Search

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset. However, current dataset distillation methods often result in synthetic datasets that are excessively difficult for networks to learn from, due to the compression of a substantial amount of information from the original data through metrics measuring feature similarity, e,g., distribution matching (DM). In this work, we introduce conditional mutual information (CMI) to assess the class-aware complexity of a dataset and propose a novel method by minimizing CMI. Specifically, we minimize the distillation loss while constraining the class-aware complexity of the synthetic dataset by minimizing its empirical CMI from the feature space of pre-trained networks, simultaneously. Conducting on a thorough set of experiments, we show that our method can serve as a general regularization method to existing DD methods and improve the performance and training efficiency.

Contact-rich tasks present significant challenges for robotic manipulation policies due to the complex dynamics of contact and the need for precise control. Vision-based policies often struggle with the skill required for such tasks, as they typically lack critical contact feedback modalities like force/torque information. To address this issue, we propose FoAR, a force-aware reactive policy that combines high-frequency force/torque sensing with visual inputs to enhance the performance in contact-rich manipulation. Built upon the RISE policy, FoAR incorporates a multimodal feature fusion mechanism guided by a future contact predictor, enabling dynamic adjustment of force/torque data usage between non-contact and contact phases. Its reactive control strategy also allows FoAR to accomplish contact-rich tasks accurately through simple position control. Experimental results demonstrate that FoAR significantly outperforms all baselines across various challenging contact-rich tasks while maintaining robust performance under unexpected dynamic disturbances. Project website: https://tonyfang.net/FoAR/, Comment: 9 pages, 5 figures

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning incurs significant training cost and prompting increases inference overhead. We introduce $GenerativeAdapter$, an effective and efficient adaptation method that directly maps new contexts to low-rank LM adapters, thereby significantly reducing inference overhead with no need for finetuning. The adapter generator is trained via self-supervised learning, and can be used to adapt a single frozen LM for any new task simply by mapping the associated task or domain context to a new adapter. We apply $GenerativeAdapter$ to two pretrained LMs (Mistral-7B-Instruct and Llama2-7B-Chat) and evaluate the adapted models in three adaption scenarios: knowledge acquisition from documents, learning from demonstrations, and personalization for users. In StreamingQA, our approach is effective in injecting knowledge into the LM's parameters, achieving a 63.5% improvement in F1 score over the model with supervised fine-tuning (from $19.5$ to $31.5$) for contexts as long as 32K tokens. In the MetaICL in-context learning evaluation, our method achieves an average accuracy of $44.9$ across 26 tasks, outperforming the base model. On MSC, our method proves to be highly competitive in memorizing user information from conversations with a 4x reduction in computation and memory costs compared to prompting with full conversation history. Together, these results suggest that $GenerativeAdapter$ should allow for general adaption to a wide range of different contexts.

Generalization in robotic manipulation remains a critical challenge, particularly when scaling to new environments with limited demonstrations. This paper introduces CAGE, a novel robotic manipulation policy designed to overcome these generalization barriers by integrating a causal attention mechanism. CAGE utilizes the powerful feature extraction capabilities of the vision foundation model DINOv2, combined with LoRA fine-tuning for robust environment understanding. The policy further employs a causal Perceiver for effective token compression and a diffusion-based action prediction head with attention mechanisms to enhance task-specific fine-grained conditioning. With as few as 50 demonstrations from a single training environment, CAGE achieves robust generalization across diverse visual changes in objects, backgrounds, and viewpoints. Extensive experiments validate that CAGE significantly outperforms existing state-of-the-art RGB/RGB-D approaches in various manipulation tasks, especially under large distribution shifts. In similar environments, CAGE offers an average of 42% increase in task completion rate. While all baselines fail to execute the task in unseen environments, CAGE manages to obtain a 43% completion rate and a 51% success rate in average, making a huge step towards practical deployment of robots in real-world settings. Project website: cage-policy.github.io., Comment: Submitted to ICRA 2025

