Search

Urban Air Mobility (UAM), powered by flying cars, is poised to revolutionize urban transportation by expanding vehicle travel from the ground to the air. This advancement promises to alleviate congestion and enable faster commutes. However, the fast travel speeds mean vehicles will encounter vastly different environments during a single journey. As a result, onboard learning systems need access to extensive environmental data, leading to high costs in data collection and training. These demands conflict with the limited in-vehicle computing and battery resources. Fortunately, learning model sharing offers a solution. Well-trained local Deep Learning (DL) models can be shared with other vehicles, reducing the need for redundant data collection and training. However, this sharing process relies heavily on efficient vehicular communications in UAM. To address these challenges, this paper leverages the multi-hop Reconfigurable Intelligent Surface (RIS) technology to improve DL model sharing between distant flying cars. We also employ knowledge distillation to reduce the size of the shared DL models and enable efficient integration of non-identical models at the receiver. Our approach enhances model sharing and onboard learning performance for cars entering new environments. Simulation results show that our scheme improves the total reward by 85% compared to benchmark methods., Comment: 13pages, 17 figures

An isolated attosecond vortex $\gamma$-ray pulse is generated by using a relativistic spatiotemporal optical vortex (STOV) laser in particle-in-cell simulations. A $\sim$ 300-attosecond electron slice with transverse orbital angular momentum (TOAM) is initially selected and accelerated by the central spatiotemporal singularity of the STOV laser. This slice then collides with the laser's reflected Gaussian-like front from a planar target, initiating nonlinear Compton scattering and resulting in an isolated, attosecond ($\sim$ 300 as), highly collimated ($\sim$ 4$\degree$), ultra-brilliant ($\sim 5\times 10^{24}$ photons/s/mm$^2$/mrad$^2$/0.1\%BW at 1 MeV) $\gamma$-ray pulse. This STOV-driven approach overcomes the significant beam divergence and complex two-laser requirements of prior Gaussian-based methods while introducting TOAM to the attosecond $\gamma$-ray pulse, which opens avenues for ultrafast imaging, nuclear excitation, and detection applications.

We study computational problems related to the Schr\"odinger operator $H = -\Delta + V$ in the real space under the condition that (i) the potential function $V$ is smooth and has its value and derivative bounded within some polynomial of $n$ and (ii) $V$ only consists of $O(1)$-body interactions. We prove that (i) simulating the dynamics generated by the Schr\"odinger operator implements universal quantum computation, i.e., it is BQP-hard, and (ii) estimating the ground energy of the Schr\"odinger operator is as hard as estimating that of local Hamiltonians with no sign problem (a.k.a. stoquastic Hamiltonians), i.e., it is StoqMA-complete. This result is particularly intriguing because the ground energy problem for general bosonic Hamiltonians is known to be QMA-hard and it is widely believed that $\texttt{StoqMA}\varsubsetneq \texttt{QMA}$., Comment: 32 pages, 5 figures, submitted to QIP 2025

Power electronic converters are gradually becoming the main components of modern power systems due to the increasing integration of renewable energy sources. However, power converters may become unstable when interacting with the complex and time-varying power grid. To deal with this problem, an adaptive control design scheme for power converters is preferable, which can capture the closed-loop dynamical interaction between the converter and the grid via online data. In this paper, we propose an adaptive data-driven control method, called data-enabled policy optimization (DeePO), to stabilize power converters by using only online input-output data. Our contributions are threefold. First, we propose a covariance parameterization of partially observed linear systems with input-output data. Second, we develop a DeePO algorithm, which updates the parameterized policy with data-based gradient descent to achieve computationally efficient adaptive control. Third, we use high-fidelity simulations to verify that DeePO can effectively stabilize grid-connected power converters and quickly adapt to the changes in the power grid.

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context lengths, there is a growing interest in understanding how these models perform in RAG scenarios. Can these new long context models improve RAG performance? This paper presents a comprehensive study of the impact of increased context length on RAG performance across 20 popular open source and commercial LLMs. We ran RAG workflows while varying the total context length from 2,000 to 128,000 tokens (and 2 million tokens when possible) on three domain-specific datasets, and report key insights on the benefits and limitations of long context in RAG applications. Our findings reveal that while retrieving more documents can improve performance, only a handful of the most recent state of the art LLMs can maintain consistent accuracy at long context above 64k tokens. We also identify distinct failure modes in long context scenarios, suggesting areas for future research., Comment: 2024 NeurIPS workshop on Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning

This technical report outlines the methodologies we applied for the PRCV Challenge, focusing on cognition and decision-making in driving scenarios. We employed InternVL-2.0, a pioneering open-source multi-modal model, and enhanced it by refining both the model input and training methodologies. For the input data, we strategically concatenated and formatted the multi-view images. It is worth mentioning that we utilized the coordinates of the original images without transformation. In terms of model training, we initially pre-trained the model on publicly available autonomous driving scenario datasets to bolster its alignment capabilities of the challenge tasks, followed by fine-tuning on the DriveLM-nuscenes Dataset. During the fine-tuning phase, we innovatively modified the loss function to enhance the model's precision in predicting coordinate values. These approaches ensure that our model possesses advanced cognitive and decision-making capabilities in driving scenarios. Consequently, our model achieved a score of 0.6064, securing the first prize on the competition's final results.

As industrial models and designs grow increasingly complex, the demand for optimal control of large-scale dynamical systems has significantly increased. However, traditional methods for optimal control incur significant overhead as problem dimensions grow. In this paper, we introduce an end-to-end quantum algorithm for linear-quadratic control with provable speedups. Our algorithm, based on a policy gradient method, incorporates a novel quantum subroutine for solving the matrix Lyapunov equation. Specifically, we build a quantum-assisted differentiable simulator for efficient gradient estimation that is more accurate and robust than classical methods relying on stochastic approximation. Compared to the classical approaches, our method achieves a super-quadratic speedup. To the best of our knowledge, this is the first end-to-end quantum application to linear control problems with provable quantum advantage.

Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics., Comment: 9 Pages, 3 Figures, GTA3 Workshop-2024, October 2024, 33rd International Conference on Information and Knowledge Management, Boise, Idaho, USA

Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $\mu$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on.

In sensor networks characterized by irregular layouts and poor connectivity, anisotropic properties can significantly reduce the accuracy of distance estimation between nodes, consequently impairing the localization precision of unidentified nodes. Since distance estimation is contingent upon the multi-hop paths between anchor node pairs, assigning differential weights based on the reliability of these paths could enhance localization accuracy. To address this, we introduce an adaptive weighted method, termed AW-MinMax, for range-free node localization. This method involves constructing a weighted mean nodes localization model, where each multi-hop path weight is inversely proportional to the number of hops. Despite the model's inherent non-convexity and non-differentiability, it can be reformulated into an optimization model with convex objective functions and non-convex constraints through matrix transformations. To resolve these constraints, we employ a Sequential Convex Approximation (SCA) algorithm that utilizes first-order Taylor expansion for iterative refinement. Simulation results validate that our proposed algorithm substantially improves stability and accuracy in estimating range-free node locations.

Medical Vision-Language Pretraining (MedVLP) shows promise in learning generalizable and transferable visual representations from paired and unpaired medical images and reports. MedVLP can provide useful features to downstream tasks and facilitate adapting task-specific models to new setups using fewer examples. However, existing MedVLP methods often differ in terms of datasets, preprocessing, and finetuning implementations. This pose great challenges in evaluating how well a MedVLP method generalizes to various clinically-relevant tasks due to the lack of unified, standardized, and comprehensive benchmark. To fill this gap, we propose BenchX, a unified benchmark framework that enables head-to-head comparison and systematical analysis between MedVLP methods using public chest X-ray datasets. Specifically, BenchX is composed of three components: 1) Comprehensive datasets covering nine datasets and four medical tasks; 2) Benchmark suites to standardize data preprocessing, train-test splits, and parameter selection; 3) Unified finetuning protocols that accommodate heterogeneous MedVLP methods for consistent task adaptation in classification, segmentation, and report generation, respectively. Utilizing BenchX, we establish baselines for nine state-of-the-art MedVLP methods and found that the performance of some early MedVLP methods can be enhanced to surpass more recent ones, prompting a revisiting of the developments and conclusions from prior works in MedVLP. Our code are available at https://github.com/yangzhou12/BenchX., Comment: Accepted to NeurIPS24 Datasets and Benchmarks Track

Sleep monitoring plays a crucial role in maintaining good health, with sleep staging serving as an essential metric in the monitoring process. Traditional methods, utilizing medical sensors like EEG and ECG, can be effective but often present challenges such as unnatural user experience, complex deployment, and high costs. Ballistocardiography~(BCG), a type of piezoelectric sensor signal, offers a non-invasive, user-friendly, and easily deployable alternative for long-term home monitoring. However, reliable BCG-based sleep staging is challenging due to the limited sleep monitoring data available for BCG. A restricted training dataset prevents the model from generalization across populations. Additionally, transferring to BCG faces difficulty ensuring model robustness when migrating from other data sources. To address these issues, we introduce SleepNetZero, a zero-shot learning based approach for sleep staging. To tackle the generalization challenge, we propose a series of BCG feature extraction methods that align BCG components with corresponding respiratory, cardiac, and movement channels in PSG. This allows models to be trained on large-scale PSG datasets that are diverse in population. For the migration challenge, we employ data augmentation techniques, significantly enhancing generalizability. We conducted extensive training and testing on large datasets~(12393 records from 9637 different subjects), achieving an accuracy of 0.803 and a Cohen's Kappa of 0.718. ZeroSleepNet was also deployed in real prototype~(monitoring pads) and tested in actual hospital settings~(265 users), demonstrating an accuracy of 0.697 and a Cohen's Kappa of 0.589. To the best of our knowledge, this work represents the first known reliable BCG-based sleep staging effort and marks a significant step towards in-home health monitoring., Comment: 25 pages

Spiking Neural Networks (SNNs) are considered as a potential candidate for the next generation of artificial intelligence with appealing characteristics such as sparse computation and inherent temporal dynamics. By adopting architectures of Artificial Neural Networks (ANNs), SNNs achieve competitive performances on benchmark tasks like image classification. However, successful architectures of ANNs are not optimal for SNNs. In this work, we apply Neural Architecture Search (NAS) to find suitable architectures for SNNs. Previous NAS methods for SNNs focus primarily on the spatial dimension, with a notable lack of consideration for the temporal dynamics that are of critical importance for SNNs. Drawing inspiration from the heterogeneity of biological neural networks, we propose a differentiable approach to optimize SNN on both spatial and temporal dimensions. At spatial level, we have developed a spike-based differentiable hierarchical search (SpikeDHS) framework, where spike-based operation is optimized on both the cell and the layer level under computational constraints. We further propose a differentiable surrogate gradient search (DGS) method to evolve local SG functions independently during training. At temporal level, we explore an optimal configuration of diverse temporal dynamics on different types of spiking neurons by evolving their time constants, based on which we further develop hybrid networks combining SNN and ANN, balancing both accuracy and efficiency. Our methods achieve comparable classification performance of CIFAR10/100 and ImageNet with accuracies of 96.43%, 78.96%, and 70.21%, respectively. On event-based deep stereo, our methods find optimal layer variation and surpass the accuracy of specially designed ANNs with 26$\times$ lower computational cost ($6.7\mathrm{mJ}$), demonstrating the potential of SNN in processing highly sparse and dynamic signals.

