Search

Recent advancements in transition metal dichalcogenides (TMDs) have unveiled exceptional optical and electronic characteristics, opened up new opportunities, and provided a unique platform for exploring light-matter interactions under the strong coupling regime. The exploitation of exciton-polaritons, with their peculiar hybrid light-matter properties, for the development of spintronic customizable devices that enhance both the information capacity and functionality at ambient temperatures is often suggested as a promising route. However, although TMD polaritons have shown promising potential, the microscopic mechanisms leading to nonlinearities in TMD polaritons are complex and their spin-anisotropy, a crucial requirement for many proposed polaritonic devices, has been missing. Here, we demonstrate the absence of spin-anisotropic interaction in a monolayer WS2 microcavity (at room temperature) and show how spin-dependent interactions can be controlled and spin anisotropy recovered by engineering double WS2 layer structures with varied interlayer spacing. We attribute this phenomenon to a distinctive feature in exciton-polariton physics: layer-dependent polariton-phonon coupling. We use theoretical calculations of the phonon electrostatic potentials finding a drastically different coupling strength for single and double monolayer samples and discuss qualitatively how this explains the observed spin-anisotropic response. This is further consistent with experiments on multi WS2 layer samples and the identification of a critical separation distance, above which an effective single monolayer spin-anisotropic response is recovered, both in experiment and theory. Our work lays the groundwork for the development of spin-optronic polaritonic devices at room temperature.

Semi-structured networks (SSNs) merge the structures familiar from additive models with deep neural networks, allowing the modeling of interpretable partial feature effects while capturing higher-order non-linearities at the same time. A significant challenge in this integration is maintaining the interpretability of the additive model component. Inspired by large-scale biomechanics datasets, this paper explores extending SSNs to functional data. Existing methods in functional data analysis are promising but often not expressive enough to account for all interactions and non-linearities and do not scale well to large datasets. Although the SSN approach presents a compelling potential solution, its adaptation to functional data remains complex. In this work, we propose a functional SSN method that retains the advantageous properties of classical functional regression approaches while also improving scalability. Our numerical experiments demonstrate that this approach accurately recovers underlying signals, enhances predictive performance, and performs favorably compared to competing methods., Comment: Accepted at NeurIPS 2024

Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in crucial areas such as the face and hands, and neglect the explicit modeling for motion blur, leading to unrealistic low-quality synthesis. To address these limitations, we first leverage regional supervision for detailed regions to enhance face and hand faithfulness. Second, we model the motion blur explicitly to further improve the appearance quality. Third, we explore novel training strategies for high-resolution human animation to improve the overall fidelity. Experimental results demonstrate that our proposed method outperforms state-of-the-art approaches, achieving significant improvements upon the strongest baseline by more than 21.0% and 57.4% in terms of reconstruction precision (L1) and perceptual quality (FVD) on HumanDance dataset. Code and model will be made available.

Digital identity plays a vital role in enabling secure access to resources and services in the digital world. Traditional identity authentication methods, such as password-based and biometric authentications, have limitations in terms of security, privacy, and scalability. Decentralized authentication approaches leveraging blockchain technology have emerged as a promising solution. However, existing decentralized authentication methods often rely on indirect identity verification (e.g. using passwords or digital signatures as authentication credentials) and face challenges such as Sybil attacks. In this paper, we propose BioZero, an efficient and privacy-preserving decentralized biometric authentication protocol that can be implemented on open blockchain. BioZero leverages Pedersen commitment and homomorphic computation to protect user biometric privacy while enabling efficient verification. We enhance the protocol with non-interactive homomorphic computation and employ zero-knowledge proofs for secure on-chain verification. The unique aspect of BioZero is that it is fully decentralized and can be executed by blockchain smart contracts in a very efficient way. We analyze the security of BioZero and validate its performance through a prototype implementation. The results demonstrate the effectiveness, efficiency, and security of BioZero in decentralized authentication scenarios. Our work contributes to the advancement of decentralized identity authentication using biometrics., Comment: 14 pages, 3 figures

