command and control (C2) paths for issuing commands to malware are sometimes the only indicators of its existence within networks. Identifying potential C2 channels is often a manually driven process that involves a deep understanding of cyber tradecraft. Efforts to improve discovery of these channels through using a reinforcement learning (RL) based approach that learns to automatically carry out C2 attack campaigns on large networks, where multiple defense layers are in place serves to drive efficiency for network operators. In this paper, we model C2 traffic flow as a three-stage process and formulate it as a Markov decision process (MDP) with the objective to maximize the number of valuable hosts whose data is exfiltrated. The approach also specifically models payload and defense mechanisms such as firewalls which is a novel contribution. The attack paths learned by the RL agent can in turn help the blue team identify high-priority vulnerabilities and develop improved defense strategies. The method is evaluated on a large network with more than a thousand hosts and the results demonstrate that the agent can effectively learn attack paths while avoiding firewalls., Comment: SoutheastCon 2023. IEEE, 2023

Crystal structure prediction (CSP) has made significant progress, but most methods focus on unconditional generations of inorganic crystal with limited atoms in the unit cell. This study introduces XtalNet, the first equivariant deep generative model for end-to-end CSP from Powder X-ray Diffraction (PXRD). Unlike previous methods that rely solely on composition, XtalNet leverages PXRD as an additional condition, eliminating ambiguity and enabling the generation of complex organic structures with up to 400 atoms in the unit cell. XtalNet comprises two modules: a Contrastive PXRD-Crystal Pretraining (CPCP) module that aligns PXRD space with crystal structure space, and a Conditional Crystal Structure Generation (CCSG) module that generates candidate crystal structures conditioned on PXRD patterns. Evaluation on two MOF datasets (hMOF-100 and hMOF-400) demonstrates XtalNet's effectiveness. XtalNet achieves a top-10 Match Rate of 90.2% and 79% for hMOF-100 and hMOF-400 datasets in conditional crystal structure prediction task, respectively. XtalNet represents a significant advance in CSP, enabling the prediction of complex structures from PXRD data without the need for external databases or manual intervention. It has the potential to revolutionize PXRD analysis. It enables the direct prediction of crystal structures from experimental measurements, eliminating the need for manual intervention and external databases. This opens up new possibilities for automated crystal structure determination and the accelerated discovery of novel materials.

Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network's edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, Artificial Intelligence (AI) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this paper we comprehensively provide a survey of security and privacy in MEC from the perspective of AI. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our based framework while merging the Software Defined Network (SDN) and Network Function Virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI. Finally, we comprehensively discuss the opportunities and challenges associated with applying AI to MEC security and privacy as possible future research directions., Comment: Accepted at IEEE IoTJ

This paper proposes a second-order accurate numerical scheme for the Patlak-Keller-Segel system with various mobilities for the description of chemotaxis. Formulated in a variational structure, the entropy part is novelly discretized by a modified Crank-Nicolson approach so that the solution to the proposed nonlinear scheme corresponds to a minimizer of a convex functional. A careful theoretical analysis reveals that the unique solvability and positivity-preserving property could be theoretically justified. More importantly, such a second order numerical scheme is able to preserve the dissipative property of the original energy functional, instead of a modified one. To the best of our knowledge, the proposed scheme is the first second-order accurate one in literature that could achieve both the numerical positivity and original energy dissipation. In addition, an optimal rate convergence estimate is provided for the proposed scheme, in which rough and refined error estimate techniques have to be included to accomplish such an analysis. Ample numerical results are presented to demonstrate robust performance of the proposed scheme in preserving positivity and original energy dissipation in blowup simulations.

U-Net has become a cornerstone in various visual applications such as image segmentation and diffusion probability models. While numerous innovative designs and improvements have been introduced by incorporating transformers or MLPs, the networks are still limited to linearly modeling patterns as well as the deficient interpretability. To address these challenges, our intuition is inspired by the impressive results of the Kolmogorov-Arnold Networks (KANs) in terms of accuracy and interpretability, which reshape the neural network learning via the stack of non-linear learnable activation functions derived from the Kolmogorov-Anold representation theorem. Specifically, in this paper, we explore the untapped potential of KANs in improving backbones for vision tasks. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. Rigorous medical image segmentation benchmarks verify the superiority of U-KAN by higher accuracy even with less computation cost. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures. These endeavours unveil valuable insights and sheds light on the prospect that with U-KAN, you can make strong backbone for medical image segmentation and generation. Project page: https://yes-ukan.github.io