Sonar radar captures visual representations of underwater objects and structures using sound wave reflections, making it essential for exploration, mapping, and continuous surveillance in wild ecosystems. Real-time analysis of sonar data is crucial for time-sensitive applications, including environmental anomaly detection and in-season fishery management, where rapid decision-making is needed. However, the lack of both relevant datasets and pre-trained DNN models, coupled with resource limitations in wild environments, hinders the effective deployment and continuous operation of live sonar analytics. We present SALINA, a sustainable live sonar analytics system designed to address these challenges. SALINA enables real-time processing of acoustic sonar data with spatial and temporal adaptations, and features energy-efficient operation through a robust energy management module. Deployed for six months at two inland rivers in British Columbia, Canada, SALINA provided continuous 24/7 underwater monitoring, supporting fishery stewardship and wildlife restoration efforts. Through extensive real-world testing, SALINA demonstrated an up to 9.5% improvement in average precision and a 10.1% increase in tracking metrics. The energy management module successfully handled extreme weather, preventing outages and reducing contingency costs. These results offer valuable insights for long-term deployment of acoustic data systems in the wild., Comment: 14 pages, accepted by ACM SenSys 2024

Model Inversion Attacks (MIAs) aim at recovering privacy-sensitive training data from the knowledge encoded in the released machine learning models. Recent advances in the MIA field have significantly enhanced the attack performance under multiple scenarios, posing serious privacy risks of Deep Neural Networks (DNNs). However, the development of defense strategies against MIAs is relatively backward to resist the latest MIAs and existing defenses fail to achieve further trade-off between model utility and model robustness. In this paper, we provide an in-depth analysis from the perspective of intrinsic vulnerabilities of MIAs, comprehensively uncovering the weaknesses inherent in the basic pipeline, which are partially investigated in the previous defenses. Building upon these new insights, we propose a robust defense mechanism, integrating Confidence Adaptation and Low-Rank compression(CALoR). Our method includes a novel robustness-enhanced classification loss specially-designed for model inversion defenses and reveals the extraordinary effectiveness of compressing the classification header. With CALoR, we can mislead the optimization objective, reduce the leaked information and impede the backpropagation of MIAs, thus mitigating the risk of privacy leakage. Extensive experimental results demonstrate that our method achieves state-of-the-art (SOTA) defense performance against MIAs and exhibits superior generalization to existing defenses across various scenarios., Comment: 26 pages

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising widespread concerns on privacy threats of Deep Neural Networks (DNNs). Unfortunately, in tandem with the rapid evolution of MI attacks, the lack of a comprehensive, aligned, and reliable benchmark has emerged as a formidable challenge. This deficiency leads to inadequate comparisons between different attack methods and inconsistent experimental setups. In this paper, we introduce the first practical benchmark for model inversion attacks and defenses to address this critical gap, which is named \textit{MIBench}. This benchmark serves as an extensible and reproducible modular-based toolbox and currently integrates a total of 16 state-of-the-art attack and defense methods. Moreover, we furnish a suite of assessment tools encompassing 9 commonly used evaluation protocols to facilitate standardized and fair evaluation and analysis. Capitalizing on this foundation, we conduct extensive experiments from multiple perspectives to holistically compare and analyze the performance of various methods across different scenarios, which overcomes the misalignment issues and discrepancy prevalent in previous works. Based on the collected attack methods and defense strategies, we analyze the impact of target resolution, defense robustness, model predictive power, model architectures, transferability and loss function. Our hope is that this \textit{MIBench} could provide a unified, practical and extensible toolbox and is widely utilized by researchers in the field to rigorously test and compare their novel methods, ensuring equitable evaluations and thereby propelling further advancements in the future development., Comment: 23 pages

Data is crucial for robotic manipulation, as it underpins the development of robotic systems for complex tasks. While high-quality, diverse datasets enhance the performance and adaptability of robotic manipulation policies, collecting extensive expert-level data is resource-intensive. Consequently, many current datasets suffer from quality inconsistencies due to operator variability, highlighting the need for methods to utilize mixed-quality data effectively. To mitigate these issues, we propose "Select Segments to Imitate" (S2I), a framework that selects and optimizes mixed-quality demonstration data at the segment level, while ensuring plug-and-play compatibility with existing robotic manipulation policies. The framework has three components: demonstration segmentation dividing origin data into meaningful segments, segment selection using contrastive learning to find high-quality segments, and trajectory optimization to refine suboptimal segments for better policy learning. We evaluate S2I through comprehensive experiments in simulation and real-world environments across six tasks, demonstrating that with only 3 expert demonstrations for reference, S2I can improve the performance of various downstream policies when trained with mixed-quality demonstrations. Project website: https://tonyfang.net/s2i/., Comment: Project website: https://tonyfang.net/s2i/