Large language models (LLMs) are being widely researched across various disciplines, with significant recent efforts focusing on adapting LLMs for understanding of how communication networks operate. However, over-reliance on prompting techniques hinders the full exploitation of the generalization ability of these models, and the lack of efficient fine-tuning methods prevents the full realization of lightweight LLMs' potential. This paper addresses these challenges by introducing our Rephrase and Contrast (RaC) framework, an efficient fine-tuning framework. RaC enhances LLMs' comprehension and critical thinking abilities by incorporating question reformulation and contrastive analysis of correct and incorrect answers during the fine-tuning process. Experimental results demonstrate a 63.73% accuracy improvement over the foundational model when tested on a comprehensive networking problem set. Moreover, to efficiently construct the dataset for RaC fine-tuning, we develop a GPT-assisted data mining method for generating high-quality question-answer (QA) pairs; furthermore, we introduce ChoiceBoost, a data augmentation technique that expands dataset size while reducing answer-order bias. Apart from these technical innovations, we contribute to the networking community by open-sourcing valuable research resources, including: 1) the fine-tuned networking model referred to as RaC-Net, 2) the training dataset used for fine-tuning the model, 3) three testing problem sets of different difficulties to serve as benchmarks for future research, and 4) code associated with the above resources.

NP-hard computational problems can be efficiently recast as finding the ground state of an effective spin model. However, to date no convenient setup exists that can universally simulate all of them, even for a fixed problem size. Here we present such a setup, using a series of optical (or polaritonic) resonators arranged in a chain using the geometry recently introduced in [Phys. Rev. Applied 21, 024057 (2024)]. We demonstrate by example how the simulator solves Hamiltonian Cycle and traveling salesman problems, and show that it generalises to any NP-hard problem of arbitrary size.

The restless multi-armed bandit (RMAB) framework is a popular model with applications across a wide variety of fields. However, its solution is hindered by the exponentially growing state space (with respect to the number of arms) and the combinatorial action space, making traditional reinforcement learning methods infeasible for large-scale instances. In this paper, we propose GINO-Q, a three-timescale stochastic approximation algorithm designed to learn an asymptotically optimal index policy for RMABs. GINO-Q mitigates the curse of dimensionality by decomposing the RMAB into a series of subproblems, each with the same dimension as a single arm, ensuring that complexity increases linearly with the number of arms. Unlike recently developed Whittle-index-based algorithms, GINO-Q does not require RMABs to be indexable, enhancing its flexibility and applicability. Our experimental results demonstrate that GINO-Q consistently learns near-optimal policies, even for non-indexable RMABs where Whittle-index-based algorithms perform poorly, and it converges significantly faster than existing baselines., Comment: 9 pages, 11 figures

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas such as multilingual safety, exaggerated safety, and prompt injections. The framework supports both LLM and judge benchmarking and incorporates custom mutators to test safety against various text-style mutations, such as future tense and paraphrasing. Additionally, WalledEval introduces WalledGuard, a new, small, and performant content moderation tool, and two datasets: SGXSTest and HIXSTest, which serve as benchmarks for assessing the exaggerated safety of LLMs and judges in cultural contexts. We make WalledEval publicly available at https://github.com/walledai/walledeval., Comment: Under review

Semantic communication is a promising technology for next-generation wireless networks. However, the out-of-distribution (OOD) problem, where a pre-trained machine learning (ML) model is applied to unseen tasks that are outside the distribution of its training data, may compromise the integrity of semantic compression. This paper explores the use of multi-modal large language models (MLLMs) to address the OOD issue in image semantic communication. We propose a novel "Plan A - Plan B" framework that leverages the broad knowledge and strong generalization ability of an MLLM to assist a conventional ML model when the latter encounters an OOD input in the semantic encoding process. Furthermore, we propose a Bayesian optimization scheme that reshapes the probability distribution of the MLLM's inference process based on the contextual information of the image. The optimization scheme significantly enhances the MLLM's performance in semantic compression by 1) filtering out irrelevant vocabulary in the original MLLM output; and 2) using contextual similarities between prospective answers of the MLLM and the background information as prior knowledge to modify the MLLM's probability distribution during inference. Further, at the receiver side of the communication system, we put forth a "generate-criticize" framework that utilizes the cooperation of multiple MLLMs to enhance the reliability of image reconstruction.