Federated Learning (FL) stands to gain significant advantages from collaboratively training capacity-heterogeneous models, enabling the utilization of private data and computing power from low-capacity devices. However, the focus on personalizing capacity-heterogeneous models based on client-specific data has been limited, resulting in suboptimal local model utility, particularly for low-capacity clients. The heterogeneity in both data and device capacity poses two key challenges for model personalization: 1) accurately retaining necessary knowledge embedded within reduced submodels for each client, and 2) effectively sharing knowledge through aggregating size-varying parameters. To this end, we introduce Pa3dFL, a novel framework designed to enhance local model performance by decoupling and selectively sharing knowledge among capacity-heterogeneous models. First, we decompose each layer of the model into general and personal parameters. Then, we maintain uniform sizes for the general parameters across clients and aggregate them through direct averaging. Subsequently, we employ a hyper-network to generate size-varying personal parameters for clients using learnable embeddings. Finally, we facilitate the implicit aggregation of personal parameters by aggregating client embeddings through a self-attention module. We conducted extensive experiments on three datasets to evaluate the effectiveness of Pa3dFL. Our findings indicate that Pa3dFL consistently outperforms baseline methods across various heterogeneity settings. Moreover, Pa3dFL demonstrates competitive communication and computation efficiency compared to baseline approaches, highlighting its practicality and adaptability in adverse system conditions.

Collaborative fairness stands as an essential element in federated learning to encourage client participation by equitably distributing rewards based on individual contributions. Existing methods primarily focus on adjusting gradient allocations among clients to achieve collaborative fairness. However, they frequently overlook crucial factors such as maintaining consistency across local models and catering to the diverse requirements of high-contributing clients. This oversight inevitably decreases both fairness and model accuracy in practice. To address these issues, we propose FedSAC, a novel Federated learning framework with dynamic Submodel Allocation for Collaborative fairness, backed by a theoretical convergence guarantee. First, we present the concept of "bounded collaborative fairness (BCF)", which ensures fairness by tailoring rewards to individual clients based on their contributions. Second, to implement the BCF, we design a submodel allocation module with a theoretical guarantee of fairness. This module incentivizes high-contributing clients with high-performance submodels containing a diverse range of crucial neurons, thereby preserving consistency across local models. Third, we further develop a dynamic aggregation module to adaptively aggregate submodels, ensuring the equitable treatment of low-frequency neurons and consequently enhancing overall model accuracy. Extensive experiments conducted on three public benchmarks demonstrate that FedSAC outperforms all baseline methods in both fairness and model accuracy. We see this work as a significant step towards incentivizing broader client participation in federated learning. The source code is available at https://github.com/wangzihuixmu/FedSAC., Comment: Accepted by KDD'24

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on cases where the data, including concepts, are clean. In many scenarios, we always need to remove/insert some training data or new concepts from trained CBMs due to different reasons, such as privacy concerns, data mislabelling, spurious concepts, and concept annotation errors. Thus, the challenge of deriving efficient editable CBMs without retraining from scratch persists, particularly in large-scale applications. To address these challenges, we propose Editable Concept Bottleneck Models (ECBMs). Specifically, ECBMs support three different levels of data removal: concept-label-level, concept-level, and data-level. ECBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for re-training. Experimental results demonstrate the efficiency and effectiveness of our ECBMs, affirming their adaptability within the realm of CBMs., Comment: 33 pages

Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, however, leading to suboptimal performance due to insufficient tuning and inevitable error accumulations of gradients. In this paper, we propose Federated Proxy Fine-Tuning (FedPFT), a novel method enhancing FMs adaptation in downstream tasks through FL by two key modules. First, the sub-FM construction module employs a layer-wise compression approach, facilitating comprehensive FM fine-tuning across all layers by emphasizing those crucial neurons. Second, the sub-FM alignment module conducts a two-step distillations-layer-level and neuron-level-before and during FL fine-tuning respectively, to reduce error of gradient by accurately aligning sub-FM with FM under theoretical guarantees. Experimental results on seven commonly used datasets (i.e., four text and three vision) demonstrate the superiority of FedPFT., Comment: Accepted by IJCAI'24

During endovascular interventions, physicians have to perform accurate and immediate operations based on the available real-time information, such as the shape and position of guidewires observed on the fluoroscopic images, haptic information and the patients' physiological signals. For this purpose, real-time and accurate guidewire segmentation and tracking can enhance the visualization of guidewires and provide visual feedback for physicians during the intervention as well as for robot-assisted interventions. Nevertheless, this task often comes with the challenge of elongated deformable structures that present themselves with low contrast in the noisy fluoroscopic image sequences. To address these issues, a two-stage deep learning framework for real-time guidewire segmentation and tracking is proposed. In the first stage, a Yolov5s detector is trained, using the original X-ray images as well as synthetic ones, which is employed to output the bounding boxes of possible target guidewires. More importantly, a refinement module based on spatiotemporal constraints is incorporated to robustly localize the guidewire and remove false detections. In the second stage, a novel and efficient network is proposed to segment the guidewire in each detected bounding box. The network contains two major modules, namely a hessian-based enhancement embedding module and a dual self-attention module. Quantitative and qualitative evaluations on clinical intra-operative images demonstrate that the proposed approach significantly outperforms our baselines as well as the current state of the art and, in comparison, shows higher robustness to low quality images.