The escalating significance of information security has underscored the per-vasive role of encryption technology in safeguarding communication con-tent. Morse code, a well-established and effective encryption method, has found widespread application in telegraph communication and various do-mains. However, the transmission of Morse code images faces challenges due to diverse noises and distortions, thereby hindering comprehensive clas-sification outcomes. Existing methodologies predominantly concentrate on categorizing Morse code images affected by a single type of noise, neglecting the multitude of scenarios that noise pollution can generate. To overcome this limitation, we propose a novel two-stage approach, termed the Noise Adaptation Network (NANet), for Morse code image classification. Our method involves exclusive training on pristine images while adapting to noisy ones through the extraction of critical information unaffected by noise. In the initial stage, we introduce a U-shaped network structure designed to learn representative features and denoise images. Subsequently, the second stage employs a deep convolutional neural network for classification. By leveraging the denoising module from the first stage, our approach achieves enhanced accuracy and robustness in the subsequent classification phase. We conducted an evaluation of our approach on a diverse dataset, encom-passing Gaussian, salt-and-pepper, and uniform noise variations. The results convincingly demonstrate the superiority of our methodology over existing approaches. The datasets are available on https://github.com/apple1986/MorseCodeImageClassify, Comment: 8 pages, 3 figures

Contrastive loss is a powerful approach for representation learning, where larger batch sizes enhance performance by providing more negative samples to better distinguish between similar and dissimilar data. However, scaling batch sizes is constrained by the quadratic growth in GPU memory consumption, primarily due to the full instantiation of the similarity matrix. To address this, we propose a tile-based computation strategy that partitions the contrastive loss calculation into arbitrary small blocks, avoiding full materialization of the similarity matrix. Furthermore, we introduce a multi-level tiling strategy to leverage the hierarchical structure of distributed systems, employing ring-based communication at the GPU level to optimize synchronization and fused kernels at the CUDA core level to reduce I/O overhead. Experimental results show that the proposed method scales batch sizes to unprecedented levels. For instance, it enables contrastive training of a CLIP-ViT-L/14 model with a batch size of 4M or 12M using 8 or 32 A800 80GB without sacrificing any accuracy. Compared to SOTA memory-efficient solutions, it achieves a two-order-of-magnitude reduction in memory while maintaining comparable speed. The code will be made publicly available.

The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing, inconsistent lighting, conflicting view angles, etc. To effectively address these issues, we propose a \textbf{Hi}erarchical \textbf{Co}ntrollable (HiCo) diffusion model for layout-to-image generation, featuring object seperable conditioning branch structure. Our key insight is to achieve spatial disentanglement through hierarchical modeling of layouts. We use a multi branch structure to represent hierarchy and aggregate them in fusion module. To evaluate the performance of multi-objective controllable layout generation in natural scenes, we introduce the HiCo-7K benchmark, derived from the GRIT-20M dataset and manually cleaned. https://github.com/360CVGroup/HiCo_T2I., Comment: NeurIPS2024

As large language models (LLMs) become increasingly accessible in many countries, it is essential to align them to serve pluralistic human values across cultures. However, pluralistic culture alignment in LLMs remain an open problem. In this paper, we propose CultureSPA, a Self-Pluralising Culture Alignment framework that allows LLMs to simultaneously align to pluralistic cultures. The framework first generates questions on various culture topics, then yields LLM outputs in response to these generated questions under both culture-aware and culture-unaware settings. By comparing culture-aware/unaware outputs, we are able to detect and collect culture-related instances. These instances are employed to fine-tune LLMs to serve pluralistic cultures in either a culture-joint or culture-specific way. Extensive experiments demonstrate that CultureSPA significantly improves the alignment of LLMs to diverse cultures without compromising general abilities. And further improvements can be achieved if CultureSPA is combined with advanced prompt engineering techniques. Comparisons between culture-joint and culture-specific tuning strategies, along with variations in data quality and quantity, illustrate the robustness of our method. We also explore the mechanisms underlying CultureSPA and the relations between different cultures it reflects., Comment: Implementation for the paper: https://github.com/shaoyangxu/CultureSPA

Recent advancements in large multimodal models (LMMs) have significantly enhanced performance across diverse tasks, with ongoing efforts to further integrate additional modalities such as video and audio. However, most existing LMMs remain vulnerable to hallucinations, the discrepancy between the factual multimodal input and the generated textual output, which has limited their applicability in various real-world scenarios. This paper presents the first systematic investigation of hallucinations in LMMs involving the three most common modalities: language, visual, and audio. Our study reveals two key contributors to hallucinations: overreliance on unimodal priors and spurious inter-modality correlations. To address these challenges, we introduce the benchmark The Curse of Multi-Modalities (CMM), which comprehensively evaluates hallucinations in LMMs, providing a detailed analysis of their underlying issues. Our findings highlight key vulnerabilities, including imbalances in modality integration and biases from training data, underscoring the need for balanced cross-modal learning and enhanced hallucination mitigation strategies. Based on our observations and findings, we suggest potential research directions that could enhance the reliability of LMMs., Comment: Project Page: cmm-damovl.site

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that LLMs trained with Reinforcement Learning from Human Feedback (RLHF) are overconfident with a more sharpened output probability, in this study, we reveal that RLHF tends to lead models to express verbalized overconfidence in their own responses. We investigate the underlying cause of this overconfidence and demonstrate that reward models used for Proximal Policy Optimization (PPO) exhibit inherent biases towards high-confidence scores regardless of the actual quality of responses. Building upon this insight, we propose two PPO variants: PPO-M: PPO with Calibrated Reward Modeling and PPO-C: PPO with Calibrated Reward Calculation. PPO-M integrates explicit confidence scores in reward model training, which calibrates reward models to better capture the alignment between response quality and verbalized confidence. PPO-C adjusts the reward score during PPO based on the difference between the current reward and the moving average of past rewards. Both PPO-M and PPO-C can be seamlessly integrated into the current PPO pipeline and do not require additional golden labels. We evaluate our methods on both Llama3-8B and Mistral-7B across six diverse datasets including multiple-choice and open-ended generation. Experiment results demonstrate that both of our methods can reduce calibration error and maintain performance comparable to standard PPO. We further show that they do not compromise model capabilities in open-ended conversation settings.

