Search

Object detection in unmanned aerial vehicle (UAV) remote sensing images poses significant challenges due to unstable image quality, small object sizes, complex backgrounds, and environmental occlusions. Small objects, in particular, occupy minimal portions of images, making their accurate detection highly difficult. Existing multi-scale feature fusion methods address these challenges to some extent by aggregating features across different resolutions. However, these methods often fail to effectively balance classification and localization performance for small objects, primarily due to insufficient feature representation and imbalanced network information flow. In this paper, we propose a novel feature fusion framework specifically designed for UAV object detection tasks to enhance both localization accuracy and classification performance. The proposed framework integrates hybrid upsampling and downsampling modules, enabling feature maps from different network depths to be flexibly adjusted to arbitrary resolutions. This design facilitates cross-layer connections and multi-scale feature fusion, ensuring improved representation of small objects. Our approach leverages hybrid downsampling to enhance fine-grained feature representation, improving spatial localization of small targets, even under complex conditions. Simultaneously, the upsampling module aggregates global contextual information, optimizing feature consistency across scales and enhancing classification robustness in cluttered scenes. Experimental results on two public UAV datasets demonstrate the effectiveness of the proposed framework. Integrated into the YOLO-V10 model, our method achieves a 2\% improvement in average precision (AP) compared to the baseline YOLO-V10 model, while maintaining the same number of parameters. These results highlight the potential of our framework for accurate and efficient UAV object detection.

Dataset distillation aims to synthesize a smaller, representative dataset that preserves the essential properties of the original data, enabling efficient model training with reduced computational resources. Prior work has primarily focused on improving the alignment or matching process between original and synthetic data, or on enhancing the efficiency of distilling large datasets. In this work, we introduce ${\bf C}$ommittee ${\bf V}$oting for ${\bf D}$ataset ${\bf D}$istillation (CV-DD), a novel and orthogonal approach that leverages the collective wisdom of multiple models or experts to create high-quality distilled datasets. We start by showing how to establish a strong baseline that already achieves state-of-the-art accuracy through leveraging recent advancements and thoughtful adjustments in model design and optimization processes. By integrating distributions and predictions from a committee of models while generating high-quality soft labels, our method captures a wider spectrum of data features, reduces model-specific biases and the adverse effects of distribution shifts, leading to significant improvements in generalization. This voting-based strategy not only promotes diversity and robustness within the distilled dataset but also significantly reduces overfitting, resulting in improved performance on post-eval tasks. Extensive experiments across various datasets and IPCs (images per class) demonstrate that Committee Voting leads to more reliable and adaptable distilled data compared to single/multi-model distillation methods, demonstrating its potential for efficient and accurate dataset distillation. Code is available at: https://github.com/Jiacheng8/CV-DD., Comment: Code at: https://github.com/Jiacheng8/CV-DD

The local point group symmetry of luminescent centers, such as defects, impurities, and dopant ions within a crystal, dictates their optical transition properties. While conventional low-temperature spectroscopy quantifies point group symmetry by enumerating the splitting of optical transitions, it fails to capture vectorial symmetry information, such as the orientation of symmetry axes. Here, we establish a quantitative link between point group symmetry, crystal symmetry, optical transition dipole orientation, and polarized luminescence in rare-earth-doped single-particle crystals using computational electromagnetism. Combined with room-temperature single-particle polarization spectroscopy, we resolve the magnetic dipole orientations from individual optical transition of dopant ions in single microcrystal, enabling precise identification of point group symmetry and its axes. We observe single-particle chirality arising from spontaneous symmetry breaking of intrinsically chiral space group during crystallization. Based on point group and crystal symmetries, we present a practical scheme to optical sensing the 3D orientation of rare-earth-doped single particles in dynamic environments by using two arbitrarily transition bands from single-view polarization spectra. Our computational electromagnetism framework not only elucidates polarized luminescence but also provides insights into optimizing dipole orientation-dependent energy transfer for designing ultra-bright rare-earth-doped nanocrystals, such as F\"orster resonance energy transfer, and can interpret enhanced linear polarization in extreme optical phenomena like stimulated emission, superradiance, and superfluorescence following dipole-coherent radiation in single emitters., Comment: 29 pages, 5 figures

