Search

Speech Enhancement (SE) aims to improve the quality of noisy speech. It has been shown that additional visual cues can further improve performance. Given that speech communication involves audio, visual, and linguistic modalities, it is natural to expect another performance boost by incorporating linguistic information. However, bridging the modality gaps to efficiently incorporate linguistic information, along with audio and visual modalities during knowledge transfer, is a challenging task. In this paper, we propose a novel multi-modality learning framework for SE. In the model framework, a state-of-the-art diffusion Model backbone is utilized for Audio-Visual Speech Enhancement (AVSE) modeling where both audio and visual information are directly captured by microphones and video cameras. Based on this AVSE, the linguistic modality employs a PLM to transfer linguistic knowledge to the visual acoustic modality through a process termed Cross-Modal Knowledge Transfer (CMKT) during AVSE model training. After the model is trained, it is supposed that linguistic knowledge is encoded in the feature processing of the AVSE model by the CMKT, and the PLM will not be involved during inference stage. We carry out SE experiments to evaluate the proposed model framework. Experimental results demonstrate that our proposed AVSE system significantly enhances speech quality and reduces generative artifacts, such as phonetic confusion compared to the state-of-the-art. Moreover, our visualization results demonstrate that our Cross-Modal Knowledge Transfer method further improves the generated speech quality of our AVSE system. These findings not only suggest that Diffusion Model-based techniques hold promise for advancing the state-of-the-art in AVSE but also justify the effectiveness of incorporating linguistic information to improve the performance of Diffusion-based AVSE systems.

Atomic-scale ferroelectrics are of great interest for high-density electronics, particularly field-effect transistors, low-power logic, and nonvolatile memories. We devised a film with a layered structure of bismuth oxide that can stabilize the ferroelectric state down to 1 nanometer through samarium bondage. This film can be grown on a variety of substrates with a cost-effective chemical solution deposition. We observed a standard ferroelectric hysteresis loop down to a thickness of ~1 nanometer. The thin films with thicknesses that range from 1 to 4.56 nanometers possess a relatively large remanent polarization from 17 to 50 microcoulombs per square centimeter. We verified the structure with first-principles calculations, which also pointed to the material being a lone pair-driven ferroelectric material. The structure design of the ultrathin ferroelectric films has great potential for the manufacturing of atomic-scale electronic devices., Comment: preprint, 27 pages, 5 figures

We propose a two-stage concatenated coding scheme for reliable and information-theoretically secure communication over intersymbol interference wiretap channels. Motivated by the theoretical coding strategies that achieve the secrecy capacity, our scheme integrates low-density parity-check (LDPC) codes in the outer stage, forming a nested structure of wiretap codes, with trellis codes in the inner stage to improve achievable secure rates. The trellis code is specifically designed to transform the uniformly distributed codewords produced by the LDPC code stage into a Markov process, achieving tight lower bounds on the secrecy capacity. We further estimate the information leakage rate of the proposed coding scheme using an upper bound. To meet the weak secrecy criterion, we optimize degree distributions of the irregular LDPC codes at the outer stage, essentially driving the estimated upper bound on the information leakage rate to zero.

Out-of-distribution (OOD) detection has seen significant advancements with zero-shot approaches by leveraging the powerful Vision-Language Models (VLMs) such as CLIP. However, prior research works have predominantly focused on enhancing Far-OOD performance, while potentially compromising Near-OOD efficacy, as observed from our pilot study. To address this issue, we propose a novel strategy to enhance zero-shot OOD detection performances for both Far-OOD and Near-OOD scenarios by innovatively harnessing Large Language Models (LLMs) and VLMs. Our approach first exploit an LLM to generate superclasses of the ID labels and their corresponding background descriptions followed by feature extraction using CLIP. We then isolate the core semantic features for ID data by subtracting background features from the superclass features. The refined representation facilitates the selection of more appropriate negative labels for OOD data from a comprehensive candidate label set of WordNet, thereby enhancing the performance of zero-shot OOD detection in both scenarios. Furthermore, we introduce novel few-shot prompt tuning and visual prompt tuning to adapt the proposed framework to better align with the target distribution. Experimental results demonstrate that the proposed approach consistently outperforms current state-of-the-art methods across multiple benchmarks, with an improvement of up to 2.9% in AUROC and a reduction of up to 12.6% in FPR95. Additionally, our method exhibits superior robustness against covariate shift across different domains, further highlighting its effectiveness in real-world scenarios., Comment: 9 pages, 4 figures

Quantum-correlated interferometer is a newly emerging tool in quantum technology that offers classical-limit-breaking phase sensitivity. But to date, there exists a configurational bottleneck for its practicability due to the low phase-sensitive photon numbers limited by the current detection strategies. Here we establish an innovative development termed as ``quantum twin interferometer'' with dual pairs of entangled twin beams arranged in the parallel configuration, allowing fully exploits the quantum resource through the new configuration of entangled detection. We observe the distributed phase sensing with 3 dB quantum noise reduction in phase-sensing power at the level of milliwatts, which advances the record of signal-to-noise ratio so far achieved in photon-correlated interferometers by three orders of magnitude. The developed techniques in this work can be used to revolutionize a diversity of quantum devices requiring phase measurement., Comment: 12pages,7figures

Binary Neural Network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While binary neural networks are typically formulated as a constrained optimization problem and optimized in the binarized space, general neural networks are formulated as an unconstrained optimization problem and optimized in the continuous space. This paper introduces the Hyperbolic Binary Neural Network (HBNN) by leveraging the framework of hyperbolic geometry to optimize the constrained problem. Specifically, we transform the constrained problem in hyperbolic space into an unconstrained one in Euclidean space using the Riemannian exponential map. On the other hand, we also propose the Exponential Parametrization Cluster (EPC) method, which, compared to the Riemannian exponential map, shrinks the segment domain based on a diffeomorphism. This approach increases the probability of weight flips, thereby maximizing the information gain in BNNs. Experimental results on CIFAR10, CIFAR100, and ImageNet classification datasets with VGGsmall, ResNet18, and ResNet34 models illustrate the superior performance of our HBNN over state-of-the-art methods.

Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying current Low-Light Image Enhancement (LLIE) methods to real-world scenarios, primarily due to the diverse illumination conditions encountered. Furthermore, the quest for generating enhancements that are visually realistic and attractive remains an underexplored realm. In response to these challenges, we introduce a novel \textbf{LLIE} framework with the guidance of \textbf{G}enerative \textbf{P}erceptual \textbf{P}riors (\textbf{GPP-LLIE}) derived from vision-language models (VLMs). Specifically, we first propose a pipeline that guides VLMs to assess multiple visual attributes of the LL image and quantify the assessment to output the global and local perceptual priors. Subsequently, to incorporate these generative perceptual priors to benefit LLIE, we introduce a transformer-based backbone in the diffusion process, and develop a new layer normalization (\textit{\textbf{GPP-LN}}) and an attention mechanism (\textit{\textbf{LPP-Attn}}) guided by global and local perceptual priors. Extensive experiments demonstrate that our model outperforms current SOTA methods on paired LL datasets and exhibits superior generalization on real-world data. The code is released at \url{https://github.com/LowLevelAI/GPP-LLIE}., Comment: Accepted by AAAI 2025

Optimal transport has numerous applications, particularly in machine learning tasks involving generative models. In practice, the transportation process often encounters an information bottleneck, typically arising from the conversion of a communication channel into a rate-limited bit pipeline using error correction codes. While this conversion enables a channel-oblivious approach to optimal transport, it fails to fully exploit the available degrees of freedom. Motivated by the emerging paradigm of generative communication, this paper examines the problem of channel-aware optimal transport, where a block of i.i.d. random variables is transmitted through a memoryless channel to generate another block of i.i.d. random variables with a prescribed marginal distribution such that the end-to-end distortion is minimized. With unlimited common randomness available to the encoder and decoder, the source-channel separation architecture is shown to be asymptotically optimal as the blocklength approaches infinity. On the other hand, in the absence of common randomness, the source-channel separation architecture is generally suboptimal. For this scenario, a hybrid coding scheme is proposed, which partially retains the generative capabilities of the given channel while enabling reliable transmission of digital information. It is demonstrated that the proposed hybrid coding scheme can outperform both separation-based and uncoded schemes.

Traditionally, thermal noise in electric currents, arising from thermal agitation, is expected to increase with temperature $T$ and disappear as $T$ approaches zero. Contrary to this expectation, we discover that the resonant DC thermal noise (DTN) in photocurrents not only persists at $T=0$ but also exhibits a divergence proportional to $1/T$. This thermal noise \textit{anomaly} arises from the unique electron-photon interactions near the Fermi surface, manifesting as the interplay between the inherent Fermi-surface property and the resonant optical selection rules of DTN, and thereby represents an unexplored noise regime. Notably, we reveal that this \textit{anomalous} DTN, especially in time-reversal-invariant systems, is intrinsically linked to the quantum metric. We illustrate this \textit{anomalous} DTN in massless Dirac materials, including two-dimensional graphene, the surfaces of three-dimensional topological insulators, and three-dimensional Weyl semimetals, where the quantum metric plays a pivotal role. Finally, we find that the total noise spectrum at low temperatures, which includes both the DC shot noise and the \textit{anomalous} DTN, will universally peak at $\omega_p=2|\mu|$ with $\omega_p$ the frequency of light and $\mu$ the chemical potential of the bulk crystals.

Kinship face synthesis is a challenging problem due to the scarcity and low quality of the available kinship data. Existing methods often struggle to generate descendants with both high diversity and fidelity while precisely controlling facial attributes such as age and gender. To address these issues, we propose the Style Latent Diffusion Transformer (StyleDiT), a novel framework that integrates the strengths of StyleGAN with the diffusion model to generate high-quality and diverse kinship faces. In this framework, the rich facial priors of StyleGAN enable fine-grained attribute control, while our conditional diffusion model is used to sample a StyleGAN latent aligned with the kinship relationship of conditioning images by utilizing the advantage of modeling complex kinship relationship distribution. StyleGAN then handles latent decoding for final face generation. Additionally, we introduce the Relational Trait Guidance (RTG) mechanism, enabling independent control of influencing conditions, such as each parent's facial image. RTG also enables a fine-grained adjustment between the diversity and fidelity in synthesized faces. Furthermore, we extend the application to an unexplored domain: predicting a partner's facial images using a child's image and one parent's image within the same framework. Extensive experiments demonstrate that our StyleDiT outperforms existing methods by striking an excellent balance between generating diverse and high-fidelity kinship faces.