Advances in text-based image generation and editing have revolutionized content creation, enabling users to create impressive content from imaginative text prompts. However, existing methods are not designed to work well with the oversimplified prompts that are often encountered in typical scenarios when users start their editing with only vague or abstract purposes in mind. Those scenarios demand elaborate ideation efforts from the users to bridge the gap between such vague starting points and the detailed creative ideas needed to depict the desired results. In this paper, we introduce the task of Image Editing Recommendation (IER). This task aims to automatically generate diverse creative editing instructions from an input image and a simple prompt representing the users' under-specified editing purpose. To this end, we introduce Creativity-Vision Language Assistant~(Creativity-VLA), a multimodal framework designed specifically for edit-instruction generation. We train Creativity-VLA on our edit-instruction dataset specifically curated for IER. We further enhance our model with a novel 'token-for-localization' mechanism, enabling it to support both global and local editing operations. Our experimental results demonstrate the effectiveness of \ours{} in suggesting instructions that not only contain engaging creative elements but also maintain high relevance to both the input image and the user's initial hint.

Collaborative graph analysis across multiple institutions is becoming increasingly popular. Realistic examples include social network analysis across various social platforms, financial transaction analysis across multiple banks, and analyzing the transmission of infectious diseases across multiple hospitals. We define the federated graph analytics, a new problem for collaborative graph analytics under differential privacy. Although differentially private graph analysis has been widely studied, it fails to achieve a good tradeoff between utility and privacy in federated scenarios, due to the limited view of local clients and overlapping information across multiple subgraphs. Motivated by this, we first propose a federated graph analytic framework, named FEAT, which enables arbitrary downstream common graph statistics while preserving individual privacy. Furthermore, we introduce an optimized framework based on our proposed degree-based partition algorithm, called FEAT+, which improves the overall utility by leveraging the true local subgraphs. Finally, extensive experiments demonstrate that our FEAT and FEAT+ significantly outperform the baseline approach by approximately one and four orders of magnitude, respectively., Comment: 13 pages

We report the experimental emulation of trembling quantum motion, or Zitterbewegung, of exciton polaritons in a perovskite microcavity at room temperature. By introducing liquid crystal molecules into the microcavity, we achieve spinor states with synthetic Rashba-Dresselhaus spin-orbit coupling and tunable energy splitting. Under a resonant excitation, the polariton fluid exhibits clear trembling motion perpendicular to its flowing direction, accompanied by a unique spin pattern resembling interlocked fingers. Furthermore, leveraging on the sizable tunability of energy gaps by external electrical voltages, we observe the continuous transition of polariton Zitterbewegung from relativistic (small gaps) to non-relativistic (large gaps) regimes. Our findings pave the way for using exciton polaritons in the emulation of relativistic quantum physics.

Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with scalability and quadratic complexity efficiency. In this paper, we aim to leverage the long sequence modeling capability of Gated Linear Attention (GLA) Transformers, expanding its applicability to diffusion models. We introduce Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead, following the DiT design, but offering superior efficiency and effectiveness. In addition to better performance than DiT, DiG-S/2 exhibits $2.5\times$ higher training speed than DiT-S/2 and saves $75.7\%$ GPU memory at a resolution of $1792 \times 1792$. Moreover, we analyze the scalability of DiG across a variety of computational complexity. DiG models, with increased depth/width or augmentation of input tokens, consistently exhibit decreasing FID. We further compare DiG with other subquadratic-time diffusion models. With the same model size, DiG-XL/2 is $4.2\times$ faster than the recent Mamba-based diffusion model at a $1024$ resolution, and is $1.8\times$ faster than DiT with CUDA-optimized FlashAttention-2 under the $2048$ resolution. All these results demonstrate its superior efficiency among the latest diffusion models. Code is released at https://github.com/hustvl/DiG., Comment: Code is released at https://github.com/hustvl/DiG