People feel attached to places that are meaningful to them, which psychological research calls "place attachment." Place attachment is associated with self-identity, self-continuity, and psychological well-being. Even small cues, including videos, images, sounds, and scents, can facilitate feelings of connection and belonging to a place. Telepresence robots that allow people to see, hear, and interact with a remote place have the potential to establish and maintain a connection with places and support place attachment. In this paper, we explore the design space of robotic telepresence to promote place attachment, including how users might be guided in a remote place and whether they experience the environment individually or with others. We prototyped a telepresence robot that allows one or more remote users to visit a place and be guided by a local human guide or a conversational agent. Participants were 38 university alumni who visited their alma mater via the telepresence robot. Our findings uncovered four distinct user personas in the remote experience and highlighted the need for social participation to enhance place attachment. We generated design implications for future telepresence robot design to support people's connections with places of personal significance., Comment: Proceedings of the 29th ACM/IEEE International Conference on Human Robot Interaction (HRI 2025)

Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish between new domain data. In this work, we propose a method called Feature Realignment through Experts on hyperSpHere in Continual Learning (Fresh-CL). By leveraging predefined and fixed simplex equiangular tight frame (ETF) classifiers on a hypersphere, our model improves feature separation both intra and inter tasks. However, the projection to a simplex ETF shifts with new tasks, disrupting structured feature representation of previous tasks and degrading performance. Therefore, we propose a dynamic extension of ETF through mixture of experts, enabling adaptive projections onto diverse subspaces to enhance feature representation. Experiments on 11 datasets demonstrate a 2% improvement in accuracy compared to the strongest baseline, particularly in fine-grained datasets, confirming the efficacy of combining ETF and MoE to improve feature distinction in continual learning scenarios., Comment: Accepted by ICASSP 2025

Robot foundation models, particularly Vision-Language-Action (VLA) models, have garnered significant attention for their ability to enhance robot policy learning, greatly improving robot generalization and robustness. OpenAI recent model, o1, showcased impressive capabilities in solving complex problems by utilizing extensive reasoning chains. This prompts an important question: can robot models achieve better performance in multi-task, complex environments by reviewing prior observations and then providing task-specific reasoning to guide action prediction? In this paper, we introduce \textbf{Chain-of-Affordance (CoA)}, a novel approach to scaling robot models by incorporating reasoning in the format of sequential robot affordances to facilitate task completion. Specifically, we prompt the model to consider the following four types of affordances before taking action: a) object affordance - what object to manipulate and where it is; b) grasp affordance - the specific object part to grasp; c) spatial affordance - the optimal space to place the object; and d) movement affordance - the collision-free path for movement. By integrating this knowledge into the policy model, the robot gains essential context, allowing it to act with increased precision and robustness during inference. Our experiments demonstrate that CoA achieves superior performance than state-of-the-art robot foundation models, such as OpenVLA and Octo. Additionally, CoA shows strong generalization to unseen object poses, identifies free space, and avoids obstacles in novel environments., Comment: Project webpage is available at https://chain-of-affordance.github.io

The high demand for 3D imaging in intelligent robotics is motivating the advances of coherent LiDARs towards high performances with low complexity/cost. However, the current coherent LiDARs suffer from the tight coupling between the high ranging-imaging performance and the high complexity/cost. Herein, we propose a narrowband parallel coherent LiDAR with frequency-interleaving architecture. The LiDAR architecture utilizes narrowband signals for ranging, and interleaves multi-channel sparse and narrowband signals in frequency domain at the receiving end to significantly reduce the required bandwidth and the number of detection branches, facilitating massive parallelization with low system complexity/cost. In experiments, a ranging precision of 0.49 mm that approaches the shot noise limit, and a power sensitivity of -95 dBm (~9 photons) are achieved. Parallel 3D imaging with an equivalent imaging rate of 10 Mpixel/s and a 2 cm ranging precision is also demonstrated using only two 150 MHz receiving branches. With these desirable properties, this new LiDAR opens an avenue for the LiDAR ecosystem.

As immersive technologies enable unique, multimodal interaction methods, developers must also use tailored methods to support user accessibility, distinct from traditional software practices. Therefore, we interviewed 25 industry extended reality (XR) developers, including freelancers, startups, midsize, and big tech companies about their motivations, techniques, barriers, and attitudes towards incorporating accessibility features in their XR apps. Our study revealed a variety of challenges, including conflicting priorities between application and platform developers regarding accessibility infrastructure; startups rapid development culture prohibiting accessible development; and the lack of accessible interaction design considerations at the ideation, design, and early prototyping stages. As a comprehensive set of XR accessibility guidelines has yet to be established, we also compiled and evaluated a set of accessibility guidelines for 3D virtual worlds and addressed their limitations when applied to XR. Finally, we inform the creation of effective support methods for industry developers., Comment: Preprint

This study explores the application of generative adversarial networks in financial market supervision, especially for solving the problem of data imbalance to improve the accuracy of risk prediction. Since financial market data are often imbalanced, especially high-risk events such as market manipulation and systemic risk occur less frequently, traditional models have difficulty effectively identifying these minority events. This study proposes to generate synthetic data with similar characteristics to these minority events through GAN to balance the dataset, thereby improving the prediction performance of the model in financial supervision. Experimental results show that compared with traditional oversampling and undersampling methods, the data generated by GAN has significant advantages in dealing with imbalance problems and improving the prediction accuracy of the model. This method has broad application potential in financial regulatory agencies such as the U.S. Securities and Exchange Commission (SEC), the Financial Industry Regulatory Authority (FINRA), the Federal Deposit Insurance Corporation (FDIC), and the Federal Reserve.