We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation modes: for instance, when the articulation direction (e.g. push, pull, slide) or location (e.g. left side, right side) of a fully closed door are uncertain, or when distinguishing features like the plane of the door are occluded due to the viewing angle. To tackle these challenges, we propose a history-aware diffusion network that can model multi-modal distributions over articulation modes for articulated objects; our method further uses observation history to distinguish between modes and make stable predictions under occlusions. Experiments and analysis demonstrate that our method achieves state-of-art performance on articulated object manipulation and dramatically improves performance for articulated objects containing visual ambiguities. Our project website is available at https://flowbothd.github.io/., Comment: Accepted to CoRL 2024

Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on long sequential tasks, until the recent emergence of state space models (SSMs), which offer superior computational efficiency and modeling capability. However, applying the highly capable SSMs to SNNs for long sequences learning poses three major challenges: (1) The membrane potential is determined by the past spiking history of the neuron, leading to reduced efficiency for sequence modeling in parallel computing scenarios. (2) Complex dynamics of biological spiking neurons are crucial for functionality but challenging to simulate and exploit effectively in large networks. (3) It is arduous to maintain high sparsity while achieving high accuracy for spiking neurons without resorting to dense computing, as utilized in artificial neuron-based SSMs. To address them, we propose a sparse, precise and efficient spiking SSM framework, termed SPikE-SSM. For (1), we propose a boundary compression strategy (PMBC) to accelerate the inference of the spiking neuron model, enabling parallel processing for long sequence learning. For (2), we propose a novel and concise neuron model incorporating reset-refractory mechanism to leverage the inherent temporal dimension for dynamic computing with biological interpretability. For (3), we hierarchically integrate the proposed neuron model to the original SSM block, and enhance the dynamics of SPikE-SSM by incorporating trainable thresholds and refractory magnitudes to balance accuracy and sparsity. Extensive experiments verify the effectiveness and robustness of SPikE-SSM on the long range arena benchmarks and large language dataset WikiText-103, showing the potential of dynamic spiking neurons in efficient long sequence learning., Comment: 23 pages, 5 figures

The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the models. Despite its critical role in model performance, ensuring the quality of this data is challenging due to its sheer volume and the absence of sample-level quality annotations and enhancements. In this paper, we introduce DecorateLM, a data engineering method designed to refine the pretraining corpus through data rating, tagging and editing. Specifically, DecorateLM rates texts against quality criteria, tags texts with hierarchical labels, and edits texts into a more formalized format. Due to the massive size of the pretraining corpus, adopting an LLM for decorating the entire corpus is less efficient. Therefore, to balance performance with efficiency, we curate a meticulously annotated training corpus for DecorateLM using a large language model and distill data engineering expertise into a compact 1.2 billion parameter small language model (SLM). We then apply DecorateLM to enhance 100 billion tokens of the training corpus, selecting 45 billion tokens that exemplify high quality and diversity for the further training of another 1.2 billion parameter LLM. Our results demonstrate that employing such high-quality data can significantly boost model performance, showcasing a powerful approach to enhance the quality of the pretraining corpus.

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first train a teacher model to create fair representation and then distil the knowledge to a student model (using a smaller architecture). The process of distilling the student model is data-free, i.e. the student model does not have access to the training dataset while distilling. After the distillation, we use the distilled model to generate fair synthetic samples. Our extensive experiments show that our synthetic samples outperform state-of-the-art models in all three criteria (fairness, utility and synthetic quality) with a performance increase of 5% for fairness, 8% for utility and 12% in synthetic quality for both tabular and image datasets.

A plasma mirror is an optical device for high-power, ultrashort-wavelength electromagnetic fields, utilizing a sheet of relativistic oscillating electrons to generate and manipulate light. In this work, we propose that the spatiotemporally varying plasma oscillation, induced by an ultra-high-intensity laser beam, functions as a "spacetime mirror" with significant potential for exploring quantum light. We find that the spacetime mirror exhibits several exotic features: (i) a superluminal spacetime boundary, (ii) time reflection and refraction, and (iii) quantum light sources with pair generation. Our theoretical and simulation results are in excellent agreement, and experimental verification is underway. Our work demonstrates the interplay with emerging fields such as time varying media, suggesting the plasma mirror as an ideal platform to study strong-field quantum optics at extremes., Comment: 36 pages, 4 figures, SM file, 5 suppl. figures