Recent text-to-image customization works have been proven successful in generating images of given concepts by fine-tuning the diffusion models on a few examples. However, these methods tend to overfit the concepts, resulting in failure to create the concept under multiple conditions (e.g. headphone is missing when generating a dog wearing a headphone'). Interestingly, we notice that the base model before fine-tuning exhibits the capability to compose the base concept with other elements (e.g. a dog wearing a headphone) implying that the compositional ability only disappears after personalization tuning. Inspired by this observation, we present ClassDiffusion, a simple technique that leverages a semantic preservation loss to explicitly regulate the concept space when learning the new concept. Despite its simplicity, this helps avoid semantic drift when fine-tuning on the target concepts. Extensive qualitative and quantitative experiments demonstrate that the use of semantic preservation loss effectively improves the compositional abilities of the fine-tune models. In response to the ineffective evaluation of CLIP-T metrics, we introduce BLIP2-T metric, a more equitable and effective evaluation metric for this particular domain. We also provide in-depth empirical study and theoretical analysis to better understand the role of the proposed loss. Lastly, we also extend our ClassDiffusion to personalized video generation, demonstrating its flexibility.

Differential Evolution (DE) is a highly successful population based global optimisation algorithm, commonly used for solving numerical optimisation problems. However, as the complexity of the objective function increases, the wall-clock run-time of the algorithm suffers as many fitness function evaluations must take place to effectively explore the search space. Due to the inherently parallel nature of the DE algorithm, graphics processing units (GPU) have been used to effectively accelerate both the fitness evaluation and DE algorithm. This work reviews the main architectural choices made in the literature for GPU based DE algorithms and introduces a new GPU based numerical optimisation benchmark to evaluate and compare GPU based DE algorithms.

Topological exciton-polaritons are a burgeoning class of topological photonic systems distinguished by their hybrid nature as part-light, part-matter quasiparticles. Their further control over novel valley degree of freedom (DOF) has offered considerable potential for developing active topological optical devices towards information processing. However, the experimental demonstration of propagating topological exciton-polaritons with valley DOF remains elusive at room temperature. Here, employing a two-dimensional (2D) valley-Hall perovskite lattice, we report the experimental observation of valley-polarized topological exciton-polaritons and their valley-dependent propagations at room temperature. The 2D valley-Hall perovskite lattice consists of two mutually inverted honeycomb lattices with broken inversion symmetry. By measuring their band structure with angle-resolved photoluminescence spectra, we experimentally verify the existence of valley-polarized polaritonic topological kink states with a large gap opening of ~ 9 meV in the bearded interface at room temperature. Moreover, these valley-polarized states exhibit counter-propagating behaviors under a resonant excitation at room temperature. Our results not only expand the landscape of realizing topological exciton-polaritons, but also pave the way for the development of topological valleytronic devices employing exciton-polaritons with valley DOF at room temperature

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rule-based TKGRs struggle to effectively learn temporal rules that capture temporal patterns. Recently, Large Language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning. Consequently, the employment of LLMs for Temporal Knowledge Graph Reasoning (TKGR) has sparked increasing interest among researchers. Nonetheless, LLMs are known to function as black boxes, making it challenging to comprehend their reasoning process. Additionally, due to the resource-intensive nature of fine-tuning, promptly updating LLMs to integrate evolving knowledge within TKGs for reasoning is impractical. To address these challenges, in this paper, we propose a Large Language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on TKGs. Specifically, LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules. These rules unveil temporal patterns and facilitate interpretable reasoning. To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events. This ensures that the extracted rules always incorporate the most recent knowledge and better generalize to the predictions on future events. Experimental results show that without the need of fine-tuning, LLM-DA significantly improves the accuracy of reasoning over several common datasets, providing a robust framework for TKGR tasks.

Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Networks (GANs). A flurry of subsequent studies enhanced this framework's generality by leveraging large-scale diffusion models. However, these methods often suffer from inordinately long processing times (exceeding 1 minute per edit) and low success rates. Addressing these issues head on, we present LightningDrag, a rapid approach enabling high quality drag-based image editing in ~1 second. Unlike most previous methods, we redefine drag-based editing as a conditional generation task, eliminating the need for time-consuming latent optimization or gradient-based guidance during inference. In addition, the design of our pipeline allows us to train our model on large-scale paired video frames, which contain rich motion information such as object translations, changing poses and orientations, zooming in and out, etc. By learning from videos, our approach can significantly outperform previous methods in terms of accuracy and consistency. Despite being trained solely on videos, our model generalizes well to perform local shape deformations not presented in the training data (e.g., lengthening of hair, twisting rainbows, etc.). Extensive qualitative and quantitative evaluations on benchmark datasets corroborate the superiority of our approach. The code and model will be released at https://github.com/magic-research/LightningDrag., Comment: Project page: https://lightning-drag.github.io/

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow operation, thereby approaching piecewise linear flows. PeRFlow achieves superior performance in a few-step generation. Moreover, through dedicated parameterizations, the PeRFlow models inherit knowledge from the pretrained diffusion models. Thus, the training converges fast and the obtained models show advantageous transfer ability, serving as universal plug-and-play accelerators that are compatible with various workflows based on the pre-trained diffusion models. Codes for training and inference are publicly released. https://github.com/magic-research/piecewise-rectified-flow

Band selection in hyperspectral imaging (HSI) is critical for optimising data processing and enhancing analytical accuracy. Traditional approaches have predominantly concentrated on analysing spectral and pixel characteristics within individual bands independently. These approaches overlook the potential benefits of integrating multiple data sources, such as Light Detection and Ranging (LiDAR), and is further challenged by the limited availability of labeled data in HSI processing, which represents a significant obstacle. To address these challenges, this paper introduces a novel unsupervised band selection framework that incorporates attention mechanisms and an Autoencoder for reconstruction-based band selection. Our methodology distinctively integrates HSI with LiDAR data through an attention score, using a convolutional Autoencoder to process the combined feature mask. This fusion effectively captures essential spatial and spectral features and reduces redundancy in hyperspectral datasets. A comprehensive comparative analysis of our innovative fused band selection approach is performed against existing unsupervised band selection and fusion models. We used data sets such as Houston 2013, Trento, and MUUFLE for our experiments. The results demonstrate that our method achieves superior classification accuracy and significantly outperforms existing models. This enhancement in HSI band selection, facilitated by the incorporation of LiDAR features, underscores the considerable advantages of integrating features from different sources., Comment: 13 pages, 13figures, 6 tables

The fusion of hyperspectral and LiDAR data has been an active research topic. Existing fusion methods have ignored the high-dimensionality and redundancy challenges in hyperspectral images, despite that band selection methods have been intensively studied for hyperspectral image (HSI) processing. This paper addresses this significant gap by introducing a cross-attention mechanism from the transformer architecture for the selection of HSI bands guided by LiDAR data. LiDAR provides high-resolution vertical structural information, which can be useful in distinguishing different types of land cover that may have similar spectral signatures but different structural profiles. In our approach, the LiDAR data are used as the "query" to search and identify the "key" from the HSI to choose the most pertinent bands for LiDAR. This method ensures that the selected HSI bands drastically reduce redundancy and computational requirements while working optimally with the LiDAR data. Extensive experiments have been undertaken on three paired HSI and LiDAR data sets: Houston 2013, Trento and MUUFL. The results highlight the superiority of the cross-attention mechanism, underlining the enhanced classification accuracy of the identified HSI bands when fused with the LiDAR features. The results also show that the use of fewer bands combined with LiDAR surpasses the performance of state-of-the-art fusion models., Comment: 15 pages, 13 figures

This paper explores the Opportunistic Routing Protocols in the context of remote sea emergency scenarios, using the MH370 plane crash as a case study (OppNetMH370). We studied the likelihood of successful transmissions of emergency messages to response services where communication methods are inadequate in remote sea areas. The study focuses on two opportunistic routing protocols, where their performances are evaluated based on key metrics including average latency and delivery probability. Our study reveals the challenges associated with the current communication technology in remote areas and proposes potential enhancements for future simulations. The findings contribute to understanding the limitations of existing communication strategies in remote sea areas and offers insights on the future development and improvements to the routing protocols.