Creating a heterostructure by combining two magnetically and structurally distinct ruthenium oxides is a crucial approach for investigating their emergent magnetic states and interactions. Previously, research has predominantly concentrated on the intrinsic properties of the ferromagnet SrRuO3 and recently discovered altermagnet RuO2 solely. Here, we engineered an ultrasharp sublattice-matched heterointerface using pseudo-cubic SrRuO3 and rutile RuO2, conducting an in-depth analysis of their spin interactions. Structurally, to accommodate the lattice symmetry mismatch, the inverted RuO2 layer undergoes an in-plane rotation of 18 degrees during epitaxial growth on SrRuO3 layer, resulting in an interesting and rotational interface with perfect crystallinity and negligible chemical intermixing. Performance-wise, the interfacial layer of 6 nm in RuO2 adjacent to SrRuO3 exhibits a nonzero magnetic moment, contributing to an enhanced anomalous Hall effect (AHE) at low temperatures. Furthermore, our observations indicate that, in contrast to SrRuO3 single layers, the AHE of [(RuO2)15/(SrRuO3)n] heterostructures shows nonlinear behavior and reaches its maximum when the SrRuO3 thickness reaches tens of nm. These results suggest that the interfacial magnetic interaction surpasses that of all-perovskite oxides (~5-unit cells). This study underscores the significance and potential applications of magnetic interactions based on the crystallographic asymmetric interfaces in the design of spintronic devices., Comment: 30 pages/5 figures

Directly probing deep tissue activities from body surfaces offers a noninvasive approach to monitoring essential physiological processes1-3. However, this method is technically challenged by rapid signal attenuation toward the body surface and confounding motion artifacts4-6 primarily due to excessive contact impedance and mechanical mismatch with conventional electrodes. Herein, by formulating and directly spray coating biocompatible two-dimensional nanosheet ink onto the human body under ambient conditions, we create microscopically conformal and adaptive van der Waals thin films (VDWTFs) that seamlessly merge with non-Euclidean, hairy, and dynamically evolving body surfaces. Unlike traditional deposition methods, which often struggle with conformality and adaptability while retaining high electronic performance, this gentle process enables the formation of high-performance VDWTFs directly on the body surface under bio-friendly conditions, making it ideal for biological applications. This results in low-impedance electrically functionalized body surfaces (EFBS), enabling highly robust monitoring of biopotential and bioimpedance modulations associated with deep-tissue activities, such as blood circulation, muscle movements, and brain activities. Compared to commercial solutions, our VDWTF-EFBS exhibits nearly two-orders of magnitude lower contact impedance and substantially reduces the extrinsic motion artifacts, enabling reliable extraction of bioelectrical signals from irregular surfaces, such as unshaved human scalps. This advancement defines a technology for continuous, noninvasive monitoring of deep-tissue activities during routine body movements.

The Fuzzy General Grey Cognitive Map (FGGCM) and Fuzzy Grey Cognitive Map (FGCM) extend the Fuzzy Cognitive Map (FCM) by integrating uncertainty from multiple interval data or fuzzy numbers. Despite extensive studies on the convergence of FCM and FGCM, the convergence behavior of FGGCM under sigmoid activation functions remains underexplored. This paper addresses this gap by deriving sufficient conditions for the convergence of FGGCM to a unique fixed point. Using the Banach and Browder-Gohde-Kirk fixed point theorems, and Cauchy-Schwarz inequality, the study establishes conditions for the kernels and greyness of FGGCM to converge to unique fixed points. A Web Experience FCM is adapted to design an FGGCM with weights modified to GGN. Comparisons with existing FCM and FGCM convergence theorems confirm that they are special cases of the theorems proposed here. The conclusions support the application of FGGCM in domains such as control, prediction, and decision support systems.

This paper describes the zero-shot spontaneous style TTS system for the ISCSLP 2024 Conversational Voice Clone Challenge (CoVoC). We propose a LLaMA-based codec language model with a delay pattern to achieve spontaneous style voice cloning. To improve speech intelligibility, we introduce the Classifier-Free Guidance (CFG) strategy in the language model to strengthen conditional guidance on token prediction. To generate high-quality utterances, we adopt effective data preprocessing operations and fine-tune our model with selected high-quality spontaneous speech data. The official evaluations in the CoVoC constrained track show that our system achieves the best speech naturalness MOS of 3.80 and obtains considerable speech quality and speaker similarity results., Comment: Accepted by ISCSLP 2024

Born in Punjab (India) in December 1941, Balraj Singh is not only the single most prolific nuclear data evaluator and disseminator of nuclear structure and decay data with 148 evaluations in Nuclear Data Sheets -- 85 as the first and often only author -- plus other journals, but his upmost curiosity and dedication brought him to be one of the finest nuclear physicists, with an everlasting influence on many of us. Balraj passed away about a year ago on 9 October 2023 in Ottawa, Ontario (Canada) at the age of 81, and at Atomic Data and Nuclear Data Tables we would like to commemorate some of his scientific achievements., Comment: 2 pages, 1 figure

Automatic detection of depression is a rapidly growing field of research at the intersection of psychology and machine learning. However, with its exponential interest comes a growing concern for data privacy and scarcity due to the sensitivity of such a topic. In this paper, we propose a pipeline for Large Language Models (LLMs) to generate synthetic data to improve the performance of depression prediction models. Starting from unstructured, naturalistic text data from recorded transcripts of clinical interviews, we utilize an open-source LLM to generate synthetic data through chain-of-thought prompting. This pipeline involves two key steps: the first step is the generation of the synopsis and sentiment analysis based on the original transcript and depression score, while the second is the generation of the synthetic synopsis/sentiment analysis based on the summaries generated in the first step and a new depression score. Not only was the synthetic data satisfactory in terms of fidelity and privacy-preserving metrics, it also balanced the distribution of severity in the training dataset, thereby significantly enhancing the model's capability in predicting the intensity of the patient's depression. By leveraging LLMs to generate synthetic data that can be augmented to limited and imbalanced real-world datasets, we demonstrate a novel approach to addressing data scarcity and privacy concerns commonly faced in automatic depression detection, all while maintaining the statistical integrity of the original dataset. This approach offers a robust framework for future mental health research and applications., Comment: 6 pages excluding references and appendix