In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole framework is simple and flexible, making it easy to deploy and upgrade. We conduct extensive experiments using multiple real robots to validate the effectiveness of DiffusionVLA. Our tests include a challenging factory sorting task, where DiffusionVLA successfully categorizes objects, including those not seen during training. We observe that the reasoning module makes the model interpretable. It allows observers to understand the model thought process and identify potential causes of policy failures. Additionally, we test DiffusionVLA on a zero-shot bin-picking task, achieving 63.7\% accuracy on 102 previously unseen objects. Our method demonstrates robustness to visual changes, such as distractors and new backgrounds, and easily adapts to new embodiments. Furthermore, DiffusionVLA can follow novel instructions and retain conversational ability. Notably, DiffusionVLA is data-efficient and fast at inference; our smallest DiffusionVLA-2B runs 82Hz on a single A6000 GPU and can train from scratch on less than 50 demonstrations for a complex task. Finally, we scale the model from 2B to 72B parameters, showcasing improved generalization capabilities with increased model size., Comment: The project page is available at: http://diffusion-vla.github.io

This study proposes an automated data mining framework based on autoencoders and experimentally verifies its effectiveness in feature extraction and data dimensionality reduction. Through the encoding-decoding structure, the autoencoder can capture the data's potential characteristics and achieve noise reduction and anomaly detection, providing an efficient and stable solution for the data mining process. The experiment compared the performance of the autoencoder with traditional dimensionality reduction methods (such as PCA, FA, T-SNE, and UMAP). The results showed that the autoencoder performed best in terms of reconstruction error and root mean square error and could better retain data structure and enhance the generalization ability of the model. The autoencoder-based framework not only reduces manual intervention but also significantly improves the automation of data processing. In the future, with the advancement of deep learning and big data technology, the autoencoder method combined with a generative adversarial network (GAN) or graph neural network (GNN) is expected to be more widely used in the fields of complex data processing, real-time data analysis and intelligent decision-making.

We investigate the nonlinear optical response of graphene nanoribbon (GNR) heterojunctions both without and with one or multiple topological interface states. By implementing a distant-neighbor quantum-mechanical (DNQM) method, we demonstrate a pronounced enhancement of the nonlinear optical response of GNR heterojunctions as the number of topological states at their interfaces increases. Specifically, we find that GNR heterojunctions with multiple topological interface states exhibit a notably stronger third-order nonlinear optical response in comparison with the similarly sized counterparts with a single topological interface state or without such states. Furthermore, we observe that the presence of topological interface states in GNR heterojunctions can induce a significant red-shift in their quantum plasmon frequency. Our results reveal the potential to enhance the nonlinear optical response at the nanoscale by increasing the number of topological interface states in graphene nanostructures or other topological systems., Comment: 9 pages, 5 figures

Experimental control over the strength and angular dependence of interactions between atoms is a key capability for advancing quantum technologies. Here, we use microwave dressing to manipulate and enhance Rydberg-Rydberg interactions in an atomic ensemble. By varying the cloud length relative to the blockade radius and measuring the statistics of the light retrieved from the ensemble, we demonstrate a clear enhancement of the interaction strength due to microwave dressing. These results are successfully captured by a theoretical model that accounts for the excitations dynamics, atomic density distribution, and the phase-matched retrieval efficiency. Our approach offers a versatile platform for further engineering interactions by exploiting additional features of the microwave fields, such as polarization and detuning, opening pathways for new quantum control strategies., Comment: 7 pages, 3 figures and supplementary 9 pages, 7 figures

The advanced role-playing capabilities of Large Language Models (LLMs) have paved the way for developing Role-Playing Agents (RPAs). However, existing benchmarks in social interaction such as HPD and SocialBench have not investigated hallucination and face limitations like poor generalizability and implicit judgments for character fidelity. To address these issues, we propose a generalizable, explicit and effective paradigm to unlock the interactive patterns in diverse worldviews. Specifically, we define the interactive hallucination based on stance transfer and construct a benchmark, SHARP, by extracting relations from a general commonsense knowledge graph and leveraging the inherent hallucination properties of RPAs to simulate interactions across roles. Extensive experiments validate the effectiveness and stability of our paradigm. Our findings further explore the factors influencing these metrics and discuss the trade-off between blind loyalty to roles and adherence to facts in RPAs., Comment: rename the hallucination and so on