This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences. Saliency maps are widely exploited in various applications, including video compression, quality assessment, visual perception studies, the advertising industry, etc. For this competition, a previously unused large-scale audio-visual mouse saliency (AViMoS) dataset of 1500 videos with more than 70 observers per video was collected using crowdsourced mouse tracking. The dataset collection methodology has been validated using conventional eye-tracking data and has shown high consistency. Over 30 teams registered in the challenge, and there are 7 teams that submitted the results in the final phase. The final phase solutions were tested and ranked by commonly used quality metrics on a private test subset. The results of this evaluation and the descriptions of the solutions are presented in this report. All data, including the private test subset, is made publicly available on the challenge homepage - https://challenges.videoprocessing.ai/challenges/video-saliency-prediction.html., Comment: ECCVW 2024

Multi-frequency Electrical Impedance Tomography (mfEIT) is a promising biomedical imaging technique that estimates tissue conductivities across different frequencies. Current state-of-the-art (SOTA) algorithms, which rely on supervised learning and Multiple Measurement Vectors (MMV), require extensive training data, making them time-consuming, costly, and less practical for widespread applications. Moreover, the dependency on training data in supervised MMV methods can introduce erroneous conductivity contrasts across frequencies, posing significant concerns in biomedical applications. To address these challenges, we propose a novel unsupervised learning approach based on Multi-Branch Attention Image Prior (MAIP) for mfEIT reconstruction. Our method employs a carefully designed Multi-Branch Attention Network (MBA-Net) to represent multiple frequency-dependent conductivity images and simultaneously reconstructs mfEIT images by iteratively updating its parameters. By leveraging the implicit regularization capability of the MBA-Net, our algorithm can capture significant inter- and intra-frequency correlations, enabling robust mfEIT reconstruction without the need for training data. Through simulation and real-world experiments, our approach demonstrates performance comparable to, or better than, SOTA algorithms while exhibiting superior generalization capability. These results suggest that the MAIP-based method can be used to improve the reliability and applicability of mfEIT in various settings., Comment: 10 pages, 10 figures, journal

Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in conjunction with ECCV 2024 workshop. This year's challenge includes two tasks: Video Object Segmentation (VOS) and Referring Video Object Segmentation (RVOS). In this year, we replace the classic YouTube-VOS and YouTube-RVOS benchmark with latest datasets MOSE, LVOS, and MeViS to assess VOS under more challenging complex environments. This year's challenge attracted 129 registered teams from more than 20 institutes across over 8 countries. This report include the challenge and dataset introduction, and the methods used by top 7 teams in two tracks. More details can be found in our homepage https://lsvos.github.io/., Comment: ECCV 2024 LSVOS Challenge Report: https://lsvos.github.io/

Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video. In this year, LSVOS Challenge RVOS Track replaced the origin YouTube-RVOS benchmark with MeViS. MeViS focuses on referring the target object in a video through its motion descriptions instead of static attributes, posing a greater challenge to RVOS task. In this work, we integrate strengths of that leading RVOS and VOS models to build up a simple and effective pipeline for RVOS. Firstly, We finetune the state-of-the-art RVOS model to obtain mask sequences that are correlated with language descriptions. Secondly, based on a reliable and high-quality key frames, we leverage VOS model to enhance the quality and temporal consistency of the mask results. Finally, we further improve the performance of the RVOS model using semi-supervised learning. Our solution achieved 62.57 J&F on the MeViS test set and ranked 1st place for 6th LSVOS Challenge RVOS Track.

Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong performance across a wide range of tasks. In this work, we evaluate the zero-shot performance of SAM 2 on the more challenging VOS datasets MOSE and LVOS. Without fine-tuning on the training set, SAM 2 achieved 75.79 J&F on the test set and ranked 4th place for 6th LSVOS Challenge VOS Track., Comment: arXiv admin note: substantial text overlap with arXiv:2408.00714

In this work, we introduce the EyeSight Hand, a novel 7 degrees of freedom (DoF) humanoid hand featuring integrated vision-based tactile sensors tailored for enhanced whole-hand manipulation. Additionally, we introduce an actuation scheme centered around quasi-direct drive actuation to achieve human-like strength and speed while ensuring robustness for large-scale data collection. We evaluate the EyeSight Hand on three challenging tasks: bottle opening, plasticine cutting, and plate pick and place, which require a blend of complex manipulation, tool use, and precise force application. Imitation learning models trained on these tasks, with a novel vision dropout strategy, showcase the benefits of tactile feedback in enhancing task success rates. Our results reveal that the integration of tactile sensing dramatically improves task performance, underscoring the critical role of tactile information in dexterous manipulation.