We present APT, an advanced Large Language Model (LLM)-driven framework that enables autonomous agents to construct complex and creative structures within the Minecraft environment. Unlike previous approaches that primarily concentrate on skill-based open-world tasks or rely on image-based diffusion models for generating voxel-based structures, our method leverages the intrinsic spatial reasoning capabilities of LLMs. By employing chain-of-thought decomposition along with multimodal inputs, the framework generates detailed architectural layouts and blueprints that the agent can execute under zero-shot or few-shot learning scenarios. Our agent incorporates both memory and reflection modules to facilitate lifelong learning, adaptive refinement, and error correction throughout the building process. To rigorously evaluate the agent's performance in this emerging research area, we introduce a comprehensive benchmark consisting of diverse construction tasks designed to test creativity, spatial reasoning, adherence to in-game rules, and the effective integration of multimodal instructions. Experimental results using various GPT-based LLM backends and agent configurations demonstrate the agent's capacity to accurately interpret extensive instructions involving numerous items, their positions, and orientations. The agent successfully produces complex structures complete with internal functionalities such as Redstone-powered systems. A/B testing indicates that the inclusion of a memory module leads to a significant increase in performance, emphasizing its role in enabling continuous learning and the reuse of accumulated experience. Additionally, the agent's unexpected emergence of scaffolding behavior highlights the potential of future LLM-driven agents to utilize subroutine planning and leverage the emergence ability of LLMs to autonomously develop human-like problem-solving techniques., Comment: 8 pages

Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning over a large number of images. Existing benchmarks for multi-image question-answering are limited in scope, each question is paired with only up to 30 images, which does not fully capture the demands of large-scale retrieval tasks encountered in the real-world usages. To reduce these gaps, we introduce two document haystack benchmarks, dubbed DocHaystack and InfoHaystack, designed to evaluate LMM performance on large-scale visual document retrieval and understanding. Additionally, we propose V-RAG, a novel, vision-centric retrieval-augmented generation (RAG) framework that leverages a suite of multimodal vision encoders, each optimized for specific strengths, and a dedicated question-document relevance module. V-RAG sets a new standard, with a 9% and 11% improvement in Recall@1 on the challenging DocHaystack-1000 and InfoHaystack-1000 benchmarks, respectively, compared to the previous best baseline models. Additionally, integrating V-RAG with LMMs enables them to efficiently operate across thousands of images, yielding significant improvements on our DocHaystack and InfoHaystack benchmarks. Our code and datasets are available at https://github.com/Vision-CAIR/dochaystacks, Comment: the correct arxiv version

Safety is extremely important for urban flights of autonomous Unmanned Aerial Vehicles (UAVs). Risk-aware path planning is one of the most effective methods to guarantee the safety of UAVs. This type of planning can be represented as a Constrained Shortest Path (CSP) problem, which seeks to find the shortest route that meets a predefined safety constraint. Solving CSP problems is NP-hard, presenting significant computational challenges. Although traditional methods can accurately solve CSP problems, they tend to be very slow. Previously, we introduced an additional safety dimension to the traditional A* algorithm, known as ASD A*, to effectively handle Constrained Shortest Path (CSP) problems. Then, we developed a custom learning-based heuristic using transformer-based neural networks, which significantly reduced computational load and enhanced the performance of the ASD A* algorithm. In this paper, we expand our dataset to include more risk maps and tasks, improve the proposed model, and increase its performance. We also introduce a new heuristic strategy and a novel neural network, which enhance the overall effectiveness of our approach., Comment: 2024 AIAA DATC/IEEE 43rd Digital Avionics Systems Conference (DASC)

Models for trajectory prediction are an essential component of many advanced air mobility studies. These models help aircraft detect conflict and plan avoidance maneuvers, which is especially important in Unmanned Aircraft systems (UAS) landing management due to the congested airspace near vertiports. In this paper, we propose a landing trajectory prediction model for UAS based on Generative Adversarial Network (GAN). The GAN is a prestigious neural network that has been developed for many years. In previous research, GAN has achieved many state-of-the-art results in many generation tasks. The GAN consists of one neural network generator and a neural network discriminator. Because of the learning capacity of the neural networks, the generator is capable to understand the features of the sample trajectory. The generator takes the previous trajectory as input and outputs some random status of a flight. According to the results of the experiences, the proposed model can output more accurate predictions than the baseline method(GMR) in various datasets. To evaluate the proposed model, we also create a real UAV landing dataset that includes more than 2600 trajectories of drone control manually by real pilots., Comment: 9 pages, AIAA SCITECH 2023

Probabilistic Reachable Set (PRS) plays a crucial role in many fields of autonomous systems, yet efficiently generating PRS remains a significant challenge. This paper presents a learning approach to generating 2-dimensional PRS for states in a dynamic system. Traditional methods such as Hamilton-Jacobi reachability analysis, Monte Carlo, and Gaussian process classification face significant computational challenges or require detailed dynamics information, limiting their applicability in realistic situations. Existing data-driven methods may lack accuracy. To overcome these limitations, we propose leveraging neural networks, commonly used in imitation learning and computer vision, to imitate expert methods to generate PRS approximations. We trained the neural networks using a multi-label, self-supervised learning approach. We selected the fine-tuned convex approximation method as the expert to create expert PRS. Additionally, we continued sampling from the distribution to obtain a diverse array of sample sets. Given a small sample set, the trained neural networks can replicate the PRS approximation generated by the expert method, while the generation speed is much faster., Comment: 10 pages

Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression., Comment: 10 pages

DarkSHINE is a newly proposed fixed-target experiment initiative to search for the invisible decay of Dark Photon via missing energy/momentum signatures, based on the high repetition rate electron beam to be deployed/delivered by the Shanghai High repetition rate XFEL and Extreme light facility (SHINE). This report elaborates the baseline design of DarkSHINE experiment by introducing the physics goals, experimental setups, details of each sub-detector system technical designs, signal and backgground modelings, expected search sensitivities and future prospects, which mark an important step towards the further prototyping and technical demonstrations.