With the rapid growth of digital information, personalized recommendation systems have become an indispensable part of Internet services, especially in the fields of e-commerce, social media, and online entertainment. However, traditional collaborative filtering and content-based recommendation methods have limitations in dealing with data sparsity and cold start problems, especially in the face of largescale heterogeneous data, which makes it difficult to meet user expectations. This paper proposes a new label recommendation algorithm based on metric learning, which aims to overcome the challenges of traditional recommendation systems by learning effective distance or similarity metrics to capture the subtle differences between user preferences and item features. Experimental results show that the algorithm outperforms baseline methods including local response metric learning (LRML), collaborative metric learning (CML), and adaptive tensor factorization (ATF) based on adversarial learning on multiple evaluation metrics. In particular, it performs particularly well in the accuracy of the first few recommended items, while maintaining high robustness and maintaining high recommendation accuracy.

In this paper, a discrete reconfigurable intelligent surface (RIS)-assisted spatial shift keying (SSK) multiple-input multiple-output (MIMO) scheme is investigated, in which a direct link between the transmitter and the receiver is considered. To improve the reliability of the RIS-SSK-MIMO scheme, we formulate an objective function based on minimizing the average bit error probability (ABEP). Since the reflecting phase shift of RIS is discrete, it is difficult to address this problem directly. To this end, we optimize the RIS phase shift to maximize the Euclidean distance between the minimum constellations by applying the successive convex approximation (SCA) and penaltyalternating optimization method. Simulation results verify the superiority of the proposed RIS-SSK-MIMO scheme and demonstrate the impact of the number of RIS elements, the number of phase quantization bits, and the number of receive and transmit antennas in terms of reliability.

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/., Comment: 25 pages

Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of depths (MoDs) in natural language processing, we aim to address this limitation from the perspective of ``activated tokens''. Our key insight is that if most tokens are redundant for the layer computation, then can be skipped directly via the MoD layer. However, directly converting the dense layers of MLLMs to MoD layers leads to substantial performance degradation. To address this issue, we propose an innovative MoD adaptation strategy for existing MLLMs called $\gamma$-MoD. In $\gamma$-MoD, a novel metric is proposed to guide the deployment of MoDs in the MLLM, namely rank of attention maps (ARank). Through ARank, we can effectively identify which layer is redundant and should be replaced with the MoD layer. Based on ARank, we further propose two novel designs to maximize the computational sparsity of MLLM while maintaining its performance, namely shared vision-language router and masked routing learning. With these designs, more than 90% dense layers of the MLLM can be effectively converted to the MoD ones. To validate our method, we apply it to three popular MLLMs, and conduct extensive experiments on 9 benchmark datasets. Experimental results not only validate the significant efficiency benefit of $\gamma$-MoD to existing MLLMs but also confirm its generalization ability on various MLLMs. For example, with a minor performance drop, i.e., -1.5%, $\gamma$-MoD can reduce the training and inference time of LLaVA-HR by 31.0% and 53.2%, respectively.

By leveraging massively distributed data, federated learning (FL) enables collaborative instruction tuning of large language models (LLMs) in a privacy-preserving way. While FL effectively expands the data quantity, the issue of data quality remains under-explored in the current literature on FL for LLMs. To address this gap, we propose a new framework of federated instruction tuning of LLMs with data quality control (FedDQC), which measures data quality to facilitate the subsequent filtering and hierarchical training processes. Our approach introduces an efficient metric to assess each client's instruction-response alignment (IRA), identifying potentially noisy data through single-shot inference. Low-IRA samples are potentially noisy and filtered to mitigate their negative impacts. To further utilize this IRA value, we propose a quality-aware hierarchical training paradigm, where LLM is progressively fine-tuned from high-IRA to low-IRA data, mirroring the easy-to-hard learning process. We conduct extensive experiments on 4 synthetic and a real-world dataset, and compare our method with baselines adapted from centralized setting. Results show that our method consistently and significantly improves the performance of LLMs trained on mix-quality data in FL.