The hip joint moment during walking is a crucial basis for hip exoskeleton control. Compared to generating assistive torque profiles based on gait estimation, estimating hip joint moment directly using hip joint angles offers advantages such as simplified sensing and adaptability to variable walking speeds. Existing methods that directly estimate moment from hip joint angles are mainly used for offline biomechanical estimation. However, they suffer from long computation time and lack of personalization, rendering them unsuitable for personalized control of hip exoskeletons. To address these challenges, this paper proposes a fast hip joint moment estimation method based on generalized moment features (GMF). The method first employs a GMF generator to learn a feature representation of joint moment, namely the proposed GMF, which is independent of individual differences. Subsequently, a GRU-based neural network with fast computational performance is trained to learn the mapping from the joint kinematics to the GMF. Finally, the predicted GMF is decoded into the joint moment with a GMF decoder. The joint estimation model is trained and tested on a dataset comprising 20 subjects under 28 walking speed conditions. Results show that the proposed method achieves a root mean square error of 0.1180 $\pm$ 0.0021 Nm/kg for subjects in test dataset, and the computation time per estimation using the employed GRU-based estimator is 1.3420 $\pm$ 0.0031 ms, significantly faster than mainstream neural network architectures, while maintaining comparable network accuracy. These promising results demonstrate that the proposed method enhances the accuracy and computational speed of joint moment estimation neural networks, with potential for guiding exoskeleton control.

While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DSRL) method for weakly supervised VVD to utilize the strength of both Euclidean and hyperbolic geometries, capturing the visual features of events while also exploring the intrinsic relations between events, thereby enhancing the discriminative capacity of the features. DSRL employs a novel information aggregation strategy to progressively learn event context in hyperbolic spaces, which selects aggregation nodes through layer-sensitive hyperbolic association degrees constrained by hyperbolic Dirichlet energy. Furthermore, DSRL attempts to break the cyber-balkanization of different spaces, utilizing cross-space attention to facilitate information interactions between Euclidean and hyperbolic space to capture better discriminative features for final violence detection. Comprehensive experiments demonstrate the effectiveness of our proposed DSRL., Comment: Accepted by NeurIPS 2024

Urban Air Mobility (UAM) relies on developing aerospace industries, where safe aviation and efficient communication are critical features of aircraft. However, it is challenging for aircraft to sustain efficient air-ground communication in urban circumstances. Without continuous air-ground communication, aircraft may experience course deviation and safety accidents. To address these problems, a reconfigurable intelligent surface(RIS)-aided trajectory optimization scheme is proposed enabling efficient air-ground communication and safe aviation in UAM with a layered airspace structure. This paper first devises a dual-plane RIS communication scheme for layered airspace. It fully engages the omnidirectional and directional signal attributes to reduce the transmission delay of the air-ground communication. Based on the dual-plane RIS configuration, we jointly develop the intra- and inter-layer trajectory scheme to optimize communication and safe aviation. In the intra-layer trajectory optimization, we propose a dual-time-scale flight scheme to improve communication capacity and horizontal flight safety. Meanwhile, we propose a safe layer-switching method to ensure collision avoidance during vertical flight in the inter-layer trajectory optimization. The communication load of the proposed scheme can be improved 40% and the time of safe separation restoration can be lessened 66% compared with the benchmarks in the layered airspace., Comment: 15 pages, 13 figures

Rayleigh-Taylor (RT) instability occurs in a variety of scenario as a consequence of fluids of different densities pushing against the density gradient. For example, it is expected to occur in the ion acceleration of solid density targets driven by high intensity lasers and is crucial for the acceleration process. Yet, it is essential to understand the dynamics of the RT instability, a typical way to measure this phenomenon requires sophisticated diagnostics such as streak X ray radiography. Here, we report on experimental observation on periodic modulation in the energy spectrum of laser accelerated proton beams. Interestingly, theoretical model and two-dimensional particle-in-cell simulations, in good agreement with the experimental finding, indicated that such modulation is associated with periodic modulated electron density induced by transverse Rayleigh-Taylor-like instability. Furthermore, the correlation between the RT instability and the ion acceleration provides an interpretation to trace the development of the RT instability from the modulated proton spectrum. Our results thus suggest a possible tool to diagnose the evolution of the RT instability, and may have implications for further understanding for the accelerating mechanisms as well as optimization strategies for laser driven ion acceleration.

In this technical report, we describe the SNTL-NTU team's submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the detection and classification of acoustic scenes and events (DCASE) 2024 challenge. Three systems are introduced to tackle training splits of different sizes. For small training splits, we explored reducing the complexity of the provided baseline model by reducing the number of base channels. We introduce data augmentation in the form of mixup to increase the diversity of training samples. For the larger training splits, we use FocusNet to provide confusing class information to an ensemble of multiple Patchout faSt Spectrogram Transformer (PaSST) models and baseline models trained on the original sampling rate of 44.1 kHz. We use Knowledge Distillation to distill the ensemble model to the baseline student model. Training the systems on the TAU Urban Acoustic Scene 2022 Mobile development dataset yielded the highest average testing accuracy of (62.21, 59.82, 56.81, 53.03, 47.97)% on split (100, 50, 25, 10, 5)% respectively over the three systems., Comment: 5 pages, 3 figures

Sound event localization and detection (SELD) is critical for various real-world applications, including smart monitoring and Internet of Things (IoT) systems. Although deep neural networks (DNNs) represent the state-of-the-art approach for SELD, their significant computational complexity and model sizes present challenges for deployment on resource-constrained edge devices, especially under real-time conditions. Despite the growing need for real-time SELD, research in this area remains limited. In this paper, we investigate the unique challenges of deploying SELD systems for real-world, real-time applications by performing extensive experiments on a commercially available Raspberry Pi 3 edge device. Our findings reveal two critical, often overlooked considerations: the high computational cost of feature extraction and the performance degradation associated with low-latency, real-time inference. This paper provides valuable insights and considerations for future work toward developing more efficient and robust real-time SELD systems, Comment: Submitted to ICASSP'25. Code is available at this link : https://github.com/itsjunwei/Realtime-SELD-Edge