This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene editing is rooted in the diffusion model's large feasible output space (FOS), our framework controls the size of FOS and reduces inconsistency by decomposing the overall editing task into several subtasks, which are then executed progressively on the scene. Within this framework, we design a difficulty-aware subtask decomposition scheduler and an adaptive 3D Gaussian splatting (3DGS) training strategy, ensuring high quality and efficiency in performing each subtask. Extensive evaluation shows that our ProEdit achieves state-of-the-art results in various scenes and challenging editing tasks, all through a simple framework without any expensive or sophisticated add-ons like distillation losses, components, or training procedures. Notably, ProEdit also provides a new way to control, preview, and select the "aggressivity" of editing operation during the editing process., Comment: NeurIPS 2024. Project Page: https://immortalco.github.io/ProEdit/

This paper investigates a novel lossy compression framework operating under logarithmic loss, designed to handle situations where the reconstruction distribution diverges from the source distribution. This framework is especially relevant for applications that require joint compression and retrieval, and in scenarios involving distributional shifts due to processing. We show that the proposed formulation extends the classical minimum entropy coupling framework by integrating a bottleneck, allowing for a controlled degree of stochasticity in the coupling. We explore the decomposition of the Minimum Entropy Coupling with Bottleneck (MEC-B) into two distinct optimization problems: Entropy-Bounded Information Maximization (EBIM) for the encoder, and Minimum Entropy Coupling (MEC) for the decoder. Through extensive analysis, we provide a greedy algorithm for EBIM with guaranteed performance, and characterize the optimal solution near functional mappings, yielding significant theoretical insights into the structural complexity of this problem. Furthermore, we illustrate the practical application of MEC-B through experiments in Markov Coding Games (MCGs) under rate limits. These games simulate a communication scenario within a Markov Decision Process, where an agent must transmit a compressed message from a sender to a receiver through its actions. Our experiments highlight the trade-offs between MDP rewards and receiver accuracy across various compression rates, showcasing the efficacy of our method compared to conventional compression baseline., Comment: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) - Spotlight

Exposure Correction (EC) aims to recover proper exposure conditions for images captured under over-exposure or under-exposure scenarios. While existing deep learning models have shown promising results, few have fully embedded Retinex theory into their architecture, highlighting a gap in current methodologies. Additionally, the balance between high performance and efficiency remains an under-explored problem for exposure correction task. Inspired by Mamba which demonstrates powerful and highly efficient sequence modeling, we introduce a novel framework based on Mamba for Exposure Correction (ECMamba) with dual pathways, each dedicated to the restoration of reflectance and illumination map, respectively. Specifically, we firstly derive the Retinex theory and we train a Retinex estimator capable of mapping inputs into two intermediary spaces, each approximating the target reflectance and illumination map, respectively. This setup facilitates the refined restoration process of the subsequent Exposure Correction Mamba Module (ECMM). Moreover, we develop a novel 2D Selective State-space layer guided by Retinex information (Retinex-SS2D) as the core operator of ECMM. This architecture incorporates an innovative 2D scanning strategy based on deformable feature aggregation, thereby enhancing both efficiency and effectiveness. Extensive experiment results and comprehensive ablation studies demonstrate the outstanding performance and the importance of each component of our proposed ECMamba. Code is available at https://github.com/LowlevelAI/ECMamba., Comment: Accepted by NeurIPS 2024. Retinex-theory, Mamba, Exposure Correction

In this work, we propose a unified representation for Super-Resolution (SR) and Image Compression, termed Factorized Fields, motivated by the shared principles between these two tasks. Both SISR and Image Compression require recovering and preserving fine image details--whether by enhancing resolution or reconstructing compressed data. Unlike previous methods that mainly focus on network architecture, our proposed approach utilizes a basis-coefficient decomposition to explicitly capture multi-scale visual features and structural components in images, addressing the core challenges of both tasks. We first derive our SR model, which includes a Coefficient Backbone and Basis Swin Transformer for generalizable Factorized Fields. Then, to further unify these two tasks, we leverage the strong information-recovery capabilities of the trained SR modules as priors in the compression pipeline, improving both compression efficiency and detail reconstruction. Additionally, we introduce a merged-basis compression branch that consolidates shared structures, further optimizing the compression process. Extensive experiments show that our unified representation delivers state-of-the-art performance, achieving an average relative improvement of 204.4% in PSNR over the baseline in Super-Resolution (SR) and 9.35% BD-rate reduction in Image Compression compared to the previous SOTA., Comment: Project page: https://jayisaking.github.io/FIPER/

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this limitation, we propose LongVU, a spatiotemporal adaptive compression mechanism thats reduces the number of video tokens while preserving visual details of long videos. Our idea is based on leveraging cross-modal query and inter-frame dependencies to adaptively reduce temporal and spatial redundancy in videos. Specifically, we leverage DINOv2 features to remove redundant frames that exhibit high similarity. Then we utilize text-guided cross-modal query for selective frame feature reduction. Further, we perform spatial token reduction across frames based on their temporal dependencies. Our adaptive compression strategy effectively processes a large number of frames with little visual information loss within given context length. Our LongVU consistently surpass existing methods across a variety of video understanding benchmarks, especially on hour-long video understanding tasks such as VideoMME and MLVU. Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance., Comment: Project page: https://vision-cair.github.io/LongVU