The problem of grasping objects using a multi-finger hand has received significant attention in recent years. However, it remains challenging to handle a large number of unfamiliar objects in real and cluttered environments. In this work, we propose a representation that can be effectively mapped to the multi-finger grasp space. Based on this representation, we develop a simple decision model that generates accurate grasp quality scores for different multi-finger grasp poses using only hundreds to thousands of training samples. We demonstrate that our representation performs well on a real robot and achieves a success rate of 78.64% after training with only 500 real-world grasp attempts and 87% with 4500 grasp attempts. Additionally, we achieve a success rate of 84.51% in a dynamic human-robot handover scenario using a multi-finger hand., Comment: Published at International Conference on Robotics and Automation (ICRA) 2024

Dynamic community detection is crucial for elucidating the temporal evolution of social structures, information dissemination, and interactive behaviors within complex networks. Nonnegative matrix factorization provides an efficient framework for identifying communities in static networks but fall short in depicting temporal variations in community affiliations. To solve this problem, this paper proposes a Modularity maximization-incorporated Nonnegative Tensor RESCAL Decomposition (MNTD) model for dynamic community detection. This method serves two primary functions: a) Nonnegative tensor RESCAL decomposition extracts latent community structures in different time slots, highlighting the persistence and transformation of communities; and b) Incorporating an initial community structure into the modularity maximization algorithm, facilitating more precise community segmentations. Comparative analysis of real-world datasets shows that the MNTD is superior to state-of-the-art dynamic community detection methods in the accuracy of community detection., Comment: 10 pages, 5 figures,This paper will be published on 2024 IEEE International Conference on Systems, Man, and Cybernetics(SMC)

Model Inversion (MI) attacks aim to reconstruct privacy-sensitive training data from released models by utilizing output information, raising extensive concerns about the security of Deep Neural Networks (DNNs). Recent advances in generative adversarial networks (GANs) have contributed significantly to the improved performance of MI attacks due to their powerful ability to generate realistic images with high fidelity and appropriate semantics. However, previous MI attacks have solely disclosed private information in the latent space of GAN priors, limiting their semantic extraction and transferability across multiple target models and datasets. To address this challenge, we propose a novel method, Intermediate Features enhanced Generative Model Inversion (IF-GMI), which disassembles the GAN structure and exploits features between intermediate blocks. This allows us to extend the optimization space from latent code to intermediate features with enhanced expressive capabilities. To prevent GAN priors from generating unrealistic images, we apply a L1 ball constraint to the optimization process. Experiments on multiple benchmarks demonstrate that our method significantly outperforms previous approaches and achieves state-of-the-art results under various settings, especially in the out-of-distribution (OOD) scenario. Our code is available at: https://github.com/final-solution/IF-GMI, Comment: ECCV 2024

Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced \textit{single-target} generative attacks that train a generator for each target class to generate highly transferable perturbations, resulting in substantial computational overhead when handling multiple classes. \textit{Multi-target} attacks address this by training only one class-conditional generator for multiple classes. However, the generator simply uses class labels as conditions, failing to leverage the rich semantic information of the target class. To this end, we design a \textbf{C}LIP-guided \textbf{G}enerative \textbf{N}etwork with \textbf{C}ross-attention modules (CGNC) to enhance multi-target attacks by incorporating textual knowledge of CLIP into the generator. Extensive experiments demonstrate that CGNC yields significant improvements over previous multi-target generative attacks, e.g., a 21.46\% improvement in success rate from ResNet-152 to DenseNet-121. Moreover, we propose a masked fine-tuning mechanism to further strengthen our method in attacking a single class, which surpasses existing single-target methods., Comment: ECCV 2024

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary VIS attempts obtained unsatisfactory results, especially in terms of generalization ability of novel categories. We discover that the domain gap between the VLM features (e.g., CLIP) and the instance queries and the underutilization of temporal consistency are two central causes. To mitigate these issues, we design and train a novel Open-Vocabulary VIS baseline called OVFormer. OVFormer utilizes a lightweight module for unified embedding alignment between query embeddings and CLIP image embeddings to remedy the domain gap. Unlike previous image-based training methods, we conduct video-based model training and deploy a semi-online inference scheme to fully mine the temporal consistency in the video. Without bells and whistles, OVFormer achieves 21.9 mAP with a ResNet-50 backbone on LV-VIS, exceeding the previous state-of-the-art performance by 7.7. Extensive experiments on some Close-Vocabulary VIS datasets also demonstrate the strong zero-shot generalization ability of OVFormer (+ 7.6 mAP on YouTube-VIS 2019, + 3.9 mAP on OVIS). Code is available at https://github.com/fanghaook/OVFormer., Comment: ECCV 2024

Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided Video Segmentation track based on MeViS dataset. In the two new tracks, we provide additional videos and annotations that feature challenging elements, such as the disappearance and reappearance of objects, inconspicuous small objects, heavy occlusions, and crowded environments in MOSE. Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments. These new videos, sentences, and annotations enable us to foster the development of a more comprehensive and robust pixel-level understanding of video scenes in complex environments and realistic scenarios. The MOSE challenge had 140 registered teams in total, 65 teams participated the validation phase and 12 teams made valid submissions in the final challenge phase. The MeViS challenge had 225 registered teams in total, 50 teams participated the validation phase and 5 teams made valid submissions in the final challenge phase., Comment: MOSE Challenge: https://henghuiding.github.io/MOSE/ChallengeCVPR2024, MeViS Challenge: https://henghuiding.github.io/MeViS/ChallengeCVPR2024

In this paper, we study bi-Hermitian metrics on complex surfaces with split holomorphic tangent bundle and construct 2 types of metric cones. We introduce a new type of fully non-linear geometric PDE on such surfaces and establish smooth solutions. As a geometric application, we solve the prescribed Bismut Ricci problem. In various settings, we obtain canonical metrics on 2 important classes of complex surfaces: primary Hopf surfaces and Inoue surfaces of type $\mathcal{S}_{M}$., Comment: 41 pages

Efficient and robust grasp pose detection is vital for robotic manipulation. For general 6 DoF grasping, conventional methods treat all points in a scene equally and usually adopt uniform sampling to select grasp candidates. However, we discover that ignoring where to grasp greatly harms the speed and accuracy of current grasp pose detection methods. In this paper, we propose "graspness", a quality based on geometry cues that distinguishes graspable areas in cluttered scenes. A look-ahead searching method is proposed for measuring the graspness and statistical results justify the rationality of our method. To quickly detect graspness in practice, we develop a neural network named cascaded graspness model to approximate the searching process. Extensive experiments verify the stability, generality and effectiveness of our graspness model, allowing it to be used as a plug-and-play module for different methods. A large improvement in accuracy is witnessed for various previous methods after equipping our graspness model. Moreover, we develop GSNet, an end-to-end network that incorporates our graspness model for early filtering of low-quality predictions. Experiments on a large-scale benchmark, GraspNet-1Billion, show that our method outperforms previous arts by a large margin (30+ AP) and achieves a high inference speed. The library of GSNet has been integrated into AnyGrasp, which is at https://github.com/graspnet/anygrasp_sdk., Comment: ICCV 2021

Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current methods have integrated parameterization techniques to boost synthetic dataset performance by shifting the optimization space from pixel to another informative feature domain. However, they limit themselves to a fixed optimization space for distillation, neglecting the diverse guidance across different informative latent spaces. To overcome this limitation, we propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD), to systematically explore hierarchical layers within the generative adversarial networks (GANs). This allows us to progressively span from the initial latent space to the final pixel space. In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation, bridging the gap between synthetic and original datasets. Experimental results demonstrate that the proposed H-GLaD achieves a significant improvement in both same-architecture and cross-architecture performance with equivalent time consumption.

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studies have shown they are vulnerable to maliciously crafted adversarial samples. Despite recent success, these methods are generally instance-specific and require generating perturbations for each input sample. In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP). Specifically, we design a novel Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC) to achieve the attack. In light that the pivotal multimodal alignment is achieved through the advanced contrastive learning technique, we devise to turn this powerful weapon against themselves, i.e., employ a malicious version of contrastive learning to train the C-PGC based on our carefully crafted positive and negative image-text pairs for essentially destroying the alignment relationship learned by VLP models. Besides, C-PGC fully utilizes the characteristics of Vision-and-Language (V+L) scenarios by incorporating both unimodal and cross-modal information as effective guidance. Extensive experiments show that C-PGC successfully forces adversarial samples to move away from their original area in the VLP model's feature space, thus essentially enhancing attacks across various victim models and V+L tasks. The GitHub repository is available at https://github.com/ffhibnese/CPGC_VLP_Universal_Attacks.

Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video, emphasizing modeling dense text-video relations. The current RVOS methods typically use independently pre-trained vision and language models as backbones, resulting in a significant domain gap between video and text. In cross-modal feature interaction, text features are only used as query initialization and do not fully utilize important information in the text. In this work, we propose using frozen pre-trained vision-language models (VLM) as backbones, with a specific emphasis on enhancing cross-modal feature interaction. Firstly, we use frozen convolutional CLIP backbone to generate feature-aligned vision and text features, alleviating the issue of domain gap and reducing training costs. Secondly, we add more cross-modal feature fusion in the pipeline to enhance the utilization of multi-modal information. Furthermore, we propose a novel video query initialization method to generate higher quality video queries. Without bells and whistles, our method achieved 51.5 J&F on the MeViS test set and ranked 3rd place for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation.

Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable privacy concerns. A majority of gradient inversion methods rely heavily on explicit prior knowledge (e.g., a well pre-trained generative model), which is often unavailable in realistic scenarios. To alleviate this issue, researchers have proposed to leverage the implicit prior knowledge of an over-parameterized network. However, they only utilize a fixed neural architecture for all the attack settings. This would hinder the adaptive use of implicit architectural priors and consequently limit the generalizability. In this paper, we further exploit such implicit prior knowledge by proposing Gradient Inversion via Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures. Extensive experiments verify that our proposed GI-NAS can achieve superior attack performance compared to state-of-the-art gradient inversion methods, even under more practical settings with high-resolution images, large-sized batches, and advanced defense strategies.

In the past three years, working with the Pacific Salmon Foundation and various First Nations groups, we have established Starlink-empowered wild salmon monitoring sites in remote Northern British Columbia, Canada. We report our experiences with the network services in these challenging environments, including deep woods and deep valleys, that lack infrastructural support with some close to Starlink's service boundary at the far north. We assess the portability and mobility of the satellite dishes and the quality of existing network access in underdeveloped countries that Starlink expects to cover. Our experiences suggest that network access based on LEO satellite constellations holds promise but faces hurdles such as energy supply constraints and environmental factors like temperature, precipitation, and solar storms. The presence of wildlife and respecting local residents' culture and heritage pose further complications. We envision several technical solutions addressing the challenges and believe that further regulations will be necessary., Comment: 8 pages, 6 figures

Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually predict keyframes rather than continuous actions, posing difficulty in dynamic and contact-rich scenarios. To utilize 3D perception efficiently, we present RISE, an end-to-end baseline for real-world imitation learning, which predicts continuous actions directly from single-view point clouds. It compresses the point cloud to tokens with a sparse 3D encoder. After adding sparse positional encoding, the tokens are featurized using a transformer. Finally, the features are decoded into robot actions by a diffusion head. Trained with 50 demonstrations for each real-world task, RISE surpasses currently representative 2D and 3D policies by a large margin, showcasing significant advantages in both accuracy and efficiency. Experiments also demonstrate that RISE is more general and robust to environmental change compared with previous baselines. Project website: rise-policy.github.io., Comment: IROS 2024

Dexterous manipulation, particularly adept coordinating and grasping, constitutes a fundamental and indispensable capability for robots, facilitating the emulation of human-like behaviors. Integrating this capability into robots empowers them to supplement and even supplant humans in undertaking increasingly intricate tasks in both daily life and industrial settings. Unfortunately, contemporary methodologies encounter serious challenges in devising manipulation trajectories owing to the intricacies of tasks, the expansive robotic manipulation space, and dynamic obstacles. We propose a novel approach, APEX, to address all these difficulties by introducing a collision-free latent diffusion model for both robotic motion planning and manipulation. Firstly, we simplify the complexity of real-life ambidextrous dual-arm robotic manipulation tasks by abstracting them as aligning two vectors. Secondly, we devise latent diffusion models to produce a variety of robotic manipulation trajectories. Furthermore, we integrate obstacle information utilizing a classifier-guidance technique, thereby guaranteeing both the feasibility and safety of the generated manipulation trajectories. Lastly, we validate our proposed algorithm through extensive experiments conducted on the hardware platform of ambidextrous dual-arm robots. Our algorithm consistently generates successful and seamless trajectories across diverse tasks, surpassing conventional robotic motion planning algorithms. These results carry significant implications for the future design of diffusion robots, enhancing their capability to tackle more intricate robotic manipulation tasks with increased efficiency and safety. Complete video demonstrations of our experiments can be found in https://sites.google.com/view/apex-dual-arm/home., Comment: Under Review in IEEE IROS 2024