In this article we present a refined convergence analysis for a second order accurate in time, fourth order finite difference numerical scheme for the 3-D Cahn-Hilliard equation, with an improved convergence constant. A modified backward differentiation formula temporal discretization is applied, and a Douglas-Dupont artificial regularization is included to ensure the energy stability. In fact, a standard application of discrete Gronwall inequality leads to a convergence constant dependent on the interface width parameter in an exponential singular form. We aim to obtain an improved estimate, with such a singular dependence only in a polynomial order. A uniform in time functional bounds of the numerical solution, including the higher order Sobolev norms, as well as the associated bounds for the first and second order temporal difference stencil, have to be carefully established. Certain recursive analysis has to be applied in the analysis for the BDF-style temporal stencil. As a result, we are able to apply a spectrum estimate for the linearized Cahn-Hilliard operator, and this technique leads to the refined error estimate. A three-dimensional numerical example of accuracy check is presented as well.

The unique solvability and error analysis of the original Lagrange multiplier approach proposed in [8] for gradient flows is studied in this paper. We identify a necessary and sufficient condition that must be satisfied for the nonlinear algebraic equation arising from the original Lagrange multiplier approach to admit a unique solution in the neighborhood of its exact solution, and propose a modified Lagrange multiplier approach so that the computation can continue even if the aforementioned condition is not satisfied. Using Cahn-Hilliard equation as an example, we prove rigorously the unique solvability and establish optimal error estimates of a second-order Lagrange multiplier scheme assuming this condition and that the time step is sufficient small. We also present numerical results to demonstrate that the modified Lagrange multiplier approach is much more robust and can use much larger time step than the original Lagrange multiplier approach.

We present an optimal rate convergence analysis for a second order accurate in time, fully discrete finite difference scheme for the Cahn-Hilliard-Navier-Stokes (CHNS) system, combined with logarithmic Flory-Huggins energy potential. The numerical scheme has been recently proposed, and the positivity-preserving property of the logarithmic arguments, as well as the total energy stability, have been theoretically justified. In this paper, we rigorously prove second order convergence of the proposed numerical scheme, in both time and space. Since the CHNS is a coupled system, the standard $\ell^\infty (0, T; \ell^2) \cap \ell^2 (0, T; H_h^2)$ error estimate could not be easily derived, due to the lack of regularity to control the numerical error associated with the coupled terms. Instead, the $\ell^\infty (0, T; H_h^1) \cap \ell^2 (0, T; H_h^3)$ error analysis for the phase variable and the $\ell^\infty (0, T; \ell^2)$ analysis for the velocity vector, which shares the same regularity as the energy estimate, is more suitable to pass through the nonlinear analysis for the error terms associated with the coupled physical process. Furthermore, the highly nonlinear and singular nature of the logarithmic error terms makes the convergence analysis even more challenging, since a uniform distance between the numerical solution and the singular limit values of is needed for the associated error estimate. Many highly non-standard estimates, such as a higher order asymptotic expansion of the numerical solution (up to the third order accuracy in time and fourth order in space), combined with a rough error estimate (to establish the maximum norm bound for the phase variable), as well as a refined error estimate, have to be carried out to conclude the desired convergence result.

Combining millimetre-wave (mmWave) communications with an extremely large-scale antenna array (ELAA) presents a promising avenue for meeting the spectral efficiency demands of the future sixth generation (6G) mobile communications. However, beam training for mmWave ELAA systems is challenged by excessive pilot overheads as well as insufficient accuracy, as the huge near-field codebook has to be accounted for. In this paper, inspired by the similarity between far-field sub-6 GHz channels and near-field mmWave channels, we propose to leverage sub-6 GHz uplink pilot signals to directly estimate the optimal near-field mmWave codeword, which aims to reduce pilot overhead and bypass the channel estimation. Moreover, we adopt deep learning to perform this dual mapping function, i.e., sub-6 GHz to mmWave, far-field to near-field, and a novel neural network structure called NMBEnet is designed to enhance the precision of beam training. Specifically, when considering the orthogonal frequency division multiplexing (OFDM) communication scenarios with high user density, correlations arise both between signals from different users and between signals from different subcarriers. Accordingly, the convolutional neural network (CNN) module and graph neural network (GNN) module included in the proposed NMBEnet can leverage these two correlations to further enhance the precision of beam training.

The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD., Comment: Accepted by CVPR 2024