Classifying hyperspectral images is a difficult task in remote sensing, due to their complex high-dimensional data. To address this challenge, we propose HSIMamba, a novel framework that uses bidirectional reversed convolutional neural network pathways to extract spectral features more efficiently. Additionally, it incorporates a specialized block for spatial analysis. Our approach combines the operational efficiency of CNNs with the dynamic feature extraction capability of attention mechanisms found in Transformers. However, it avoids the associated high computational demands. HSIMamba is designed to process data bidirectionally, significantly enhancing the extraction of spectral features and integrating them with spatial information for comprehensive analysis. This approach improves classification accuracy beyond current benchmarks and addresses computational inefficiencies encountered with advanced models like Transformers. HSIMamba were tested against three widely recognized datasets Houston 2013, Indian Pines, and Pavia University and demonstrated exceptional performance, surpassing existing state-of-the-art models in HSI classification. This method highlights the methodological innovation of HSIMamba and its practical implications, which are particularly valuable in contexts where computational resources are limited. HSIMamba redefines the standards of efficiency and accuracy in HSI classification, thereby enhancing the capabilities of remote sensing applications. Hyperspectral imaging has become a crucial tool for environmental surveillance, agriculture, and other critical areas that require detailed analysis of the Earth surface. Please see our code in HSIMamba for more details., Comment: 11 pages, 2 figures, 8 tables

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

In federated learning, data heterogeneity significantly impacts performance. A typical solution involves segregating these parameters into shared and personalized components, a concept also relevant in multi-task learning. Addressing this, we propose "Loop Improvement" (LI), a novel method enhancing this separation and feature extraction without necessitating a central server or data interchange among participants. Our experiments reveal LI's superiority in several aspects: In personalized federated learning environments, LI consistently outperforms the advanced FedALA algorithm in accuracy across diverse scenarios. Additionally, LI's feature extractor closely matches the performance achieved when aggregating data from all clients. In global model contexts, employing LI with stacked personalized layers and an additional network also yields comparable results to combined client data scenarios. Furthermore, LI's adaptability extends to multi-task learning, streamlining the extraction of common features across tasks and obviating the need for simultaneous training. This approach not only enhances individual task performance but also achieves accuracy levels on par with classic multi-task learning methods where all tasks are trained simultaneously. LI integrates a loop topology with layer-wise and end-to-end training, compatible with various neural network models. This paper also delves into the theoretical underpinnings of LI's effectiveness, offering insights into its potential applications. The code is on https://github.com/axedge1983/LI, Comment: 11 pages, 11 figures

This work develops a machine learned structural design model for continuous beam systems from the inverse problem perspective. After demarcating between forward, optimisation and inverse machine learned operators, the investigation proposes a novel methodology based on the recently developed influence zone concept which represents a fundamental shift in approach compared to traditional structural design methods. The aim of this approach is to conceptualise a non-iterative structural design model that predicts cross-section requirements for continuous beam systems of arbitrary system size. After generating a dataset of known solutions, an appropriate neural network architecture is identified, trained, and tested against unseen data. The results show a mean absolute percentage testing error of 1.6% for cross-section property predictions, along with a good ability of the neural network to generalise well to structural systems of variable size. The CBeamXP dataset generated in this work and an associated python-based neural network training script are available at an open-source data repository to allow for the reproducibility of results and to encourage further investigations., Comment: 30 pages, 16 figures, 8 tables