The creation of complex 3D scenes tailored to user specifications has been a tedious and challenging task with traditional 3D modeling tools. Although some pioneering methods have achieved automatic text-to-3D generation, they are generally limited to small-scale scenes with restricted control over the shape and texture. We introduce SceneCraft, a novel method for generating detailed indoor scenes that adhere to textual descriptions and spatial layout preferences provided by users. Central to our method is a rendering-based technique, which converts 3D semantic layouts into multi-view 2D proxy maps. Furthermore, we design a semantic and depth conditioned diffusion model to generate multi-view images, which are used to learn a neural radiance field (NeRF) as the final scene representation. Without the constraints of panorama image generation, we surpass previous methods in supporting complicated indoor space generation beyond a single room, even as complicated as a whole multi-bedroom apartment with irregular shapes and layouts. Through experimental analysis, we demonstrate that our method significantly outperforms existing approaches in complex indoor scene generation with diverse textures, consistent geometry, and realistic visual quality. Code and more results are available at: https://orangesodahub.github.io/SceneCraft, Comment: NeurIPS 2024. Code: https://github.com/OrangeSodahub/SceneCraft Project Page: https://orangesodahub.github.io/SceneCraft

Prompt Tuning has been a popular Parameter-Efficient Fine-Tuning method attributed to its remarkable performance with few updated parameters on various large-scale pretrained Language Models (PLMs). Traditionally, each prompt has been considered indivisible and updated independently, leading the parameters increase proportionally as prompt length grows. To address this issue, we propose Adaptive Codebook for Composite and Efficient Prompt Tuning (ACCEPT). In our method, we refer to the concept of product quantization (PQ), allowing all soft prompts to share a set of learnable codebook vectors in each subspace, with each prompt differentiated by a set of adaptive weights. We achieve the superior performance on 17 diverse natural language tasks including natural language understanding (NLU) and question answering (QA) tasks by tuning only 0.3% of parameters of the PLMs. Our approach also excels in few-shot and large model settings, highlighting its significant potential., Comment: EMNLP Findings 2024

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a stochastic optimization approach, dubbed Demon, to guide the denoising process at inference time without backpropagation through reward functions or model retraining. Our approach works by controlling noise distribution in denoising steps to concentrate density on regions corresponding to high rewards through stochastic optimization. We provide comprehensive theoretical and empirical evidence to support and validate our approach, including experiments that use non-differentiable sources of rewards such as Visual-Language Model (VLM) APIs and human judgements. To the best of our knowledge, the proposed approach is the first inference-time, backpropagation-free preference alignment method for diffusion models. Our method can be easily integrated with existing diffusion models without further training. Our experiments show that the proposed approach significantly improves the average aesthetics scores for text-to-image generation., Comment: 36 pages

We study the influence of a rotation on the string tension and the temperature of the confinement-deconfinement transition of gluodynamics by gauge/gravity duality. We explore two distinct approaches, global transformation and local transformation, to introduce rotation and compare the results. It is shown that the string tension extracted from the free energy in the presence of a heavy quarkonium decreases with the increasing angular velocity, while the transition temperature determined by the Polyakov loop increases with increasing angular velocity, which is in line with lattice simulations., Comment: 23 pages, 3 figures

Collinear dipole orders such as ferroelectricity and antiferroelectricity have developed rapidly in last decades. While, the noncollinear dipole orders are rarely touched in solids. Noncollinear dipole orders can provide a route to realize ferrielectricity. Based on first-principles calculations, an inorganic molecular crystal MnO$_3$Cl has been demonstrated to own intrinsic noncollinear ferrielectricity, which originates from the stereo orientations of polar molecules. The large negative piezoelectricity effect ($d_{33}\sim-27$ pC/N) is also predicted. A strong light absorption and moderate optical anisotropy are found for this molecular crystal in the ultraviolet light window. Additionally, by electron doping via hydrogen intercalation, a ferromagnetic polar half-metals can be obtained. Our study here provide a material platform to explore the intriguing physics of noncollinear ferrielectricity and potential applications in devices., Comment: 7 pages, 4 figures

Recently, a photonic alloy with non-trivial topological properties has been proposed, based on the random mixing of Yttrium Iron Garnet (YIG) and magnetized YIG rods. When the doping concentration of magnetized YIG rods is less than one, a chiral edge state (CES) of the topological photonic alloy appears in the frequency range of the non-trivial topological gap of the magnetized YIG crystal. In this work, we surprisingly find that by randomly mixing the Perfect Electric Conductor (PEC) and magnetized YIG rods in a square lattice, the photonic alloy system with appropriate doping concentrations can present CES in special frequency intervals even when both components support the propagation of bulk states. Analyzing the band structure of two components, we noticed a shift between the first trivial bandgap for PEC and the first topological bandgap for magnetized YIG. When calculating the transmission spectrum of the photonic alloy, we discovered that the frequency range for the topological gap gradually opens from the lower limit frequency of the bandgap for PEC to the bandgap for the magnetized YIG rods. The topological gap opening occurs as the doping concentration of magnetized YIG rods increases, creating an effective band alignment effect. Moreover, the topological gap for the photonic alloy is confirmed by calculating the reflection phase winding with the scattering method. Lastly, the gradual appearance of the CES is identified by applying Fourier transformation to real-space electromagnetic fields. Our work broadens the possibilities for flexible topological gap engineering in the photonic alloy system., Comment: 8 pages, 5 figures

Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against distractors is challenging due to the limited discriminative capabilities of prevailing trackers. We present a new visual Prompting mechanism for generic Visual Object Tracking (PiVOT) to address this issue. PiVOT proposes a prompt generation network with the pre-trained foundation model CLIP to automatically generate and refine visual prompts, enabling the transfer of foundation model knowledge for tracking. While CLIP offers broad category-level knowledge, the tracker, trained on instance-specific data, excels at recognizing unique object instances. Thus, PiVOT first compiles a visual prompt highlighting potential target locations. To transfer the knowledge of CLIP to the tracker, PiVOT leverages CLIP to refine the visual prompt based on the similarities between candidate objects and the reference templates across potential targets. Once the visual prompt is refined, it can better highlight potential target locations, thereby reducing irrelevant prompt information. With the proposed prompting mechanism, the tracker can generate improved instance-aware feature maps through the guidance of the visual prompt, thus effectively reducing distractors. The proposed method does not involve CLIP during training, thereby keeping the same training complexity and preserving the generalization capability of the pretrained foundation model. Extensive experiments across multiple benchmarks indicate that PiVOT, using the proposed prompting method can suppress distracting objects and enhance the tracker., Comment: Accepted and to appear in IEEE Transactions on Multimedia

Predicting flight trajectories is a research area that holds significant merit. In this paper, we propose a data-driven learning framework, that leverages the predictive and feature extraction capabilities of the mixture models and seq2seq-based neural networks while addressing prevalent challenges caused by error propagation and dimensionality reduction. After training with this framework, the learned model can improve long-step prediction accuracy significantly given the past trajectories and the context information. The accuracy and effectiveness of the approach are evaluated by comparing the predicted trajectories with the ground truth. The results indicate that the proposed method has outperformed the state-of-the-art predicting methods on a terminal airspace flight trajectory dataset. The trajectories generated by the proposed method have a higher temporal resolution(1 timestep per second vs 0.1 timestep per second) and are closer to the ground truth., Comment: Submitted to AIAA-JAIS

Safety is a critical concern for urban flights of autonomous Unmanned Aerial Vehicles. In populated environments, risk should be accounted for to produce an effective and safe path, known as risk-aware path planning. Risk-aware path planning can be modeled as a Constrained Shortest Path (CSP) problem, aiming to identify the shortest possible route that adheres to specified safety thresholds. CSP is NP-hard and poses significant computational challenges. Although many traditional methods can solve it accurately, all of them are very slow. Our method introduces an additional safety dimension to the traditional A* (called ASD A*), enabling A* to handle CSP. Furthermore, we develop a custom learning-based heuristic using transformer-based neural networks, which significantly reduces the computational load and improves the performance of the ASD A* algorithm. The proposed method is well-validated with both random and realistic simulation scenarios., Comment: AIAA SCITECH 2024 Forum

With the success of Diffusion Models for image generation, the technologies also have revolutionized the aesthetic Quick Response (QR) code generation. Despite significant improvements in visual attractiveness for the beautified codes, their scannabilities are usually sacrificed and thus hinder their practical uses in real-world scenarios. To address this issue, we propose a novel training-free Diffusion-based QR Code generator (DiffQRCoder) to effectively craft both scannable and visually pleasing QR codes. The proposed approach introduces Scanning-Robust Perceptual Guidance (SRPG), a new diffusion guidance for Diffusion Models to guarantee the generated aesthetic codes to obey the ground-truth QR codes while maintaining their attractiveness during the denoising process. Additionally, we present another post-processing technique, Scanning Robust Manifold Projected Gradient Descent (SR-MPGD), to further enhance their scanning robustness through iterative latent space optimization. With extensive experiments, the results demonstrate that our approach not only outperforms other compared methods in Scanning Success Rate (SSR) with better or comparable CLIP aesthetic score (CLIP-aes.) but also significantly improves the SSR of the ControlNet-only approach from 60% to 99%. The subjective evaluation indicates that our approach achieves promising visual attractiveness to users as well. Finally, even with different scanning angles and the most rigorous error tolerance settings, our approach robustly achieves over 95% SSR, demonstrating its capability for real-world applications. Our project page is available at https://jwliao1209.github.io/DiffQRCoder.

Singing voice conversion (SVC) is hindered by noise sensitivity due to the use of non-robust methods for extracting pitch and energy during the inference. As clean signals are key for the source audio in SVC, music source separation preprocessing offers a viable solution for handling noisy audio, like singing with background music (BGM). However, current separating methods struggle to fully remove noise or excessively suppress signal components, affecting the naturalness and similarity of the processed audio. To tackle this, our study introduces RobustSVC, a novel any-to-one SVC framework that converts noisy vocals into clean vocals sung by the target singer. We replace the non-robust feature with a HuBERT-based melody extractor and use adversarial training mechanisms with three discriminators to reduce information leakage in self-supervised representations. Experimental results show that RobustSVC is noise-robust and achieves higher similarity and naturalness than baseline methods in both noisy and clean vocal conditions., Comment: Accepted by ISCSLP 2024