In the medical domain, acquiring large datasets poses significant challenges due to privacy concerns. Nonetheless, the development of a robust deep-learning model for retinal disease diagnosis necessitates a substantial dataset for training. The capacity to generalize effectively on smaller datasets remains a persistent challenge. The scarcity of data presents a significant barrier to the practical implementation of scalable medical AI solutions. To address this issue, we've combined a wide range of data sources to improve performance and generalization to new data by giving it a deeper understanding of the data representation from multi-modal datasets and developed a self-supervised framework based on large language models (LLMs), SwinV2 to gain a deeper understanding of multi-modal dataset representations, enhancing the model's ability to extrapolate to new data for the detection of eye diseases using optical coherence tomography (OCT) images. We adopt a two-phase training methodology, self-supervised pre-training, and fine-tuning on a downstream supervised classifier. An ablation study conducted across three datasets employing various encoder backbones, without data fusion, with low data availability setting, and without self-supervised pre-training scenarios, highlights the robustness of our method. Our findings demonstrate consistent performance across these diverse conditions, showcasing superior generalization capabilities compared to the baseline model, ResNet-50., Comment: 25 pages, 9 tables, 10 figures

The Agatston score, which is the sum of the calcification in the four main coronary arteries, has been widely used in the diagnosis of coronary artery disease (CAD). However, many studies have emphasized the importance of the vessel-specific Agatston score, as calcification in a specific vessel is significantly correlated with the occurrence of coronary heart disease (CHD). In this paper, we propose the Residual-block Inspired Coordinate Attention U-Net (RICAU-Net), which incorporates coordinate attention in two distinct manners and a customized combo loss function for lesion-specific coronary artery calcium (CAC) segmentation. This approach aims to tackle the high class-imbalance issue associated with small and sparse CAC lesions. Experimental results and the ablation study demonstrate that the proposed method outperforms the four other U-Net based methods used in medical applications, by achieving the highest per-lesion Dice scores across all four lesions., Comment: This work has been submitted to the IEEE for possible publication

Let $g$ be sufficiently large, $b\in\{0,\ldots,g-1\}$, and $\mathcal{S}_b$ be the set of integers with no digit equal to $b$ in their base $g$ expansion. We prove that every sufficiently large odd integer $N$ can be written as $p_1 + p_2 + p_3$ where $p_i$ are prime and $p_i\in \mathcal{S}_b$., Comment: 32 pages

Helmet-mounted wearable positioning systems are crucial for enhancing safety and facilitating coordination in industrial, construction, and emergency rescue environments. These systems, including LiDAR-Inertial Odometry (LIO) and Visual-Inertial Odometry (VIO), often face challenges in localization due to adverse environmental conditions such as dust, smoke, and limited visual features. To address these limitations, we propose a novel head-mounted Inertial Measurement Unit (IMU) dataset with ground truth, aimed at advancing data-driven IMU pose estimation. Our dataset captures human head motion patterns using a helmet-mounted system, with data from ten participants performing various activities. We explore the application of neural networks, specifically Long Short-Term Memory (LSTM) and Transformer networks, to correct IMU biases and improve localization accuracy. Additionally, we evaluate the performance of these methods across different IMU data window dimensions, motion patterns, and sensor types. We release a publicly available dataset, demonstrate the feasibility of advanced neural network approaches for helmet-based localization, and provide evaluation metrics to establish a baseline for future studies in this field. Data and code can be found at \url{https://lqiutong.github.io/HelmetPoser.github.io/}.

Mathematical reasoning remains an ongoing challenge for AI models, especially for geometry problems that require both linguistic and visual signals. As the vision encoders of most MLLMs are trained on natural scenes, they often struggle to understand geometric diagrams, performing no better in geometry problem solving than LLMs that only process text. This limitation is amplified by the lack of effective methods for representing geometric relationships. To address these issues, we introduce the Diagram Formalization Enhanced Geometry Problem Solver (DFE-GPS), a new framework that integrates visual features, geometric formal language, and natural language representations. We propose a novel synthetic data approach and create a large-scale geometric dataset, SynthGeo228K, annotated with both formal and natural language captions, designed to enhance the vision encoder for a better understanding of geometric structures. Our framework improves MLLMs' ability to process geometric diagrams and extends their application to open-ended tasks on the formalgeo7k dataset.

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity. To address this redundancy, we propose the Proxy-Tokenized Diffusion Transformer (PT-DiT), which employs sparse representative token attention (where the number of representative tokens is much smaller than the total number of tokens) to model global visual information efficiently. Specifically, within each transformer block, we compute an averaging token from each spatial-temporal window to serve as a proxy token for that region. The global semantics are captured through the self-attention of these proxy tokens and then injected into all latent tokens via cross-attention. Simultaneously, we introduce window and shift window attention to address the limitations in detail modeling caused by the sparse attention mechanism. Building on the well-designed PT-DiT, we further develop the Qihoo-T2X family, which includes a variety of models for T2I, T2V, and T2MV tasks. Experimental results show that PT-DiT achieves competitive performance while reducing the computational complexity in both image and video generation tasks (e.g., a 49% reduction compared to DiT and a 34% reduction compared to PixArt-$\alpha$). The visual exhibition and source code of Qihoo-T2X is available at https://360cvgroup.github.io/Qihoo-T2X/.