Federated Domain-specific Instruction Tuning (FedDIT) utilizes limited cross-client private data together with various strategies of instruction augmentation, ultimately boosting model performance within specific domains. To date, the factors affecting FedDIT remain unclear, and existing instruction augmentation methods primarily focus on the centralized setting without considering distributed environments. Our experiments reveal that the cross-client domain coverage, rather than data heterogeneity, drives model performance in FedDIT. In response, we propose FedDCA, which optimizes domain coverage through greedy client center selection and retrieval-based augmentation. At its core, the greedy selection procedure iteratively picks client centers that maximize the diversity and coverage of the instruction space while avoiding redundancy with previously selected centers. This ensures broad yet efficient coverage of the domain distribution across clients. For client-side computational efficiency and system scalability, FedDCA$^*$, the variant of FedDCA, utilizes heterogeneous encoders with server-side feature alignment. Extensive experiments across code, medical, financial, and mathematical domains substantiate the effectiveness of both methods, as well as plug-and-play capability. We further analyze privacy preservation against memory extraction attacks, showing that while privacy leakage risk is independent of augmented public data ratio, it decreases or converges as training progresses.

Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking the need for comprehensive test case coverage. Additionally, most of these methods are limited to single-turn red teaming, failing to capture the multi-turn dynamics of real-world human-machine interactions. To overcome these limitations, we propose HARM (Holistic Automated Red teaMing), which scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy. Our method also leverages a novel fine-tuning strategy and reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner. Experimental results demonstrate that our framework enables a more systematic understanding of model vulnerabilities and offers more targeted guidance for the alignment process., Comment: EMNLP 2024 camera ready version

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model size would lead to enhanced performance. However, our observations indicate that Diffusion Policy in transformer architecture (\DP) struggles to scale effectively; even minor additions of layers can deteriorate training outcomes. To address this issue, we introduce Scalable Diffusion Transformer Policy for visuomotor learning. Our proposed method, namely \textbf{\methodname}, introduces two modules that improve the training dynamic of Diffusion Policy and allow the network to better handle multimodal action distribution. First, we identify that \DP~suffers from large gradient issues, making the optimization of Diffusion Policy unstable. To resolve this issue, we factorize the feature embedding of observation into multiple affine layers, and integrate it into the transformer blocks. Additionally, our utilize non-causal attention which allows the policy network to \enquote{see} future actions during prediction, helping to reduce compounding errors. We demonstrate that our proposed method successfully scales the Diffusion Policy from 10 million to 1 billion parameters. This new model, named \methodname, can effectively scale up the model size with improved performance and generalization. We benchmark \methodname~across 50 different tasks from MetaWorld and find that our largest \methodname~outperforms \DP~with an average improvement of 21.6\%. Across 7 real-world robot tasks, our ScaleDP demonstrates an average improvement of 36.25\% over DP-T on four single-arm tasks and 75\% on three bimanual tasks. We believe our work paves the way for scaling up models for visuomotor learning. The project page is available at scaling-diffusion-policy.github.io.

Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that \methodname offers an interesting perspective on utilizing pre-trained multimodal models for policy learning. Our project is at https://tiny-vla.github.io., Comment: add more citations

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing research attention lately. Existing attack methods on LLMs inherit the extraction strategies from those designed for deep neural networks (DNNs) yet neglect the inconsistency of training tasks between MEA and LLMs' alignments. As such, they result in poor attack performances. To tackle this issue, we present Locality Reinforced Distillation (LoRD), a novel model extraction attack algorithm specifically for LLMs. In particular, we design a policy-gradient-style training task, which utilizes victim models' responses as a signal to guide the crafting of preference for the local model. Theoretical analysis has shown that i) LoRD's convergence procedure in MEAs is consistent with the alignments of LLMs, and ii) LoRD can reduce query complexity while mitigating watermark protection through exploration-based stealing. Extensive experiments on domain-specific extractions demonstrate the superiority of our method by examining the extraction of various state-of-the-art commercial LLMs., Comment: Source code: https://github.com/liangzid/alignmentExtraction

Data from fluid flow measurements are typically sparse, noisy, and heterogeneous, often from mixed pressure and velocity measurements, resulting in incomplete datasets. In this paper, we develop a physics-constrained convolutional neural network, which is a deterministic tool, to reconstruct the full flow field from incomplete data. We explore three loss functions, both from machine learning literature and newly proposed: (i) the softly-constrained loss, which allows the prediction to take any value; (ii) the snapshot-enforced loss, which constrains the prediction at the sensor locations; and (iii) the mean-enforced loss, which constrains the mean of the prediction at the sensor locations. The proposed methods do not require the full flow field during training, making it suitable for reconstruction from incomplete data. We apply the method to reconstruct a laminar wake of a bluff body and a turbulent Kolmogorov flow. First, we assume that measurements are not noisy and reconstruct both the laminar wake and the Kolmogorov flow from sensors located at fewer than 1% of all grid points. The snapshot-enforced loss reduces the reconstruction error of the Kolmogorov flow by approximately 25% compared to the softly-constrained loss. Second, we assume that measurements are noisy and propose the mean-enforced loss to reconstruct the laminar wake and the Kolmogorov flow at three different signal-to-noise ratios. We find that, across the ratios tested, the loss functions with harder constraints are more robust to both the random initialization of the networks and the noise levels in the measurements. At high noise levels, the mean-enforced loss can recover the instantaneous snapshots accurately, making it the suitable choice when reconstructing flows from data corrupted with an unknown amount of noise. The proposed method opens opportunities for physical flow reconstruction from sparse, noisy data.