Fuzzy General Grey Cognitive Map (FGGCM) and Fuzzy Grey Cognitive Map (FGCM) are extensions of Fuzzy Cognitive Map (FCM) in terms of uncertainty. FGGCM allows for the processing of general grey number with multiple intervals, enabling FCM to better address uncertain situations. Although the convergence of FCM and FGCM has been discussed in many literature, the convergence of FGGCM has not been thoroughly explored. This paper aims to fill this research gap. First, metrics for the general grey number space and its vector space is given and proved using the Minkowski inequality. By utilizing the characteristic that Cauchy sequences are convergent sequences, the completeness of these two space is demonstrated. On this premise, utilizing Banach fixed point theorem and Browder-Gohde-Kirk fixed point theorem, combined with Lagrange's mean value theorem and Cauchy's inequality, deduces the sufficient conditions for FGGCM to converge to a unique fixed point when using tanh and sigmoid functions as activation functions. The sufficient conditions for the kernels and greyness of FGGCM to converge to a unique fixed point are also provided separately. Finally, based on Web Experience and Civil engineering FCM, designed corresponding FGGCM with sigmoid and tanh as activation functions by modifying the weights to general grey numbers. By comparing with the convergence theorems of FCM and FGCM, the effectiveness of the theorems proposed in this paper was verified. It was also demonstrated that the convergence theorems of FCM are special cases of the theorems proposed in this paper. The study for convergence of FGGCM is of great significance for guiding the learning algorithm of FGGCM, which is needed for designing FGGCM with specific fixed points, lays a solid theoretical foundation for the application of FGGCM in fields such as control, prediction, and decision support systems.

One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most graph-based methods adopt an off-the-shelf detector to locate candidate objects (i.e., regions detected by the object detector), they face two challenges that result in subpar performance: (1) the presence of significant noise caused by numerous irrelevant objects during reasoning, and (2) inaccurate localization outcomes attributed to the provided detector. To address these issues, we introduce a plug-and-adapt module guided by sub-expressions, called dynamic gate constraint (DGC), which can adaptively disable irrelevant proposals and their connections in graphs during reasoning. We further introduce an expression-guided regression strategy (EGR) to refine location prediction. Extensive experimental results on the RefCOCO, RefCOCO+, RefCOCOg, Flickr30K, RefClef, and Ref-reasoning datasets demonstrate the effectiveness of the DGC module and the EGR strategy in consistently boosting the performances of various graph-based REC methods. Without any pretaining, the proposed graph-based method achieves better performance than the state-of-the-art (SOTA) transformer-based methods., Comment: 12 pages to appear in IEEE Transactions on Multimedia

This paper investigates the best known bounds on the quadratic Gaussian distortion-rate-perception function with limited common randomness for the Kullback-Leibler divergence-based perception measure, as well as their counterparts for the squared Wasserstein-2 distance-based perception measure, recently established by Xie et al. These bounds are shown to be nondegenerate in the sense that they cannot be deduced from each other via a refined version of Talagrand's transportation inequality. On the other hand, an improved lower bound is established when the perception measure is given by the squared Wasserstein-2 distance. In addition, it is revealed by exploiting the connection between rate-distortion-perception coding and entropy-constrained scalar quantization that all the aforementioned bounds are generally not tight in the weak perception constraint regime.

Based on the non-extensive statistical mechanics and the gluon polarization tensor obtained from kinetic theory, we derive the longitudinal and transverse gluon self-energies for the quark-gluon plasma. The electric permittivity $\varepsilon$ and the magnetic permeability $\mu_M$ are evaluated from the gluon self-energies through which the real part of the square of the refraction index ${\rm Re}\, n^2$ and the Depine-Lakhtakia index $n_{DL}$ are investigated. The real part of $\varepsilon$ displays a frequency pole $\omega_d=p$, which is just the position of the frequency inflexion of the imaginary part of $\varepsilon$. The non-extensive parameter $q$ significantly affects the real and imaginary parts of $\varepsilon$ in the space-like region $\omega

Cognition refers to the function of information perception and processing, which is the fundamental psychological essence of human beings. It is responsible for reasoning and decision-making, while its evaluation is significant for the aviation domain in mitigating potential safety risks. Existing studies tend to use varied methods for cognitive state evaluation yet have limitations in timeliness, generalisation, and interpretability. Accordingly, this study adopts brain functional connectivity with electroencephalography signals to capture associations in brain regions across multiple subjects for evaluating real-time cognitive states. Specifically, a virtual reality-based flight platform is constructed with multi-screen embedded. Three distinctive cognitive tasks are designed and each has three degrees of difficulty. Thirty subjects are acquired for analysis and evaluation. The results are interpreted through different perspectives, including inner-subject and cross-subject for task-wise and gender-wise underlying brain functional connectivity. Additionally, this study incorporates questionnaire-based, task performance-based, and physiological measure-based approaches to fairly label the trials. A multi-class cognitive state evaluation is further conducted with the active brain connections. Benchmarking results demonstrate that the identified brain regions have considerable influences in cognition, with a multi-class accuracy rate of 95.83% surpassing existing studies. The derived findings bring significance to understanding the dynamic relationships among human brain functional regions, cross-subject cognitive behaviours, and decision-making, which have promising practical application values.

Diffusion Models have emerged as powerful generative models for high-quality image synthesis, with many subsequent image editing techniques based on them. However, the ease of text-based image editing introduces significant risks, such as malicious editing for scams or intellectual property infringement. Previous works have attempted to safeguard images from diffusion-based editing by adding imperceptible perturbations. These methods are costly and specifically target prevalent Latent Diffusion Models (LDMs), while Pixel-domain Diffusion Models (PDMs) remain largely unexplored and robust against such attacks. Our work addresses this gap by proposing a novel attack framework, AtkPDM. AtkPDM is mainly composed of a feature representation attacking loss that exploits vulnerabilities in denoising UNets and a latent optimization strategy to enhance the naturalness of adversarial images. Extensive experiments demonstrate the effectiveness of our approach in attacking dominant PDM-based editing methods (e.g., SDEdit) while maintaining reasonable fidelity and robustness against common defense methods. Additionally, our framework is extensible to LDMs, achieving comparable performance to existing approaches.