Quantum state reconstruction is an essential element in quantum information processing. However, efficient and reliable reconstruction of non-trivial quantum states in the presence of hardware imperfections can be challenging. This task is particularly demanding for high-dimensional states encoded in continuous-variable (CV) systems, as many error-prone measurements are needed to cover the relevant degrees of freedom of the system in phase space. In this work, we introduce an efficient and robust technique for optimized reconstruction based on excitation number sampling (ORENS). We use a standard bosonic circuit quantum electrodynamics (cQED) setup to experimentally demonstrate the robustness of ORENS and show that it outperforms the existing cQED reconstruction techniques such as Wigner and Husimi Q tomography. Our investigation highlights that ORENS is naturally free of parasitic system dynamics and resilient to decoherence effects in the hardware. Finally, ORENS relies only on the ability to accurately measure the excitation number of the state, making it a versatile and accessible tool for a wide range of CV platforms and readily scalable to multimode systems. Thus, our work provides a crucial and valuable primitive for practical quantum information processing using bosonic modes., Comment: Main text (6 pages with 4 figures) and Appendices (10 pages with 7 figures and 4 tables)

The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale.

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at https://github.com/MengyuWang826/SegRefiner., Comment: NeurIPS 2023, Code: https://github.com/MengyuWang826/SegRefiner

Training-free guided sampling in diffusion models leverages off-the-shelf pre-trained networks, such as an aesthetic evaluation model, to guide the generation process. Current training-free guided sampling algorithms obtain the guidance energy function based on a one-step estimate of the clean image. However, since the off-the-shelf pre-trained networks are trained on clean images, the one-step estimation procedure of the clean image may be inaccurate, especially in the early stages of the generation process in diffusion models. This causes the guidance in the early time steps to be inaccurate. To overcome this problem, we propose Symplectic Adjoint Guidance (SAG), which calculates the gradient guidance in two inner stages. Firstly, SAG estimates the clean image via $n$ function calls, where $n$ serves as a flexible hyperparameter that can be tailored to meet specific image quality requirements. Secondly, SAG uses the symplectic adjoint method to obtain the gradients accurately and efficiently in terms of the memory requirements. Extensive experiments demonstrate that SAG generates images with higher qualities compared to the baselines in both guided image and video generation tasks.

Conversational recommender systems (CRS) utilize natural language interactions and dialogue history to infer user preferences and provide accurate recommendations. Due to the limited conversation context and background knowledge, existing CRSs rely on external sources such as knowledge graphs to enrich the context and model entities based on their inter-relations. However, these methods ignore the rich intrinsic information within entities. To address this, we introduce the Knowledge-Enhanced Entity Representation Learning (KERL) framework, which leverages both the knowledge graph and a pre-trained language model to improve the semantic understanding of entities for CRS. In our KERL framework, entity textual descriptions are encoded via a pre-trained language model, while a knowledge graph helps reinforce the representation of these entities. We also employ positional encoding to effectively capture the temporal information of entities in a conversation. The enhanced entity representation is then used to develop a recommender component that fuses both entity and contextual representations for more informed recommendations, as well as a dialogue component that generates informative entity-related information in the response text. A high-quality knowledge graph with aligned entity descriptions is constructed to facilitate our study, namely the Wiki Movie Knowledge Graph (WikiMKG). The experimental results show that KERL achieves state-of-the-art results in both recommendation and response generation tasks., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Task-oriented communications are an important element in future intelligent IoT systems. Existing IoT systems, however, are limited in their capacity to handle complex tasks, particularly in their interactions with humans to accomplish these tasks. In this paper, we present LLMind, an LLM-based task-oriented AI agent framework that enables effective collaboration among IoT devices, with humans communicating high-level verbal instructions, to perform complex tasks. Inspired by the functional specialization theory of the brain, our framework integrates an LLM with domain-specific AI modules, enhancing its capabilities. Complex tasks, which may involve collaborations of multiple domain-specific AI modules and IoT devices, are executed through a control script generated by the LLM using a Language-Code transformation approach, which first converts language descriptions to an intermediate finite-state machine (FSM) before final precise transformation to code. Furthermore, the framework incorporates a novel experience accumulation mechanism to enhance response speed and effectiveness, allowing the framework to evolve and become progressively sophisticated through continuing user and machine interactions.