Traumatic brain injury (TBI) can cause a range of cognitive and communication challenges that negatively affect social participation in both face-to-face interactions and computer-mediated communication. In particular, individuals with TBI report barriers that limit access to participation on social media platforms. To improve access to and use of social media for users with TBI, we introduce the Social Media Accessibility and Rehabilitation Toolkit (\textbf{SMART-TBI}). The toolkit includes five aids (Writing Aid, Interpretation Aid, Filter Mode, Focus Mode, and Facebook Customization) designed to address the cognitive and communicative needs of individuals with TBI. We asked eight users with moderate-severe TBI and five TBI rehabilitation experts to evaluate each aid. Our findings revealed potential benefits of aids and areas for improvement, including the need for psychological safety, privacy control, and balancing business and accessibility needs; and overall mixed reactions among the participants to AI-based aids., Comment: In Proceedings The 26th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'24)

Sparse view computed tomography (CT) reconstruction poses a challenging ill-posed inverse problem, necessitating effective regularization techniques. In this letter, we employ $L_p$-norm ($0

The drastic increase of large language models' (LLMs) parameters has led to a new research direction of fine-tuning-free downstream customization by prompts, i.e., task descriptions. While these prompt-based services (e.g. OpenAI's GPTs) play an important role in many businesses, there has emerged growing concerns about the prompt leakage, which undermines the intellectual properties of these services and causes downstream attacks. In this paper, we analyze the underlying mechanism of prompt leakage, which we refer to as prompt memorization, and develop corresponding defending strategies. By exploring the scaling laws in prompt extraction, we analyze key attributes that influence prompt extraction, including model sizes, prompt lengths, as well as the types of prompts. Then we propose two hypotheses that explain how LLMs expose their prompts. The first is attributed to the perplexity, i.e. the familiarity of LLMs to texts, whereas the second is based on the straightforward token translation path in attention matrices. To defend against such threats, we investigate whether alignments can undermine the extraction of prompts. We find that current LLMs, even those with safety alignments like GPT-4, are highly vulnerable to prompt extraction attacks, even under the most straightforward user attacks. Therefore, we put forward several defense strategies with the inspiration of our findings, which achieve 83.8\% and 71.0\% drop in the prompt extraction rate for Llama2-7B and GPT-3.5, respectively. Source code is avaliable at \url{https://github.com/liangzid/PromptExtractionEval}.

Recently, binary cyclic codes with parameters $[n,(n\pm1)/2,\geq \sqrt{n}]$ have been a hot topic since their minimum distances have a square-root bound. In this paper, we construct four classes of binary cyclic codes $\mathcal{C}_{\mathcal{S},0}$, $\mathcal{C}_{\mathcal{S},1}$ and $\mathcal{C}_{\mathcal{D},0}$, $\mathcal{C}_{\mathcal{D},1}$ by using two families of sequences, and obtain some codes with parameters $[n,(n\pm1)/2,\geq \sqrt{n}]$. For $m\equiv2\pmod4$, the code $\mathcal{C}_{\mathcal{S},0}$ has parameters $[2^m-1,2^{m-1},\geq2^{\frac{m}{2}}+2]$, and the code $\mathcal{C}_{\mathcal{D},0}$ has parameters $[2^m-1,2^{m-1},\geq2^{\frac{m}{2}}+2]$ if $h=1$ and $[2^m-1,2^{m-1},\geq2^{\frac{m}{2}}]$ if $h=2$.

Unmanned Aerial Vehicles (UAVs) have significantly enhanced fog computing by acting as both flexible computation platforms and communication mobile relays. In this paper, we propose a holistic framework that jointly optimizes the total latency and energy consumption for UAV-assisted fog computing in a three-dimensional spatial domain with varying terrain elevations and dynamic task generations. Our proposed framework considers three important and interdependent modules: attitude control, trajectory planning, and task assignment. We first establish a fuzzy proportional-integral-derivative control model to determine the UAV's attitude. Then, we propose an enhanced Ant Colony System (ACS) based algorithm, that includes a safety value and a decoupling mechanism to overcome the convergence issue in classical ACS, to compute the optimal UAV trajectory. Finally, we design an algorithm based on the Particle Swarm Optimization technique, to determine where each offloaded task should be executed. Under our proposed framework, the outcome of one module would affect the decision-making in one other, providing a holistic perspective of the system and thus leading to improved solutions. We demonstrate by extensive simulation results that our proposed framework can significantly improve the overall performance, measured by latency and energy consumption, compared to existing baseline approaches., Comment: 14 pages, 10 figures