We develop an open-source, end-to-end software (named QHDOPT), which can solve nonlinear optimization problems using the quantum Hamiltonian descent (QHD) algorithm. QHDOPT offers an accessible interface and automatically maps tasks to various supported quantum backends (i.e., quantum hardware machines). These features enable users, even those without prior knowledge or experience in quantum computing, to utilize the power of existing quantum devices for nonlinear and nonconvex optimization tasks. In its intermediate compilation layer, QHDOPT employs SimuQ, an efficient interface for Hamiltonian-oriented programming, to facilitate multiple algorithmic specifications and ensure compatible cross-hardware deployment. The detailed documentation of QHDOPT is available at https://github.com/jiaqileng/QHDOPT., Comment: 23 pages, 7 figures. The full repository is available at https://github.com/jiaqileng/QHDOPT

Dynamic-shape deep neural networks (DNNs) are rapidly evolving, attracting attention for their ability to handle variable input sizes in real-time applications. However, existing compilation optimization methods for such networks often rely heavily on predefined samples to guide the compilation process, which restricts their adaptability and efficiency. These sample-driven methods struggle to efficiently manage the diverse and unpredictable shapes encountered in real-world scenarios, often resulting in suboptimal performance. To tackle these issues, we introduce Vortex, a hardware-driven and sample-free compiler tailored for dynamic-shape tensor programs. Vortex capitalizes on detailed hardware information and hierarchizes the strategy space to facilitate high-performance code generation without relying on runtime shape samples. It features a unique bidirectional compilation workflow, combining top-down abstraction for aligning tensor program execution with hardware hierarchies and bottom-up kernel construction to narrow the search space, enabling Vortex to achieve remarkable efficiency. Comprehensive evaluations confirm that Vortex reduces compilation time by $176\times$ compared to the existing dynamic-shape compiler. Additionally, it substantially outperforms existing vendor-provided libraries and dynamic-shape compilers on both CPU and GPU platforms, delivering speedups of $2.53\times$ and $3.01\times$, respectively.

This paper presents the development of a Physics-realistic and Photo-\underline{r}ealistic humanoid robot testbed, PR2, to facilitate collaborative research between Embodied Artificial Intelligence (Embodied AI) and robotics. PR2 offers high-quality scene rendering and robot dynamic simulation, enabling (i) the creation of diverse scenes using various digital assets, (ii) the integration of advanced perception or foundation models, and (iii) the implementation of planning and control algorithms for dynamic humanoid robot behaviors based on environmental feedback. The beta version of PR2 has been deployed for the simulation track of a nationwide full-size humanoid robot competition for college students, attracting 137 teams and over 400 participants within four months. This competition covered traditional tasks in bipedal walking, as well as novel challenges in loco-manipulation and language-instruction-based object search, marking a first for public college robotics competitions. A retrospective analysis of the competition suggests that future events should emphasize the integration of locomotion with manipulation and perception. By making the PR2 testbed publicly available at https://github.com/pr2-humanoid/PR2-Platform, we aim to further advance education and training in humanoid robotics.

Known as low energy consumption networks, spiking neural networks (SNNs) have gained a lot of attention within the past decades. While SNNs are increasing competitive with artificial neural networks (ANNs) for vision tasks, they are rarely used for long sequence tasks, despite their intrinsic temporal dynamics. In this work, we develop spiking state space models (SpikingSSMs) for long sequence learning by leveraging on the sequence learning abilities of state space models (SSMs). Inspired by dendritic neuron structure, we hierarchically integrate neuronal dynamics with the original SSM block, meanwhile realizing sparse synaptic computation. Furthermore, to solve the conflict of event-driven neuronal dynamics with parallel computing, we propose a light-weight surrogate dynamic network which accurately predicts the after-reset membrane potential and compatible to learnable thresholds, enabling orders of acceleration in training speed compared with conventional iterative methods. On the long range arena benchmark task, SpikingSSM achieves competitive performance to state-of-the-art SSMs meanwhile realizing on average 90\% of network sparsity. On language modeling, our network significantly surpasses existing spiking large language models (spikingLLMs) on the WikiText-103 dataset with only a third of the model size, demonstrating its potential as backbone architecture for low computation cost LLMs.

High-power broadband tunable long-wavelength infrared (LWIR) femtosecond lasers operating at fingerprint wavelengths of 7-14 {\mu}m hold significant promise across a range of applications, including molecular hyperspectral imaging, strong-field light-matter interaction, and resonant tissue ablation. Here we present 6-12 {\mu}m broadband tunable parametric amplifier based on LiGaS2 or BaGa4S7, generating new record output power of 2.4 W at 7.5 {\mu}m, and 1.5 W at 9.5 {\mu}m, pumped by a simple and effective thin-square-rod Yb:YAG amplifier producing 110 W 274 fs output pulses. As a proof of concept, we showcase efficient resonant ablation and microstructure fabrication on enamel at the hydroxyapatite resonant wavelength of 9.5 {\mu}m, with a laser intensity two orders-of-magnitude lower than that required by non-resonant femtosecond lasers, which could foster more precision surgical applications with superior biosafety.

In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models are available at https://github.com/360CVGroup/Inner-Adaptor-Architecture.

Data Fairness is a crucial topic due to the recent wide usage of AI powered applications. Most of the real-world data is filled with human or machine biases and when those data are being used to train AI models, there is a chance that the model will reflect the bias in the training data. Existing bias-mitigating generative methods based on GANs, Diffusion models need in-processing fairness objectives and fail to consider computational overhead while choosing computationally-heavy architectures, which may lead to high computational demands, instability and poor optimization performance. To mitigate this issue, in this work, we present a fair data generation technique based on knowledge distillation, where we use a small architecture to distill the fair representation in the latent space. The idea of fair latent space distillation enables more flexible and stable training of Fair Generative Models (FGMs). We first learn a syntax-agnostic (for any data type) fair representation of the data, followed by distillation in the latent space into a smaller model. After distillation, we use the distilled fair latent space to generate high-fidelity fair synthetic data. While distilling, we employ quality loss (for fair distillation) and utility loss (for data utility) to ensure that the fairness and data utility characteristics remain in the distilled latent space. Our approaches show a 5%, 5% and 10% rise in performance in fairness, synthetic sample quality and data utility, respectively, than the state-of-the-art fair generative model.