Bimetallic nanoalloys have gained extensive attention due to their tunable properties and wide range of catalytic applications. However, achieving good compositional control in nanoalloy catalysts remains a formidable challenge. In this work, we demonstrate that heat treatment can be used to tune the composition of Pt-Zn nanoalloy catalysts, leveraging the volatile nature of zinc to enhance their performance in propane dehydrogenation. Through identical location (scanning) transmission electron microscopy (IL-(S)TEM) using an in-situ EM gas cell, as well as other complementary techniques, we observed that the zinc content of the Pt-Zn nanoalloy particles decreased over time of the heat treatment under hydrogen. The rate of change depends on the original composition of the particles, as well as the heat treatment conditions such as temperature and flow rate. Our experimental results and theoretical calculations suggest that Zn in the intermetallic phase might be more stable, providing an opportunity for precise tuning the nanoparticle compositions. This approach presents a viable strategy for developing better Pt-Zn catalysts for propane dehydrogenation.

Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play crucial roles in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.

It is fundamentally challenging for robots to serve as useful assistants in human environments because this requires addressing a spectrum of sub-problems across robotics, including perception, language understanding, reasoning, and planning. The recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated their exceptional abilities in solving complex mathematical problems, mastering commonsense and abstract reasoning. This has led to the recent utilization of MLLMs as the brain in robotic systems, enabling these models to conduct high-level planning prior to triggering low-level control actions for task execution. However, it remains uncertain whether existing MLLMs are reliable in serving the brain role of robots. In this study, we introduce the first benchmark for evaluating Multimodal LLM for Robotic (MMRo) benchmark, which tests the capability of MLLMs for robot applications. Specifically, we identify four essential capabilities perception, task planning, visual reasoning, and safety measurement that MLLMs must possess to qualify as the robot's central processing unit. We have developed several scenarios for each capability, resulting in a total of 14 metrics for evaluation. We present experimental results for various MLLMs, including both commercial and open-source models, to assess the performance of existing systems. Our findings indicate that no single model excels in all areas, suggesting that current MLLMs are not yet trustworthy enough to serve as the cognitive core for robots. Our data can be found in https://mm-robobench.github.io/.

All-dielectric optical resonators, exhibiting exotic near-field distributions upon excitations, have emerged as low-loss, versatile and highly adaptable components in nanophotonic structures for manipulating electromagnetic waves and enhancing light-matter interactions. However, achieving experimental full three-dimensional characterization of near-fields within dielectric materials poses significant challenges. Here, we develop a novel technique using high-order sideband generation to image near-field wave patterns inside dielectric optical resonators. By exploiting the phase-sensitivity of various harmonic orders that enables the detection of near-field distributions at distinct depths, we realize three-dimensional tomographic and super-resolution near-field imaging inside a micrometer-thick silicon anapole resonator. Furthermore, our method offers high-contrast polarization sensitivity and phase-resolving capability, providing comprehensive vectorial near-field information. Our approach can potentially be applied to diverse dielectric metamaterials, and becomes a valuable tool for comprehensive characterization of near-field wave phenomena within dielectric materials., Comment: 26 pages, 4 figures

Self-propelled micromotors can efficiently convert ambient energy into mechanical motion, which is of great interest for its potential biomedical applications in delivering therapeutics noninvasively. However, navigating these micromotors through biological barriers remains a significant challenge as most micromotors do not provide sufficient disruption forces in in-vivo conditions. In this study, we employed focused scanning laser from conventional confocal microscope to manipulate carbon microbottle based microswimmers. With the increasing of the laser power, the microswimmers' motions translates from autonomous to directional, and finally the high power laser induced the microswimmer explosions, which effectively deliveres microbottle fragments through the cell membrane. It is revealed that photothermally-induced cavitation bubbles enable the propulsion of microbottles in liquids, where the motion direction can be precisely regulated by the scanning orientation of the laser. Furthermore, the membrane penetration ability of the microbottles promised potential applications in drug delivery and cellular injections. As microbottles navigate toward cells, we strategically increase the laser power to trigger their explosion. By loading microswimmers with transfection genes, cytoplasmic transfection can be realized, which is demonstrated by successful gene transfection of GPF in cells. Our findings open new possibilities for cell injection and gene transfection using micromotors., Comment: 30 pages, 6 figures