What a large language model (LLM) would respond in ethically relevant context? In this paper, we curate a large benchmark CMoralEval for morality evaluation of Chinese LLMs. The data sources of CMoralEval are two-fold: 1) a Chinese TV program discussing Chinese moral norms with stories from the society and 2) a collection of Chinese moral anomies from various newspapers and academic papers on morality. With these sources, we aim to create a moral evaluation dataset characterized by diversity and authenticity. We develop a morality taxonomy and a set of fundamental moral principles that are not only rooted in traditional Chinese culture but also consistent with contemporary societal norms. To facilitate efficient construction and annotation of instances in CMoralEval, we establish a platform with AI-assisted instance generation to streamline the annotation process. These help us curate CMoralEval that encompasses both explicit moral scenarios (14,964 instances) and moral dilemma scenarios (15,424 instances), each with instances from different data sources. We conduct extensive experiments with CMoralEval to examine a variety of Chinese LLMs. Experiment results demonstrate that CMoralEval is a challenging benchmark for Chinese LLMs. The dataset is publicly available at \url{https://github.com/tjunlp-lab/CMoralEval}., Comment: Accepted by ACL 2024 (Findings)

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text control, equivalently guiding different frame generations without frame-specific textual guidance. Thus, the model's capacity to comprehend the temporal logic conveyed in prompts and generate videos with coherent motion is restricted. To tackle this limitation, we introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism with the well-designed Cross-frame Textual Guidance Module (CTGM). Specifically, CTGM incorporates the Temporal Information Injector (TII), Temporal Affinity Refiner (TAR), and Temporal Feature Booster (TFB) at the beginning, middle, and end of cross-attention, respectively, to achieve frame-specific textual guidance. Firstly, TII injects frame-specific information from latent features into text conditions, thereby obtaining cross-frame textual conditions. Then, TAR refines the correlation matrix between cross-frame textual conditions and latent features along the time dimension. Lastly, TFB boosts the temporal consistency of latent features. Extensive experiments comprising both quantitative and qualitative evaluations demonstrate the effectiveness of FancyVideo. Our video demo, code and model are available at https://360cvgroup.github.io/FancyVideo/.

Long-horizon planning is hindered by challenges such as uncertainty accumulation, computational complexity, delayed rewards and incomplete information. This work proposes an approach to exploit the task hierarchy from human instructions to facilitate multi-robot planning. Using Large Language Models (LLMs), we propose a two-step approach to translate multi-sentence instructions into a structured language, Hierarchical Linear Temporal Logic (LTL), which serves as a formal representation for planning. Initially, LLMs transform the instructions into a hierarchical representation defined as Hierarchical Task Tree, capturing the logical and temporal relations among tasks. Following this, a domain-specific fine-tuning of LLM translates sub-tasks of each task into flat LTL formulas, aggregating them to form hierarchical LTL specifications. These specifications are then leveraged for planning using off-the-shelf planners. Our framework not only bridges the gap between instructions and algorithmic planning but also showcases the potential of LLMs in harnessing hierarchical reasoning to automate multi-robot task planning. Through evaluations in both simulation and real-world experiments involving human participants, we demonstrate that our method can handle more complex instructions compared to existing methods. The results indicate that our approach achieves higher success rates and lower costs in multi-robot task allocation and plan generation. Demos videos are available at https://youtu.be/7WOrDKxIMIs .

Neural Radiance Field (NeRF) has emerged as a promising alternative for photorealistic rendering. Despite recent algorithmic advancements, achieving real-time performance on today's resource-constrained devices remains challenging. In this paper, we identify the primary bottlenecks in current NeRF algorithms and introduce a unified algorithm-architecture co-design, Potamoi, designed to accommodate various NeRF algorithms. Specifically, we introduce a runtime system featuring a plug-and-play algorithm, SpaRW, which significantly reduces the per-frame computational workload and alleviates compute inefficiencies. Furthermore, our unified streaming pipeline coupled with customized hardware support effectively tames both SRAM and DRAM inefficiencies by minimizing repetitive DRAM access and completely eliminating SRAM bank conflicts. When evaluated against a baseline utilizing a dedicated DNN accelerator, our framework demonstrates a speed-up and energy reduction of 53.1$\times$ and 67.7$\times$, respectively, all while maintaining high visual quality with less than a 1.0 dB reduction in peak signal-to-noise ratio., Comment: arXiv admin note: substantial text overlap with arXiv:2404.11852

With rapid urbanization comes the increase of community, construction, and transportation noise in residential areas. The conventional approach of solely relying on sound pressure level (SPL) information to decide on the noise environment and to plan out noise control and mitigation strategies is inadequate. This paper presents an end-to-end IoT system that extracts real-time urban sound metadata using edge devices, providing information on the sound type, location and duration, rate of occurrence, loudness, and azimuth of a dominant noise in nine residential areas. The collected metadata on environmental sound is transmitted to and aggregated in a cloud-based platform to produce detailed descriptive analytics and visualization. Our approach to integrating different building blocks, namely, hardware, software, cloud technologies, and signal processing algorithms to form our real-time IoT system is outlined. We demonstrate how some of the sound metadata extracted by our system are used to provide insights into the noise in residential areas. A scalable workflow to collect and prepare audio recordings from nine residential areas to construct our urban sound dataset for training and evaluating a location-agnostic model is discussed. Some practical challenges of managing and maintaining a sensor network deployed at numerous locations are also addressed., Comment: 13 pages, 15 figures, journal