Nowadays, attackers target Internet of Things (IoT) devices for security exploitation, and search engines for devices and services compromise user privacy, including IP addresses, open ports, device types, vendors, and products.Typically, application banners are used to recognize IoT device profiles during network measurement and reconnaissance. In this paper, we propose a novel approach to obfuscating IoT device banners (BANADV) based on adversarial examples. The key idea is to explore the susceptibility of fingerprinting techniques to a slight perturbation of an IoT device banner. By modifying device banners, BANADV disrupts the collection of IoT device profiles. To validate the efficacy of BANADV, we conduct a set of experiments. Our evaluation results show that adversarial examples can spoof state-of-the-art fingerprinting techniques, including learning- and matching-based approaches. We further provide a detailed analysis of the weakness of learning-based/matching-based fingerprints to carefully crafted samples. Overall, the innovations of BANADV lie in three aspects: (1) it utilizes an IoT-related semantic space and a visual similarity space to locate available manipulating perturbations of IoT banners; (2) it achieves at least 80\% success rate for spoofing IoT scanning techniques; and (3) it is the first to utilize adversarial examples of IoT banners in network measurement and reconnaissance.

We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 1,000 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains(e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 191 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of 3 proprietary models and 11 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4V, Claude-3-opus only achieve an average score of 73.2 and 53.7, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence., Comment: Data and code are available at https://github.com/ChartMimic/ChartMimic

This project intends to study the image representation based on attention mechanism and multimodal data. By adding multiple pattern layers to the attribute model, the semantic and hidden layers of image content are integrated. The word vector is quantified by the Word2Vec method and then evaluated by a word embedding convolutional neural network. The published experimental results of the two groups were tested. The experimental results show that this method can convert discrete features into continuous characters, thus reducing the complexity of feature preprocessing. Word2Vec and natural language processing technology are integrated to achieve the goal of direct evaluation of missing image features. The robustness of the image feature evaluation model is improved by using the excellent feature analysis characteristics of a convolutional neural network. This project intends to improve the existing image feature identification methods and eliminate the subjective influence in the evaluation process. The findings from the simulation indicate that the novel approach has developed is viable, effectively augmenting the features within the produced representations.

Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also have a large demand for computing resources, which may cause convolutional neural networks to be unable to be implemented on terminals. Therefore, this paper will carry out the optimal classification of convolutional neural networks. Firstly, according to the characteristics of pneumonia images, AlexNet and InceptionV3 were selected to obtain better image recognition results. Combining the features of medical images, the forward neural network with deeper and more complex structure is learned. Finally, knowledge extraction technology is used to extract the obtained data into the AlexNet model to achieve the purpose of improving computing efficiency and reducing computing costs. The results showed that the prediction accuracy, specificity, and sensitivity of the trained AlexNet model increased by 4.25 percentage points, 7.85 percentage points, and 2.32 percentage points, respectively. The graphics processing usage has decreased by 51% compared to the InceptionV3 mode.

Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the community has put massive efforts from diverse aspects including framework, performance, and privacy. However, an unpleasant fact is that there are currently no realistic datasets and benchmarks for FedLLM and previous works all rely on artificially constructed datasets, failing to capture properties in real-world scenarios. Addressing this, we propose FedLLM-Bench, which involves 8 training methods, 4 training datasets, and 6 evaluation metrics, to offer a comprehensive testbed for the FedLLM community. FedLLM-Bench encompasses three datasets (e.g., user-annotated multilingual dataset) for federated instruction tuning and one dataset (e.g., user-annotated preference dataset) for federated preference alignment, whose scale of client number ranges from 38 to 747. Our datasets incorporate several representative diversities: language, quality, quantity, instruction, length, embedding, and preference, capturing properties in real-world scenarios. Based on FedLLM-Bench, we conduct experiments on all datasets to benchmark existing FL methods and provide empirical insights (e.g., multilingual collaboration). We believe that our FedLLM-Bench can benefit the FedLLM community by reducing required efforts, providing a practical testbed, and promoting fair comparisons. Code and datasets are available at https://github.com/rui-ye/FedLLM-Bench., Comment: 22 pages

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant structural units, aiming to more effectively leverage their low-power consumption and biological interpretability advantages. Currently, most model compression techniques for SNNs are based on unstructured pruning of individual connections, which requires specific hardware support. Hence, we propose a structured pruning approach based on the activity levels of convolutional kernels named Spiking Channel Activity-based (SCA) network pruning framework. Inspired by synaptic plasticity mechanisms, our method dynamically adjusts the network's structure by pruning and regenerating convolutional kernels during training, enhancing the model's adaptation to the current target task. While maintaining model performance, this approach refines the network architecture, ultimately reducing computational load and accelerating the inference process. This indicates that structured dynamic sparse learning methods can better facilitate the application of deep SNNs in low-power and high-efficiency scenarios.